mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-09-05 04:00:31 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Zohaib Hassnain
|
071f78c77c | ||
|
Zohaib Hassnain
|
301c4636d7 |
@@ -543,7 +543,7 @@ cuda-pathfinder==1.6.0 \
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
# cuda-bindings
|
||||
cuda-toolkit==13.0.3 \
|
||||
cuda-toolkit==13.0.3.0 \
|
||||
--hash=sha256:d693caaa261214ddd7dbb60d68e71cbed884e68c2be7509778f3051da0b91c3f
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
|
||||
@@ -403,7 +403,7 @@ cuda-pathfinder==1.6.0 \
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
# cuda-bindings
|
||||
cuda-toolkit==13.0.3 \
|
||||
cuda-toolkit==13.0.3.0 \
|
||||
--hash=sha256:d693caaa261214ddd7dbb60d68e71cbed884e68c2be7509778f3051da0b91c3f
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
|
||||
@@ -547,7 +547,7 @@ cuda-pathfinder==1.6.0 \
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
# cuda-bindings
|
||||
cuda-toolkit==13.0.3 \
|
||||
cuda-toolkit==13.0.3.0 \
|
||||
--hash=sha256:d693caaa261214ddd7dbb60d68e71cbed884e68c2be7509778f3051da0b91c3f
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
|
||||
@@ -600,7 +600,7 @@ cuda-pathfinder==1.6.0 \
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
# cuda-bindings
|
||||
cuda-toolkit==13.0.3 \
|
||||
cuda-toolkit==13.0.3.0 \
|
||||
--hash=sha256:d693caaa261214ddd7dbb60d68e71cbed884e68c2be7509778f3051da0b91c3f
|
||||
# via
|
||||
# -c requirements-ci.txt
|
||||
|
||||
@@ -168,5 +168,3 @@ jobs:
|
||||
|
||||
print("Explorer frontend is packaged")
|
||||
PY
|
||||
- name: Run Google ADK Integration Tests
|
||||
run: pytest tests/integrations/google_adk/
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
|
||||
### Graph-Native Infrastructure for Context and Accountable AI Systems
|
||||
|
||||
#### *Developer-first, knowledge infrastructure for AI, alternative to expensive enterprise platforms.*
|
||||
#### *The Open Source Palantir for AI Agents*
|
||||
|
||||
> Ingest your enterprise data, extract what matters, build a Context Graph and knowledge graph (KG), and run graph analytics and causal reasoning over all of it, with full decision provenance baked in. Explainable, traceable, and trustworthy by design.
|
||||
|
||||
@@ -28,13 +28,7 @@
|
||||
|
||||
[](https://github.com/semantica-agi/semantica) [](https://github.com/semantica-agi/semantica/network/members) [](https://github.com/semantica-agi/semantica/graphs/contributors) [](https://pypi.org/project/semantica/) [](https://pepy.tech/project/semantica) [](https://www.python.org/) [](https://opensource.org/licenses/MIT) [](https://github.com/semantica-agi/semantica/actions) [](https://github.com/semantica-agi/semantica/actions/workflows/install-matrix.yml) [](https://scorecard.dev/viewer/?uri=github.com/semantica-agi/semantica) [](https://deepwiki.com/semantica-agi/semantica)
|
||||
|
||||
[](https://getsemantica.ai/)
|
||||
[](https://docs.getsemantica.ai/)
|
||||
[](https://discord.gg/sV34vps5hH)
|
||||
[](https://x.com/BuildSemantica)
|
||||
|
||||
[](https://www.youtube.com/watch?v=QfnNZg4-dZA)
|
||||
|
||||
[](https://getsemantica.ai/) [](https://docs.getsemantica.ai/) [](https://discord.gg/sV34vps5hH) [](https://x.com/BuildSemantica) [](https://www.youtube.com/watch?v=QfnNZg4-dZA) [](CHANGELOG.md)
|
||||
|
||||
```bash
|
||||
pip install semantica
|
||||
@@ -1461,22 +1455,6 @@ semantica-explorer --graph my_graph.json
|
||||
|
||||
For contributor / dev-server setup: **[explorer/README.md: Local Setup Guide](explorer/README.md)**
|
||||
|
||||
The CLI exposes the loaded `ContextGraph`. To also browse and edit an existing
|
||||
`AgentMemory`, create the ASGI app programmatically with both live objects:
|
||||
|
||||
```python
|
||||
from semantica.context import AgentMemory, ContextGraph
|
||||
from semantica.explorer.app import create_app
|
||||
from semantica.explorer.session import GraphSession
|
||||
|
||||
graph = ContextGraph()
|
||||
memory = AgentMemory()
|
||||
app = create_app(session=GraphSession(graph), agent_memory=memory)
|
||||
```
|
||||
|
||||
The Memories workspace is shown only when `agent_memory` is provided. Apply
|
||||
updates the supplied runtime object; it does not add disk persistence.
|
||||
|
||||
---
|
||||
|
||||
## What's New in v0.6.7
|
||||
@@ -1485,7 +1463,7 @@ updates the supplied runtime object; it does not add disk persistence.
|
||||
|
||||
- **First-class LangChain integration** (`semantica[langchain]`): a `BaseRetriever` and `VectorStore` over `HybridSearch`, plus graph/decision-query tools
|
||||
- **SAP OData ingestor** (`semantica[ingest-sap]`): OAuth2/Basic-auth, SSRF-guarded ingestion for Business Partners and Sales Orders, following the existing Snowflake/Databricks connector pattern
|
||||
- **`ContextGraph` gains deterministic, human-editable Markdown round-trip persistence** alongside the existing JSON API, and Explorer can validate and apply Markdown edits to individual graph nodes and AgentMemory items supplied by the hosting application
|
||||
- **`ContextGraph` gains deterministic, human-editable Markdown round-trip persistence** alongside the existing JSON API, and the Explorer graph inspector gains a read-only Markdown content viewer
|
||||
- **`reasoning` gains a structured Action layer**: rule-driven `Assert`/`Retract`/`Call`/`EmitEvent` actions with optional provenance, turning the reasoner into a production-rule system
|
||||
- **`run_shacl_validation` is now a public, documented API**, and a dozen ontology/RDF export correctness fixes land: OWL property/class export, SHACL target-namespace resolution, one canonical confidence datatype across all four RDF formats, reachable OWL-Time reification, JSON-LD default-graph and content-derived document identity, and full metadata passthrough on every RDF serializer
|
||||
- **Security**: Agno's `AgnoKnowledgeGraph.load_urls()` and OpenClaw's MCP tool now route outbound requests through the shared SSRF guard
|
||||
|
||||
@@ -149,25 +149,25 @@ registry.register_plugin("my_plugin", MyPlugin, version="1.0.0")
|
||||
|
||||
<Accordion title="Modularity: use only what you need" icon="puzzle-piece">
|
||||
|
||||
Every component works standalone. `NERExtractor` runs without a graph store. `VectorStore` runs without decision tracking. The framework never forces a full stack instantiation; you pay only for what you import.
|
||||
Every component works standalone. `NERExtractor` runs without a graph store. `VectorStore` runs without decision tracking. The framework never forces a full stack instantiation: you pay only for what you import.
|
||||
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Pluggability: extend without modifying core" icon="plug">
|
||||
|
||||
Custom ingestors, extractors, validators, and exporters follow the same base class pattern. Register them via `PluginRegistry` and they participate in the full pipeline (provenance tracking, retry policies, and parallel execution included) with no changes to core code.
|
||||
Custom ingestors, extractors, validators, and exporters follow the same base class pattern. Register them via `PluginRegistry` and they participate in the full pipeline: provenance tracking, retry policies, and parallel execution included: with no changes to core code.
|
||||
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Provenance by default" icon="link">
|
||||
|
||||
Lineage tracking is built into graph construction at the lowest level. Every node and edge carries a `source_id` pointing back to the originating document, extraction method, and timestamp. There is no opt-in required; provenance is always on.
|
||||
Lineage tracking is built into graph construction at the lowest level. Every node and edge carries a `source_id` pointing back to the originating document, extraction method, and timestamp. There's no opt-in required: provenance is always on.
|
||||
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Configuration over convention" icon="sliders">
|
||||
|
||||
Centralized `ConfigManager` with environment variable overrides. No magic defaults; all behavior is explicit and overridable. Suitable for multi-environment deployments where dev, staging, and production need different backends.
|
||||
Centralized `ConfigManager` with environment variable overrides. No magic defaults: all behavior is explicit and overridable. Suitable for multi-environment deployments where dev, staging, and production need different backends.
|
||||
|
||||
</Accordion>
|
||||
|
||||
@@ -179,13 +179,13 @@ Centralized `ConfigManager` with environment variable overrides. No magic defaul
|
||||
| Characteristic | Mechanism |
|
||||
| :-------------- | :--------- |
|
||||
| **Parallel execution** | `Pipeline(workers=N)` with configurable workers per stage |
|
||||
| **Delta processing** | Incremental graph updates (no full recompute on new data) |
|
||||
| **Delta processing** | Incremental graph updates: no full recompute on new data |
|
||||
| **Streaming ingestion** | Process large corpora without loading everything into memory |
|
||||
| **Backend flexibility** | Swap in-memory NetworkX for Neo4j / FalkorDB with no API changes |
|
||||
| **Deduplication v2** | `blocking_v2`, `hybrid_v2`, `semantic_v2`: up to 7x faster than v1 |
|
||||
| **Indexed search** | Explorer search at 0.004ms on 118k nodes (v0.5.0) |
|
||||
|
||||
- [Modules](/modules): full module documentation with code examples.
|
||||
- [Learning More](/learning-more): configuration reference, performance guide, and troubleshooting.
|
||||
- [Pipeline Reference](/reference/pipeline): pipeline orchestration, workers, and retry policies.
|
||||
- [Core Reference](/reference/core): framework lifecycle, plugin registry, and configuration.
|
||||
- [Modules](/modules) — Full module documentation with code examples.
|
||||
- [Learning More](/learning-more) — Configuration reference, performance guide, and troubleshooting.
|
||||
- [Pipeline Reference](/reference/pipeline) — Pipeline orchestration, workers, and retry policies.
|
||||
- [Core Reference](/reference/core) — Framework lifecycle, plugin registry, and configuration.
|
||||
|
||||
+183
-4
@@ -1,9 +1,14 @@
|
||||
/* ============================================================
|
||||
SEMANTICA DOCS — DESIGN SYSTEM
|
||||
SEMANTICA DOCS — PREMIUM DESIGN SYSTEM
|
||||
Dark-first (#080C10 bg, #10B981 emerald accent)
|
||||
Minimal, static styling — no decorative motion.
|
||||
============================================================ */
|
||||
|
||||
/* ── Keyframes ─────────────────────────────────────────────── */
|
||||
@keyframes pageFadeIn {
|
||||
from { opacity: 0; transform: translateY(6px); }
|
||||
to { opacity: 1; transform: translateY(0); }
|
||||
}
|
||||
|
||||
/* ── Global ─────────────────────────────────────────────────── */
|
||||
html {
|
||||
scroll-behavior: smooth;
|
||||
@@ -24,7 +29,16 @@ html {
|
||||
}
|
||||
::-webkit-scrollbar-thumb:hover { background: rgba(16, 185, 129, 0.4); }
|
||||
|
||||
/* ── Focus rings (accessibility — kept) ─────────────────────── */
|
||||
/* ── Page entrance ──────────────────────────────────────────── */
|
||||
main,
|
||||
article,
|
||||
[class*="content-area"],
|
||||
[class*="ContentArea"],
|
||||
[class*="prose"] {
|
||||
animation: pageFadeIn 0.35s ease both;
|
||||
}
|
||||
|
||||
/* ── Focus rings ─────────────────────────────────────────────── */
|
||||
*:focus-visible {
|
||||
outline: 2px solid rgba(16, 185, 129, 0.55) !important;
|
||||
outline-offset: 3px !important;
|
||||
@@ -45,7 +59,7 @@ h1::after {
|
||||
left: 0;
|
||||
width: 44px;
|
||||
height: 2px;
|
||||
background: #10B981;
|
||||
background: linear-gradient(90deg, #10B981 0%, transparent 100%);
|
||||
border-radius: 1px;
|
||||
}
|
||||
|
||||
@@ -57,6 +71,9 @@ article a,
|
||||
[class*="prose"] a {
|
||||
text-decoration-color: rgba(16, 185, 129, 0.35);
|
||||
text-underline-offset: 3px;
|
||||
transition:
|
||||
text-decoration-color 0.15s ease,
|
||||
color 0.15s ease;
|
||||
}
|
||||
|
||||
article a:hover,
|
||||
@@ -72,6 +89,14 @@ blockquote {
|
||||
padding: 0.9rem 1.2rem !important;
|
||||
font-style: italic;
|
||||
color: rgba(255, 255, 255, 0.68) !important;
|
||||
transition:
|
||||
border-color 0.2s ease,
|
||||
background-color 0.2s ease !important;
|
||||
}
|
||||
|
||||
blockquote:hover {
|
||||
border-left-color: rgba(16, 185, 129, 0.65) !important;
|
||||
background: rgba(16, 185, 129, 0.07) !important;
|
||||
}
|
||||
|
||||
/* ── HR / Divider ────────────────────────────────────────────── */
|
||||
@@ -98,11 +123,165 @@ table thead th {
|
||||
border-bottom: 1px solid rgba(16, 185, 129, 0.18) !important;
|
||||
}
|
||||
|
||||
table tbody tr {
|
||||
transition: background-color 0.15s ease;
|
||||
cursor: default;
|
||||
}
|
||||
|
||||
table tbody tr:hover {
|
||||
background-color: rgba(16, 185, 129, 0.06) !important;
|
||||
}
|
||||
|
||||
table tbody tr:hover td {
|
||||
background-color: transparent !important;
|
||||
}
|
||||
|
||||
table td,
|
||||
table th {
|
||||
transition: background-color 0.15s ease;
|
||||
}
|
||||
|
||||
/* ── CODE BLOCKS ─────────────────────────────────────────────── */
|
||||
pre,
|
||||
[class*="codeblock"],
|
||||
[class*="code-group"],
|
||||
[class*="CodeBlock"],
|
||||
[data-rehype-pretty-code-fragment] {
|
||||
transition:
|
||||
box-shadow 0.25s cubic-bezier(0.4, 0, 0.2, 1),
|
||||
border-color 0.25s cubic-bezier(0.4, 0, 0.2, 1),
|
||||
transform 0.25s cubic-bezier(0.4, 0, 0.2, 1) !important;
|
||||
}
|
||||
|
||||
pre:hover,
|
||||
[class*="codeblock"]:hover,
|
||||
[class*="CodeBlock"]:hover,
|
||||
[data-rehype-pretty-code-fragment]:hover {
|
||||
transform: translateY(-1px) !important;
|
||||
box-shadow:
|
||||
0 0 0 1px rgba(16, 185, 129, 0.18),
|
||||
0 2px 12px rgba(16, 185, 129, 0.06),
|
||||
0 8px 32px rgba(0, 0, 0, 0.2) !important;
|
||||
border-color: rgba(16, 185, 129, 0.2) !important;
|
||||
}
|
||||
|
||||
/* ── CARDS ───────────────────────────────────────────────────── */
|
||||
[class*="card"],
|
||||
[class*="Card"],
|
||||
[data-card],
|
||||
.group\/card {
|
||||
transition:
|
||||
transform 0.22s ease,
|
||||
box-shadow 0.22s ease,
|
||||
border-color 0.22s ease !important;
|
||||
}
|
||||
|
||||
[class*="card"]:hover,
|
||||
[class*="Card"]:hover,
|
||||
[data-card]:hover,
|
||||
.group\/card:hover {
|
||||
transform: translateY(-3px) !important;
|
||||
box-shadow:
|
||||
0 8px 28px rgba(0, 0, 0, 0.18),
|
||||
0 0 0 1px rgba(16, 185, 129, 0.22) !important;
|
||||
border-color: rgba(16, 185, 129, 0.28) !important;
|
||||
}
|
||||
|
||||
/* ── CALLOUTS / ADMONITIONS ──────────────────────────────────── */
|
||||
[class*="callout"],
|
||||
[class*="Callout"],
|
||||
[class*="admonition"] {
|
||||
transition:
|
||||
box-shadow 0.2s ease,
|
||||
border-color 0.2s ease !important;
|
||||
}
|
||||
|
||||
[class*="callout"]:hover,
|
||||
[class*="Callout"]:hover,
|
||||
[class*="admonition"]:hover {
|
||||
box-shadow: 0 2px 16px rgba(16, 185, 129, 0.08) !important;
|
||||
border-color: rgba(16, 185, 129, 0.35) !important;
|
||||
}
|
||||
|
||||
/* ── STEPS ───────────────────────────────────────────────────── */
|
||||
[class*="step"],
|
||||
[class*="Step"] {
|
||||
transition: background-color 0.15s ease !important;
|
||||
}
|
||||
|
||||
[class*="step"]:hover,
|
||||
[class*="Step"]:hover {
|
||||
background-color: rgba(16, 185, 129, 0.04) !important;
|
||||
}
|
||||
|
||||
/* ── INLINE CODE ─────────────────────────────────────────────── */
|
||||
:not(pre) > code {
|
||||
transition:
|
||||
background-color 0.15s ease,
|
||||
color 0.15s ease !important;
|
||||
cursor: text;
|
||||
}
|
||||
|
||||
:not(pre) > code:hover {
|
||||
background-color: rgba(16, 185, 129, 0.16) !important;
|
||||
}
|
||||
|
||||
/* ── NAVIGATION / SIDEBAR ────────────────────────────────────── */
|
||||
nav a,
|
||||
[class*="sidebar"] a,
|
||||
[class*="Sidebar"] a {
|
||||
transition: color 0.15s ease !important;
|
||||
text-decoration: none;
|
||||
position: relative;
|
||||
}
|
||||
|
||||
nav a::after,
|
||||
[class*="sidebar"] a::after,
|
||||
[class*="Sidebar"] a::after {
|
||||
content: "";
|
||||
position: absolute;
|
||||
bottom: -1px;
|
||||
left: 0;
|
||||
width: 0;
|
||||
height: 1px;
|
||||
background: #10B981;
|
||||
transition: width 0.2s ease;
|
||||
}
|
||||
|
||||
nav a:hover::after,
|
||||
[class*="sidebar"] a:hover::after,
|
||||
[class*="Sidebar"] a:hover::after {
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
/* ── TEXT / LIST ITEMS ───────────────────────────────────────── */
|
||||
ul > li,
|
||||
ol > li {
|
||||
border-radius: 3px;
|
||||
transition: background-color 0.12s ease;
|
||||
}
|
||||
|
||||
ul > li:hover,
|
||||
ol > li:hover {
|
||||
background-color: rgba(16, 185, 129, 0.04);
|
||||
}
|
||||
|
||||
/* ── PRIMARY BUTTON / CTA ────────────────────────────────────── */
|
||||
button[class*="primary"],
|
||||
a[class*="primary"],
|
||||
[class*="btn-primary"],
|
||||
[class*="ButtonPrimary"] {
|
||||
transition:
|
||||
box-shadow 0.2s ease,
|
||||
transform 0.2s ease !important;
|
||||
}
|
||||
|
||||
button[class*="primary"]:hover,
|
||||
a[class*="primary"]:hover,
|
||||
[class*="btn-primary"]:hover,
|
||||
[class*="ButtonPrimary"]:hover {
|
||||
box-shadow: 0 0 22px rgba(16, 185, 129, 0.28) !important;
|
||||
transform: translateY(-1px) !important;
|
||||
}
|
||||
|
||||
/* ── HIDE THEME TOGGLE ───────────────────────────────────────── */
|
||||
|
||||
+19
-19
@@ -5,7 +5,7 @@ icon: "compass"
|
||||
---
|
||||
|
||||
<Info>
|
||||
Every module works independently: import only what you need. This page maps developer goals to starting points. The [Module Reference](/modules) covers every module in depth.
|
||||
Every module works independently — import only what you need. This page maps developer goals to starting points. The [Module Reference](/modules) covers every module in depth.
|
||||
</Info>
|
||||
|
||||
## Quick Reference
|
||||
@@ -75,7 +75,7 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
sources = FileIngestor().ingest("report.pdf")
|
||||
parsed = DocumentParser().parse_document("report.pdf")
|
||||
|
||||
# No API key required: pattern-based extraction
|
||||
# No API key required — pattern-based extraction
|
||||
entities = NERExtractor(method="pattern").extract(parsed)
|
||||
relationships = RelationExtractor(method="rule").extract(parsed, entities=entities)
|
||||
|
||||
@@ -89,7 +89,7 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
Pass `method="pattern"` to `NERExtractor` for zero-cost, zero-API-key extraction. Switch to `method="llm"` with any of the supported providers for higher recall.
|
||||
</Tip>
|
||||
|
||||
See the [Quickstart →](/quickstart) for a full pipeline with visualization and export.
|
||||
**Next:** [Quickstart →](/quickstart) — full pipeline with visualization and export.
|
||||
</Tab>
|
||||
|
||||
<Tab title="Build GraphRAG">
|
||||
@@ -109,7 +109,7 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
knowledge_graph=ContextGraph(advanced_analytics=True),
|
||||
)
|
||||
|
||||
# Store facts: retrieval uses both vectors and graph structure
|
||||
# Store facts — retrieval uses both vectors and graph structure
|
||||
context.store("Apple Inc. was co-founded by Steve Jobs in 1976 in Cupertino.")
|
||||
|
||||
# GraphRAG query with multi-hop reasoning trace
|
||||
@@ -206,11 +206,11 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
```python
|
||||
from semantica.export import RDFExporter, ParquetExporter, LPGExporter, ArangoAQLExporter
|
||||
|
||||
# RDF: multiple serialization formats
|
||||
# RDF — multiple serialization formats
|
||||
RDFExporter().export(graph, "graph.ttl", format="turtle")
|
||||
RDFExporter().export(graph, "graph.jsonld", format="jsonld")
|
||||
|
||||
# Parquet: for Spark, BigQuery, Databricks, Snowflake
|
||||
# Parquet — for Spark, BigQuery, Databricks, Snowflake
|
||||
ParquetExporter().export(graph, "output/graph.parquet")
|
||||
|
||||
# Neo4j / Memgraph via Cypher
|
||||
@@ -225,15 +225,15 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
**Next:** [Export module reference →](/reference/export)
|
||||
</Tab>
|
||||
|
||||
<Tab title="MCP: Claude / Cursor">
|
||||
Use Semantica from Claude Desktop, Cursor, VS Code, or any MCP-aware tool; no Python code required after setup. 15 tools are available.
|
||||
<Tab title="MCP — Claude / Cursor">
|
||||
Use Semantica from Claude Desktop, Cursor, VS Code, or any MCP-aware tool — no Python code required after setup. 15 tools available instantly.
|
||||
|
||||
**Step 1: Install**
|
||||
**Step 1 — Install:**
|
||||
```bash
|
||||
pip install semantica
|
||||
```
|
||||
|
||||
**Step 2: Add to your MCP client config**
|
||||
**Step 2 — Add to your MCP client config:**
|
||||
|
||||
<CodeGroup>
|
||||
|
||||
@@ -273,10 +273,10 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
</Tabs>
|
||||
|
||||
|
||||
## Architecture Selection Guidance
|
||||
## Still Unsure?
|
||||
|
||||
<AccordionGroup>
|
||||
<Accordion title="Knowledge graph vs. vector store selection" icon="scale-balanced">
|
||||
<Accordion title="Knowledge graph vs. vector store — which do I need?" icon="scale-balanced">
|
||||
Use a **knowledge graph** (`kg`) when you need structured reasoning, multi-hop traversal, provenance, or compliance audit trails.
|
||||
|
||||
Use a **vector store** (`vector_store`) when you need fast fuzzy similarity search over large text corpora and relationships between items don't matter.
|
||||
@@ -286,12 +286,12 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
See also: [Core Concepts](/concepts)
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Fast local pipeline setup" icon="rocket">
|
||||
<Accordion title="I just want to run something quickly." icon="rocket">
|
||||
Start with the [Quickstart](/quickstart). It builds a complete pipeline (ingest → parse → extract → graph → visualize → export) with no API key required.
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Minimum configuration for existing agents" icon="plug">
|
||||
Add `AgentContext` to equip an existing agent with memory, decision tracking, and precedent search, with no changes to your LLM provider or agent framework required.
|
||||
<Accordion title="I'm adding Semantica to an existing agent — what's the minimum?" icon="plug">
|
||||
Add `AgentContext`. It wraps your existing agent with memory, decision tracking, and precedent search — no changes to your LLM provider or agent framework needed.
|
||||
|
||||
```python
|
||||
from semantica.context import AgentContext, ContextGraph
|
||||
@@ -307,7 +307,7 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
[Context module reference →](/reference/context)
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Minimum stack for compliance-ready pipelines" icon="shield-check">
|
||||
<Accordion title="I need a compliance-ready pipeline — what's the minimum stack?" icon="shield-check">
|
||||
| Layer | Module | Key class |
|
||||
| :---- | :------ | :--------- |
|
||||
| Ingestion | `ingest` | `FileIngestor` |
|
||||
@@ -322,6 +322,6 @@ Pick your goal to see the minimum imports and a working skeleton.
|
||||
|
||||
---
|
||||
|
||||
- [Quickstart](/quickstart): full pipeline in 5 minutes.
|
||||
- [Module Reference](/modules): every module with examples and common chains.
|
||||
- [API Reference](/reference/context): complete class and method documentation.
|
||||
- [Quickstart](/quickstart) — Full pipeline in 5 minutes.
|
||||
- [Module Reference](/modules) — Every module with examples and common chains.
|
||||
- [API Reference](/reference/context) — Complete class and method documentation.
|
||||
|
||||
+3
-3
@@ -43,10 +43,10 @@ icon: "quote-left"
|
||||
|
||||
## Share Your Research
|
||||
|
||||
If you publish research using Semantica, [let us know](https://github.com/semantica-agi/semantica/issues) so we can feature your work.
|
||||
Published research using Semantica? [Let us know](https://github.com/semantica-agi/semantica/issues): we may feature your work.
|
||||
|
||||
|
||||
## See Also
|
||||
|
||||
- [License](/project-license): MIT License details.
|
||||
- [Community](/community): connect with the Semantica community.
|
||||
- [License](/project-license) — MIT License details.
|
||||
- [Community](/community) — Connect with the Semantica community.
|
||||
|
||||
+11
-11
@@ -18,7 +18,7 @@ After installation the following commands are available:
|
||||
| Command | Entry point | What it does |
|
||||
| :------- | :----------- | :------------ |
|
||||
| `semantica` | `semantica.cli:main` | General-purpose CLI for pipeline runs, extraction, and graph operations |
|
||||
| `semantica-server` | `semantica.server:main` | FastAPI/uvicorn REST API server bound to `127.0.0.1:8000` by default (set `SEMANTICA_HOST` to override) |
|
||||
| `semantica-server` | `semantica.server:main` | FastAPI/uvicorn REST API server bound to `0.0.0.0:8000` |
|
||||
| `semantica-worker` | `semantica.worker:main` | Background worker process entry point for Semantica deployments |
|
||||
| `semantica-explorer` | `semantica.explorer:main` | Interactive browser dashboard for knowledge graph exploration |
|
||||
| `semantica-mcp` | `semantica.mcp_server:main` | MCP server (stdio) for Claude Desktop, Cursor, Windsurf, and other MCP clients |
|
||||
@@ -49,11 +49,11 @@ python -c "import semantica; print(semantica.__version__)"
|
||||
|
||||
## When to Use Each Command
|
||||
|
||||
- **semantica**: general-purpose CLI. Use it for one-off pipeline runs, entity extraction, and graph operations from a shell script or CI job.
|
||||
- **semantica-server**: starts the REST API server. Binds to `127.0.0.1:8000` by default; set `SEMANTICA_HOST` to expose beyond localhost. Use this when another service or application needs programmatic access to Semantica over HTTP.
|
||||
- **semantica-worker**: background task processor. Run alongside `semantica-server` when you need async pipeline execution outside the request cycle. Start the server first, then start one or more workers pointing at the same backend.
|
||||
- **semantica-explorer**: launches the browser dashboard. Requires `pip install semantica[explorer]`. Use this to explore a saved knowledge graph interactively. See [Explorer Setup](/explorer-setup).
|
||||
- **semantica-mcp**: runs the MCP server over stdio. Configure it in your MCP client's settings file to expose all 15 tools and 3 resources to Claude Desktop, Cursor, Windsurf, or any MCP-aware client. See [MCP Server](/reference/mcp_server).
|
||||
- **semantica** — The general-purpose CLI. Use it for one-off pipeline runs, entity extraction, and graph operations from a shell script or CI job.
|
||||
- **semantica-server** — Starts the REST API server. Binds to `0.0.0.0:8000`. Use this when another service or application needs programmatic access to Semantica over HTTP.
|
||||
- **semantica-worker** — Background task processor. Run alongside `semantica-server` when you need async pipeline execution outside the request cycle. Start the server first, then start one or more workers pointing at the same backend.
|
||||
- **semantica-explorer** — Launches the browser dashboard. Requires `pip install semantica[explorer]`. Use this to explore a saved knowledge graph interactively. See [Explorer Setup](/explorer-setup).
|
||||
- **semantica-mcp** — Runs the MCP server over stdio. Configure it in your MCP client's settings file to expose all 15 tools and 3 resources to Claude Desktop, Cursor, Windsurf, or any MCP-aware client. See [MCP Server](/reference/mcp_server).
|
||||
|
||||
|
||||
## Usage Examples
|
||||
@@ -61,7 +61,7 @@ python -c "import semantica; print(semantica.__version__)"
|
||||
<Tabs>
|
||||
<Tab title="REST server">
|
||||
```bash
|
||||
# Starts FastAPI + uvicorn on 127.0.0.1:8000 (set SEMANTICA_HOST to change)
|
||||
# Starts FastAPI + uvicorn on 0.0.0.0:8000
|
||||
semantica-server
|
||||
```
|
||||
|
||||
@@ -228,7 +228,7 @@ Install the [Microsoft Visual C++ Redistributable](https://aka.ms/vs/17/release/
|
||||
|
||||
## Next Steps
|
||||
|
||||
- [Explorer Setup](/explorer-setup): build a graph, save it, and launch the browser dashboard.
|
||||
- [MCP Server](/reference/mcp_server): all 15 tools and 3 resources exposed over the MCP protocol.
|
||||
- [Installation](/installation): virtual environments, optional extras, and platform-specific notes.
|
||||
- [Quickstart](/quickstart): end-to-end pipeline walkthrough with working code.
|
||||
- [Explorer Setup](/explorer-setup) — Build a graph, save it, and launch the browser dashboard.
|
||||
- [MCP Server](/reference/mcp_server) — All 15 tools and 3 resources exposed over the MCP protocol.
|
||||
- [Installation](/installation) — Virtual environments, optional extras, and platform-specific notes.
|
||||
- [Quickstart](/quickstart) — End-to-end pipeline walkthrough with working code.
|
||||
|
||||
@@ -66,12 +66,12 @@ Production deployments span regulated and high-stakes industries where AI accoun
|
||||
| :-------- | :---- |
|
||||
| **OpenAI** | GPT-4o, GPT-4, GPT-3.5 |
|
||||
| **Anthropic** | Claude Opus, Sonnet, Haiku |
|
||||
| **Google Gemini** | Gemini Pro and other Gemini models |
|
||||
| **Groq** | LLaMA, Mixtral (fast inference) |
|
||||
| **Google Gemini** |: |
|
||||
| **Groq** | LLaMA, Mixtral: fast inference |
|
||||
| **Ollama** | Fully local, air-gapped |
|
||||
| **HuggingFace** | Transformers-based local LLM models |
|
||||
| **DeepSeek** | deepseek-chat and reasoning models |
|
||||
| **Novita AI** | OpenAI-compatible gateway, DeepSeek-V3.2 default |
|
||||
| **HuggingFace** |: |
|
||||
| **DeepSeek** |: |
|
||||
| **Novita AI** |: |
|
||||
| **LiteLLM** | 100+ model gateway |
|
||||
</Tab>
|
||||
<Tab title="NLP Libraries">
|
||||
@@ -114,7 +114,7 @@ See [Architecture](/architecture#extension-points) for the full extension guide.
|
||||
|
||||
## How to Contribute
|
||||
|
||||
- [Contributing Guide](/contributing-guide): submit code, documentation, tests, or cookbook notebooks.
|
||||
- [GitHub Issues](https://github.com/semantica-agi/semantica/issues): report bugs, request features, or propose integrations.
|
||||
- [Discord](https://discord.gg/sV34vps5hH): share what you're building with the community.
|
||||
- [GitHub Discussions](https://github.com/semantica-agi/semantica/discussions): long-form questions, design discussions, and ideas.
|
||||
- [Contributing Guide](/contributing-guide) — Submit code, documentation, tests, or cookbook notebooks.
|
||||
- [GitHub Issues](https://github.com/semantica-agi/semantica/issues) — Report bugs, request features, or propose integrations.
|
||||
- [Discord](https://discord.gg/sV34vps5hH) — Share what you're building with the community.
|
||||
- [GitHub Discussions](https://github.com/semantica-agi/semantica/discussions) — Long-form questions, design discussions, and ideas.
|
||||
|
||||
+8
-8
@@ -9,10 +9,10 @@ Semantica is built in the open, with contributions from researchers, engineers,
|
||||
|
||||
## Get Help
|
||||
|
||||
- [GitHub Issues](https://github.com/semantica-agi/semantica/issues): file bug reports and feature requests with full context.
|
||||
- [GitHub Discussions](https://github.com/semantica-agi/semantica/discussions): ask questions, share ideas, and discuss design decisions.
|
||||
- [Pull Requests](https://github.com/semantica-agi/semantica/pulls): browse open contributions and submit your own.
|
||||
- [Security Issues](https://github.com/semantica-agi/semantica/security/advisories/new): report vulnerabilities privately (never in public issues).
|
||||
- [GitHub Issues](https://github.com/semantica-agi/semantica/issues) — File bug reports and feature requests with full context.
|
||||
- [GitHub Discussions](https://github.com/semantica-agi/semantica/discussions) — Ask questions, share ideas, and discuss design decisions.
|
||||
- [Pull Requests](https://github.com/semantica-agi/semantica/pulls) — Browse open contributions and submit your own.
|
||||
- [Security Issues](https://github.com/semantica-agi/semantica/security/advisories/new) — Report vulnerabilities privately: never in public issues.
|
||||
|
||||
|
||||
## Community Guidelines
|
||||
@@ -68,7 +68,7 @@ See the [Contributing Guide](/contributing-guide) for the full development workf
|
||||
|
||||
## See Also
|
||||
|
||||
- [Contributing Guide](/contributing-guide): step-by-step guide for submitting PRs and setting up your dev environment.
|
||||
- [Community Projects](/community-projects): projects and integrations built by the community.
|
||||
- [FAQ](/faq): common questions answered.
|
||||
- [Governance](/governance): how the project is run and decisions are made.
|
||||
- [Contributing Guide](/contributing-guide) — Step-by-step guide for submitting PRs and setting up your dev environment.
|
||||
- [Community Projects](/community-projects) — Projects and integrations built by the community.
|
||||
- [FAQ](/faq) — Common questions answered.
|
||||
- [Governance](/governance) — How the project is run and decisions are made.
|
||||
|
||||
+10
-10
@@ -8,16 +8,16 @@ icon: "book-open"
|
||||
New here? Start with [Getting Started](/getting-started) for hands-on examples, then return here for deeper understanding.
|
||||
</Info>
|
||||
|
||||
Semantica transforms unstructured data (documents, web pages, reports, databases) into **knowledge graphs**: structured representations that AI systems can query, reason about, and trace back to sources.
|
||||
Semantica transforms unstructured data: documents, web pages, reports, databases: into **knowledge graphs**: structured representations that AI systems can query, reason about, and trace back to sources.
|
||||
|
||||
At its core, Semantica adds a context and semantic layer on top of your existing AI stack. It doesn't replace LangChain, LlamaIndex, or your LLM provider. It makes their outputs grounded, traceable, and auditable.
|
||||
At its core, Semantica adds a **context and accountability layer** on top of your existing AI stack. It doesn't replace LangChain, LlamaIndex, or your LLM provider: it makes their outputs **grounded**, **traceable**, and **auditable**.
|
||||
|
||||
- **Context Layer.** Knowledge graphs, GraphRAG retrieval, semantic embeddings, and temporal intelligence ground every LLM response in structured, queryable facts.
|
||||
- **Accountability Layer.** Provenance tracking, decision intelligence, conflict detection, and W3C PROV-O compliance make every claim in your AI stack auditable and explainable.
|
||||
- **Extension Layer.** `PluginRegistry` and `MethodRegistry` let you replace or augment any component (ingestors, extractors, reasoning engines, backends) without changing framework code.
|
||||
- **Context Layer** — Knowledge graphs, GraphRAG retrieval, semantic embeddings, and temporal intelligence ground every LLM response in structured, queryable facts.
|
||||
- **Accountability Layer** — Provenance tracking, decision intelligence, conflict detection, and W3C PROV-O compliance make every claim in your AI stack auditable and explainable.
|
||||
- **Extension Layer** — `PluginRegistry` and `MethodRegistry` let you replace or augment any component: ingestors, extractors, reasoning engines, backends: without changing framework code.
|
||||
|
||||
<Warning>
|
||||
**This is system-level explainability, not foundation-model explainability.** Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model. Its internal reasoning or chain-of-thought stays opaque, as it does for any external system. What Semantica explains is *outside* the model: the context and data fed in, the decision produced, its provenance, the relevant relationships, the policies applied, and the full execution trail. In short, Semantica explains and audits *what the AI system did*, not the foundation model's private internal reasoning.
|
||||
**This is system-level explainability, not foundation-model explainability.** Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model — its internal reasoning or chain-of-thought stays opaque, as it does for any external system. What Semantica explains is *outside* the model: the context and data fed in, the decision produced, its provenance, the relevant relationships, the policies applied, and the full execution trail. In short, Semantica explains and audits *what the AI system did*, not the foundation model's private internal reasoning.
|
||||
</Warning>
|
||||
|
||||
## Knowledge Graphs
|
||||
@@ -30,7 +30,7 @@ The foundation of everything in Semantica. A knowledge graph stores information
|
||||
- **Edges (relationships)**: `works_for`, `located_in`, `founded_by`
|
||||
- **Properties**: name, date, confidence score, source URL
|
||||
|
||||
This structure makes knowledge searchable, connectable, and queryable. Critically, it's explainable: every answer can be traced back to the facts and relationships that produced it.
|
||||
This structure makes knowledge **searchable**, **connectable**, **queryable**, and: critically: **explainable**: every answer can be traced back to the facts and relationships that produced it.
|
||||
|
||||
|
||||
## Entity Extraction (NER)
|
||||
@@ -513,6 +513,6 @@ Semantica is designed for extension. Any component: ingestor, extractor, graph b
|
||||
</Accordion>
|
||||
</AccordionGroup>
|
||||
|
||||
- [Quickstart Tutorial](/quickstart): build a full pipeline with code.
|
||||
- [Modules Guide](/modules): every module explained with examples.
|
||||
- [API Reference](/reference/context): complete technical reference.
|
||||
- [Quickstart Tutorial](/quickstart) — Build a full pipeline with code.
|
||||
- [Modules Guide](/modules) — Every module explained with examples.
|
||||
- [API Reference](/reference/context) — Complete technical reference.
|
||||
|
||||
@@ -4,7 +4,7 @@ description: "How to contribute code, documentation, tests, and community suppor
|
||||
icon: "code-pull-request"
|
||||
---
|
||||
|
||||
Contributions of all kinds are welcome (code, documentation, tests, and community support). Every contribution is recognized in release notes and the GitHub contributors list.
|
||||
Contributions of all kinds are welcome: code, documentation, tests, and community support. Every contribution is recognized in release notes and the GitHub contributors list.
|
||||
|
||||
|
||||
## Quick Start
|
||||
@@ -17,15 +17,15 @@ pip install -e ".[dev]"
|
||||
pytest
|
||||
```
|
||||
|
||||
First-time contributors can start with [`good-first-issue`](https://github.com/semantica-agi/semantica/labels/good-first-issue) labeled tickets, which are scoped to be completable in a few hours without deep codebase knowledge.
|
||||
New to the project? Start with [`good-first-issue`](https://github.com/semantica-agi/semantica/labels/good-first-issue) labeled tickets: they're scoped to be completable in a few hours without deep codebase knowledge.
|
||||
|
||||
|
||||
## Ways to Contribute
|
||||
|
||||
- **Code**: fix bugs, implement features, optimize performance, or add new ingestors, parsers, and exporters using the plugin registry.
|
||||
- **Documentation**: fix typos, improve clarity, add missing examples, write tutorials, or keep the API reference accurate as modules evolve.
|
||||
- **Testing**: add test coverage for untested modules or edge cases, reproduce reported bugs with minimal repros, or improve cross-platform reliability.
|
||||
- **Community**: answer questions in GitHub Issues and Discussions, review pull requests with constructive feedback, or share Semantica in blog posts and talks.
|
||||
- **Code** — Fix bugs, implement features, optimize performance, or add new ingestors, parsers, and exporters using the plugin registry.
|
||||
- **Documentation** — Fix typos, improve clarity, add missing examples, write tutorials, or keep the API reference accurate as modules evolve.
|
||||
- **Testing** — Add test coverage for untested modules or edge cases, reproduce reported bugs with minimal repros, or improve cross-platform reliability.
|
||||
- **Community** — Answer questions in GitHub Issues and Discussions, review pull requests with constructive feedback, or share Semantica in blog posts and talks.
|
||||
|
||||
|
||||
## Development Setup
|
||||
@@ -76,7 +76,7 @@ Before submitting a PR, confirm:
|
||||
|
||||
## Code of Conduct
|
||||
|
||||
All contributors are expected to follow the [Contributor Covenant Code of Conduct](https://github.com/semantica-agi/semantica/blob/main/CODE_OF_CONDUCT.md). Be respectful, patient, and constructive, especially toward newcomers. Report violations by opening an issue with the `[CoC]` prefix.
|
||||
All contributors are expected to follow the [Contributor Covenant Code of Conduct](https://github.com/semantica-agi/semantica/blob/main/CODE_OF_CONDUCT.md). Be respectful, patient, and constructive: especially toward newcomers. Report violations by opening an issue with the `[CoC]` prefix.
|
||||
|
||||
|
||||
## Help
|
||||
@@ -85,5 +85,5 @@ All contributors are expected to follow the [Contributor Covenant Code of Conduc
|
||||
- [GitHub Discussions](https://github.com/semantica-agi/semantica/discussions)
|
||||
- [Discord](https://discord.gg/sV34vps5hH)
|
||||
|
||||
- [Community](/community): community guidelines and values.
|
||||
- [Governance](/governance): how decisions are made and the project is run.
|
||||
- [Community](/community) — Community guidelines and values.
|
||||
- [Governance](/governance) — How decisions are made and the project is run.
|
||||
|
||||
+25
-25
@@ -18,43 +18,43 @@ icon: "flask"
|
||||
|
||||
## Featured Recipe
|
||||
|
||||
- **[Your First Knowledge Graph](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/08_Your_First_Knowledge_Graph.ipynb)**: go from raw text to a queryable knowledge graph in 20 minutes. Topics: Extraction, Graph Construction, Visualization · *Beginner*
|
||||
- **[Your First Knowledge Graph](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/08_Your_First_Knowledge_Graph.ipynb)** — Go from raw text to a queryable knowledge graph in 20 minutes. Topics: Extraction, Graph Construction, Visualization · *Beginner*
|
||||
|
||||
|
||||
## Core Tutorials
|
||||
|
||||
Essential guides to master the Semantica framework.
|
||||
|
||||
- **[Welcome to Semantica](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/01_Welcome_to_Semantica.ipynb)**: interactive introduction to the framework's core philosophy and all modules. Topics: Framework Overview, Architecture · *Beginner*
|
||||
- **[Data Ingestion](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/02_Data_Ingestion.ipynb)**: loading data from files, web, databases, streams, feeds, repositories, email, and MCP. Topics: FileIngestor, WebIngestor, DBIngestor · *Beginner*
|
||||
- **[Document Parsing](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/03_Document_Parsing.ipynb)**: extracting clean text from complex formats like PDF, DOCX, and HTML. Topics: OCR, PDF Parsing, Text Extraction · *Beginner*
|
||||
- **[Data Normalization](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/04_Data_Normalization.ipynb)**: pipelines for cleaning, normalizing, and preparing text. Topics: Text Cleaning, Unicode, Formatting · *Beginner*
|
||||
- **[Entity Extraction](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/05_Entity_Extraction.ipynb)**: using NER to identify people, organizations, and custom entities. Topics: NER, spaCy, LLM Extraction · *Beginner*
|
||||
- **[Relation Extraction](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/06_Relation_Extraction.ipynb)**: discovering and classifying relationships between entities. Topics: Relation Classification, Dependency Parsing · *Beginner*
|
||||
- **[Embedding Generation](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/12_Embedding_Generation.ipynb)**: creating and managing vector embeddings for semantic search. Topics: Embeddings, OpenAI, HuggingFace · *Intermediate*
|
||||
- **[Vector Store](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/13_Vector_Store.ipynb)**: setting up vector stores for similarity search and retrieval. *Intermediate*
|
||||
- **[Graph Store](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/09_Graph_Store.ipynb)**: persisting knowledge graphs in Neo4j or FalkorDB. Topics: Neo4j, Cypher, Persistence · *Intermediate*
|
||||
- **[Ontology](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/14_Ontology.ipynb)**: defining domain schemas and ontologies to structure your data. Topics: OWL, RDF, Schema Design · *Intermediate*
|
||||
- **[Seed Data](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/25_Seed_Data.ipynb)**: bootstrapping a knowledge graph from trusted CSV, JSON, database, and API sources before extraction runs. Topics: SeedDataManager, Foundation Graphs · *Intermediate*
|
||||
- **[Semantic Layer Basics](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/26_Semantic_Layer_Basics.ipynb)**: capstone tutorial that combines a knowledge graph, generated ontology, explicit mappings, ontology-aligned RDF, and a SPARQL query. Topics: Semantic Layer, Ontology Mapping, Oxigraph, SPARQL · *Intermediate*
|
||||
- **[Welcome to Semantica](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/01_Welcome_to_Semantica.ipynb)** — Interactive introduction to the framework's core philosophy and all modules. Topics: Framework Overview, Architecture · *Beginner*
|
||||
- **[Data Ingestion](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/02_Data_Ingestion.ipynb)** — Loading data from files, web, databases, streams, feeds, repositories, email, and MCP. Topics: FileIngestor, WebIngestor, DBIngestor · *Beginner*
|
||||
- **[Document Parsing](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/03_Document_Parsing.ipynb)** — Extracting clean text from complex formats like PDF, DOCX, and HTML. Topics: OCR, PDF Parsing, Text Extraction · *Beginner*
|
||||
- **[Data Normalization](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/04_Data_Normalization.ipynb)** — Pipelines for cleaning, normalizing, and preparing text. Topics: Text Cleaning, Unicode, Formatting · *Beginner*
|
||||
- **[Entity Extraction](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/05_Entity_Extraction.ipynb)** — Using NER to identify people, organizations, and custom entities. Topics: NER, spaCy, LLM Extraction · *Beginner*
|
||||
- **[Relation Extraction](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/06_Relation_Extraction.ipynb)** — Discovering and classifying relationships between entities. Topics: Relation Classification, Dependency Parsing · *Beginner*
|
||||
- **[Embedding Generation](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/12_Embedding_Generation.ipynb)** — Creating and managing vector embeddings for semantic search. Topics: Embeddings, OpenAI, HuggingFace · *Intermediate*
|
||||
- **[Vector Store](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/13_Vector_Store.ipynb)** — Setting up vector stores for similarity search and retrieval. *Intermediate*
|
||||
- **[Graph Store](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/09_Graph_Store.ipynb)** — Persisting knowledge graphs in Neo4j or FalkorDB. Topics: Neo4j, Cypher, Persistence · *Intermediate*
|
||||
- **[Ontology](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/14_Ontology.ipynb)** — Defining domain schemas and ontologies to structure your data. Topics: OWL, RDF, Schema Design · *Intermediate*
|
||||
- **[Seed Data](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/25_Seed_Data.ipynb)** — Bootstrapping a knowledge graph from trusted CSV, JSON, database, and API sources before extraction runs. Topics: SeedDataManager, Foundation Graphs · *Intermediate*
|
||||
- **[Semantic Layer Basics](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/26_Semantic_Layer_Basics.ipynb)** — Capstone tutorial that combines a knowledge graph, generated ontology, explicit mappings, ontology-aligned RDF, and a SPARQL query. Topics: Semantic Layer, Ontology Mapping, Oxigraph, SPARQL · *Intermediate*
|
||||
|
||||
|
||||
## Advanced Concepts
|
||||
|
||||
Deep dive into advanced features, customization, and complex workflows.
|
||||
|
||||
- **[Advanced Extraction](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/01_Advanced_Extraction.ipynb)**: custom extractors, LLM-based extraction, and complex pattern matching. Topics: Custom Models, Regex, LLMs · *Advanced*
|
||||
- **[Advanced Graph Analytics](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/02_Advanced_Graph_Analytics.ipynb)**: centrality, community detection, and pathfinding algorithms. Topics: PageRank, Louvain, Shortest Path · *Advanced*
|
||||
- **[Advanced Context Engineering](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb)**: persistent memory system for AI agents using FAISS and Neo4j. Topics: Agent Memory, GraphRAG, Entity Injection · *Advanced*
|
||||
- **[Complete Visualization Suite](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/03_Complete_Visualization_Suite.ipynb)**: interactive network, analytics, and temporal visualizations for graphs. Topics: PyVis, NetworkX, D3.js · *Intermediate*
|
||||
- **[Conflict Resolution](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/17_Conflict_Detection_and_Resolution.ipynb)**: strategies for handling contradictory information from multiple sources. Topics: Truth Discovery, Voting, Confidence · *Advanced*
|
||||
- **[Multi-Format Export](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/05_Multi_Format_Export.ipynb)**: exporting to RDF, OWL, JSON-LD, and NetworkX formats. Topics: Serialization, Interoperability · *Intermediate*
|
||||
- **[Multi-Source Integration](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/06_Multi_Source_Data_Integration.ipynb)**: merging data from disparate sources into a unified graph. Topics: Entity Resolution, Merging, Fusion · *Advanced*
|
||||
- **[Reasoning and Inference](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/08_Reasoning_and_Inference.ipynb)**: using logical reasoning to infer new knowledge from existing facts. Topics: Logic Rules, Inference Engines · *Advanced*
|
||||
- **[Temporal Knowledge Graphs](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/10_Temporal_Knowledge_Graphs.ipynb)**: modeling and querying data that changes over time. Topics: Time Series, Temporal Logic, Allen Algebra · *Advanced*
|
||||
- **[Provenance Tracking](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/22_Provenance_Tracking.ipynb)**: W3C PROV-O-aligned lineage tracking and checksum verification for entities, relationships, and chunks. Topics: PROV-O, Lineage, Checksums, Invalidation · *Advanced*
|
||||
- **[Reasoning Module](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/23_Reasoning.ipynb)**: deriving new knowledge from existing facts with forward chaining, backward chaining, and Datalog strategies. Topics: Reasoner, Datalog, Explanations · *Advanced*
|
||||
- **[Change Management](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/24_Change_Management.ipynb)**: versioning, audit trails, and data-integrity checks for knowledge graphs and ontologies. Topics: ChangeLogEntry, Version Storage, Data Integrity · *Advanced*
|
||||
- **[Advanced Extraction](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/01_Advanced_Extraction.ipynb)** — Custom extractors, LLM-based extraction, and complex pattern matching. Topics: Custom Models, Regex, LLMs · *Advanced*
|
||||
- **[Advanced Graph Analytics](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/02_Advanced_Graph_Analytics.ipynb)** — Centrality, community detection, and pathfinding algorithms. Topics: PageRank, Louvain, Shortest Path · *Advanced*
|
||||
- **[Advanced Context Engineering](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb)** — Production-grade memory system for AI agents using FAISS and Neo4j. Topics: Agent Memory, GraphRAG, Entity Injection · *Advanced*
|
||||
- **[Complete Visualization Suite](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/03_Complete_Visualization_Suite.ipynb)** — Interactive, publication-ready visualizations of your graphs. Topics: PyVis, NetworkX, D3.js · *Intermediate*
|
||||
- **[Conflict Resolution](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/17_Conflict_Detection_and_Resolution.ipynb)** — Strategies for handling contradictory information from multiple sources. Topics: Truth Discovery, Voting, Confidence · *Advanced*
|
||||
- **[Multi-Format Export](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/05_Multi_Format_Export.ipynb)** — Exporting to RDF, OWL, JSON-LD, and NetworkX formats. Topics: Serialization, Interoperability · *Intermediate*
|
||||
- **[Multi-Source Integration](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/06_Multi_Source_Data_Integration.ipynb)** — Merging data from disparate sources into a unified graph. Topics: Entity Resolution, Merging, Fusion · *Advanced*
|
||||
- **[Reasoning and Inference](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/08_Reasoning_and_Inference.ipynb)** — Using logical reasoning to infer new knowledge from existing facts. Topics: Logic Rules, Inference Engines · *Advanced*
|
||||
- **[Temporal Knowledge Graphs](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/10_Temporal_Knowledge_Graphs.ipynb)** — Modeling and querying data that changes over time. Topics: Time Series, Temporal Logic, Allen Algebra · *Advanced*
|
||||
- **[Provenance Tracking](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/22_Provenance_Tracking.ipynb)** — Audit-grade, W3C PROV-O-aligned tracking of where every entity, relationship, and chunk came from. Topics: PROV-O, Lineage, Checksums, Invalidation · *Advanced*
|
||||
- **[Reasoning Module](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/23_Reasoning.ipynb)** — Deriving new knowledge from existing facts with forward chaining, backward chaining, and Datalog strategies. Topics: Reasoner, Datalog, Explanations · *Advanced*
|
||||
- **[Change Management](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/24_Change_Management.ipynb)** — Versioning, audit trails, and data-integrity checks for knowledge graphs and ontologies. Topics: ChangeLogEntry, Version Storage, Data Integrity · *Advanced*
|
||||
|
||||
|
||||
## How to Run
|
||||
|
||||
+29
-30
@@ -2,7 +2,7 @@
|
||||
"$schema": "https://mintlify.com/docs.json",
|
||||
"theme": "mint",
|
||||
"name": "Semantica",
|
||||
"description": "The Context and Semantic Layer for AI in High-Stakes Domains — Context Graphs · Decision Intelligence · Full Provenance",
|
||||
"description": "The Accountability and Context Layer for AI — Context Graphs · Decision Intelligence · Full Provenance",
|
||||
"colors": {
|
||||
"primary": "#10B981",
|
||||
"light": "#10B981",
|
||||
@@ -43,7 +43,7 @@
|
||||
"raiseIssue": true
|
||||
},
|
||||
"metadata": {
|
||||
"og:title": "Semantica — Context & Semantic Layer for AI in High-Stakes Domains",
|
||||
"og:title": "Semantica — Accountability & Context Layer for AI",
|
||||
"og:description": "Build explainable, auditable knowledge graphs with full provenance. Open source. MIT licensed.",
|
||||
"og:image": "/assets/img/semantica-logo.png",
|
||||
"twitter:card": "summary_large_image",
|
||||
@@ -121,23 +121,6 @@
|
||||
"pages": [
|
||||
"vector_stores/pgvector"
|
||||
]
|
||||
},
|
||||
{
|
||||
"group": "FAQ",
|
||||
"pages": [
|
||||
"faq"
|
||||
]
|
||||
},
|
||||
{
|
||||
"group": "Community",
|
||||
"pages": [
|
||||
"community",
|
||||
"community-projects",
|
||||
"contributing-guide",
|
||||
"governance",
|
||||
"citation",
|
||||
"project-license"
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -184,17 +167,7 @@
|
||||
"guides/policy-engine",
|
||||
"guides/visualization",
|
||||
"guides/distance-intelligence",
|
||||
"guides/graph-analytics"
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tab": "API Reference",
|
||||
"groups": [
|
||||
{
|
||||
"group": "Context & Intelligence",
|
||||
"pages": [
|
||||
"guides/graph-analytics",
|
||||
"reference/context",
|
||||
"reference/kg",
|
||||
"reference/temporal",
|
||||
@@ -263,6 +236,32 @@
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tab": "FAQ",
|
||||
"groups": [
|
||||
{
|
||||
"group": "FAQ",
|
||||
"pages": [
|
||||
"faq"
|
||||
]
|
||||
},
|
||||
{
|
||||
"group": "Community",
|
||||
"pages": [
|
||||
"community",
|
||||
"community-projects",
|
||||
"contributing-guide",
|
||||
"governance",
|
||||
"citation",
|
||||
"project-license"
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tab": "Changelog",
|
||||
"href": "https://github.com/semantica-agi/semantica/releases"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
@@ -109,7 +109,7 @@ Explorer loads a graph from a JSON file on disk. You need to create that file fi
|
||||
</Steps>
|
||||
|
||||
<Tip>
|
||||
Pipelines that already produced a saved graph can skip straight to Step 2, provided the file was saved with `ContextGraph.save_to_file()`.
|
||||
Already have a graph from a pipeline run? Skip straight to Step 2. The only requirement is that the file was saved with `ContextGraph.save_to_file()`.
|
||||
</Tip>
|
||||
|
||||
|
||||
@@ -264,7 +264,7 @@ Once running, Explorer exposes a REST API and dashboard for:
|
||||
|
||||
The full endpoint catalogue is documented in the Swagger UI at `/docs` and in the reference page below.
|
||||
|
||||
- [Explorer Reference](/reference/explorer): every REST endpoint, WebSocket events, analytics, and all supported flags.
|
||||
- [CLI Setup](/cli-setup): all five Semantica executables and when to use each one.
|
||||
- [Context Module](/reference/context): full documentation for ContextGraph (build, query, save, and load).
|
||||
- [Quickstart](/quickstart): end-to-end pipeline (ingest → extract → build graph → export).
|
||||
- [Explorer Reference](/reference/explorer) — Every REST endpoint, WebSocket events, analytics, and all supported flags.
|
||||
- [CLI Setup](/cli-setup) — All five Semantica executables and when to use each one.
|
||||
- [Context Module](/reference/context) — Full documentation for ContextGraph: build, query, save, and load.
|
||||
- [Quickstart](/quickstart) — End-to-end pipeline: ingest → extract → build graph → export.
|
||||
|
||||
+7
-7
@@ -27,7 +27,7 @@ icon: "circle-question"
|
||||
|
||||
<Accordion title="What is Semantica?" icon="info-circle">
|
||||
|
||||
Semantica is an open-source framework for building context graphs and decision intelligence layers for AI. It transforms unstructured data (documents, APIs, databases) into structured knowledge graphs with full provenance tracking, making AI systems explainable and auditable.
|
||||
Semantica is an open-source framework for building context graphs and decision intelligence layers for AI. It transforms unstructured data: documents, APIs, databases: into structured knowledge graphs with full provenance tracking, making AI systems explainable and auditable.
|
||||
|
||||
It's not a replacement for LangChain or LlamaIndex. It's the **accountability layer** that goes on top: recording decisions, tracing facts to sources, and making reasoning transparent.
|
||||
|
||||
@@ -46,7 +46,7 @@ It's not a replacement for LangChain or LlamaIndex. It's the **accountability la
|
||||
|
||||
<Accordion title="What makes Semantica different from LangChain or LlamaIndex?" icon="scale-balanced">
|
||||
|
||||
Most frameworks stop at retrieval or generation. Semantica adds an **accountability layer**: every decision is recorded, every fact links to a source, and every reasoning step is explainable. It's designed for environments where you need to audit *why* an AI reached a conclusion, not just what it said.
|
||||
Most frameworks stop at retrieval or generation. Semantica adds an **accountability layer**: every decision is recorded, every fact links to a source, and every reasoning step is explainable. It's designed for environments where you need to audit *why* an AI reached a conclusion: not just what it said.
|
||||
|
||||
Semantica works alongside these frameworks, not against them.
|
||||
|
||||
@@ -54,11 +54,11 @@ Semantica works alongside these frameworks, not against them.
|
||||
|
||||
<Accordion title="Does Semantica explain an LLM's internal reasoning or chain-of-thought?" icon="triangle-exclamation">
|
||||
|
||||
No. This is **system-level explainability, not foundation-model explainability**. Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model. Its internal reasoning or chain-of-thought stays opaque, as it does for any external system.
|
||||
No. This is **system-level explainability, not foundation-model explainability**. Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model — its internal reasoning or chain-of-thought stays opaque, as it does for any external system.
|
||||
|
||||
What Semantica explains is *outside* the model: what context and data were used, what decision was produced, the provenance behind it, the relevant relationships, the policies applied, and the resulting decision trail.
|
||||
|
||||
In short, Semantica explains and audits *what the AI system did*, not the foundation model's private internal reasoning.
|
||||
In short: Semantica explains and audits *what the AI system did* — not the foundation model's private internal reasoning.
|
||||
|
||||
</Accordion>
|
||||
|
||||
@@ -348,6 +348,6 @@ set PYTHONIOENCODING=utf-8
|
||||
|
||||
## Support
|
||||
|
||||
- [Discord](https://discord.gg/sV34vps5hH): community chat and live support.
|
||||
- [GitHub Issues](https://github.com/semantica-agi/semantica/issues): bug reports and feature requests.
|
||||
- [Contributing](/contributing-guide): help improve Semantica.
|
||||
- [Discord](https://discord.gg/sV34vps5hH) — Community chat and live support.
|
||||
- [GitHub Issues](https://github.com/semantica-agi/semantica/issues) — Bug reports and feature requests.
|
||||
- [Contributing](/contributing-guide) — Help improve Semantica.
|
||||
|
||||
+32
-32
@@ -23,16 +23,16 @@ A persistent, queryable graph of everything an agent knows, decides, and reasons
|
||||
A first-class object in Semantica: a recorded agent choice with category, scenario, reasoning, outcome, confidence score, causal chain, and source provenance. Stored and searchable via `context.record_decision()`.
|
||||
|
||||
**Entity**
|
||||
A distinct object or concept in the real world (person, organization, location, event, or abstract concept). Entities are nodes in a knowledge graph, each with typed properties and a source provenance record.
|
||||
A distinct object or concept in the real world: a person, organization, location, event, or abstract concept. Entities are nodes in a knowledge graph, each with typed properties and a source provenance record.
|
||||
|
||||
**Knowledge Graph (KG)**
|
||||
A structured representation of knowledge using entities (nodes) and relationships (edges). Knowledge graphs enable reasoning, querying, semantic search, and traceable inference, unlike flat vector stores.
|
||||
A structured representation of knowledge using entities (nodes) and relationships (edges). Knowledge graphs enable reasoning, querying, semantic search, and traceable inference: unlike flat vector stores.
|
||||
|
||||
**Relationship**
|
||||
A directed, typed connection between two entities (e.g., `works_for`, `located_in`, `founded_by`). Relationships carry confidence scores and provenance back to the source document.
|
||||
A directed, typed connection between two entities: e.g., `works_for`, `located_in`, `founded_by`. Relationships carry confidence scores and provenance back to the source document.
|
||||
|
||||
**Semantic**
|
||||
Relating to meaning in language or logic. Semantic understanding captures context and intent, going beyond keyword matching to understand what text *means*.
|
||||
Relating to meaning in language or logic. Semantic understanding captures context and intent: going beyond keyword matching to understand what text *means*.
|
||||
|
||||
|
||||
## Data Processing
|
||||
@@ -41,19 +41,19 @@ Relating to meaning in language or logic. Semantic understanding captures contex
|
||||
Splitting large documents into smaller pieces while preserving semantic context. Semantica supports recursive, semantic boundary, entity-aware, relation-aware, sliding window, structural, and table-aware chunking strategies.
|
||||
|
||||
**Ingestion**
|
||||
Loading data from external sources (files, databases, APIs, streams) into the pipeline as a unified `SourceDocument`. The first stage in every Semantica pipeline.
|
||||
Loading data from external sources: files, databases, APIs, streams: into the pipeline as a unified `SourceDocument`. The first stage in every Semantica pipeline.
|
||||
|
||||
**Normalization**
|
||||
Standardizing data into a consistent canonical form by converting dates to ISO format, canonicalizing entity names, fixing encoding issues, and stripping noise. Ensures downstream extraction works on clean, consistent text.
|
||||
Standardizing data into a consistent canonical form: converting dates to ISO format, canonicalizing entity names, fixing encoding issues, stripping noise. Ensures downstream extraction works on clean, consistent text.
|
||||
|
||||
**Parsing**
|
||||
Extracting structured text, layout, and metadata from unstructured or semi-structured documents (PDFs, Word files, HTML, PPTX). `DoclingParser` additionally handles multi-column layouts, merged-cell tables, and OCR.
|
||||
Extracting structured text, layout, and metadata from unstructured or semi-structured documents: PDFs, Word files, HTML, PPTX. `DoclingParser` additionally handles multi-column layouts, merged-cell tables, and OCR.
|
||||
|
||||
|
||||
## Artificial Intelligence
|
||||
|
||||
**Abductive Reasoning**
|
||||
Inference to the most plausible explanation for observed facts. One of six reasoning engines in `semantica.reasoning`, returning the most likely hypothesis given available evidence.
|
||||
Inference to the most plausible explanation for observed facts. One of six reasoning engines in `semantica.reasoning`: returns the most likely hypothesis given available evidence.
|
||||
|
||||
**Datalog**
|
||||
A declarative logic programming language for knowledge base queries. Semantica's `DatalogEngine` supports recursive Horn clause rules with bottom-up semi-naive fixpoint semantics. Added in v0.4.0.
|
||||
@@ -62,7 +62,7 @@ A declarative logic programming language for knowledge base queries. Semantica's
|
||||
An advanced RAG approach that combines vector similarity search with knowledge graph traversal. Every LLM response is grounded in structured graph context, with each claim traceable to a source node. Eliminates hallucination without source attribution.
|
||||
|
||||
**Inference**
|
||||
Deriving new facts or conclusions from existing knowledge using logical rules, without the derived facts being explicitly present in the source data.
|
||||
Deriving new facts or conclusions from existing knowledge using logical rules: without the derived facts being explicitly present in the source data.
|
||||
|
||||
**LLM (Large Language Model)**
|
||||
An AI model trained on large text corpora, capable of understanding and generating natural language. Semantica integrates with 8+ LLM providers for entity extraction, relation extraction, and reasoning.
|
||||
@@ -74,7 +74,7 @@ A technique that enhances LLM outputs by retrieving relevant context from a know
|
||||
## Knowledge Graph Components
|
||||
|
||||
**Allen Interval Algebra**
|
||||
A system of 13 relations for describing how two time intervals relate (before, after, meets, overlaps, during, starts, finishes, equals, and their inverses). Supported in `TemporalKnowledgeGraph` since v0.4.0.
|
||||
A system of 13 relations for describing how two time intervals relate: before, after, meets, overlaps, during, starts, finishes, equals, and their inverses. Supported in `TemporalKnowledgeGraph` since v0.4.0.
|
||||
|
||||
**BiTemporalFact**
|
||||
A fact with two independent time dimensions: *valid time* (when it was true in the world) and *transaction time* (when it was recorded in the system). Enables full audit trails for slowly changing data.
|
||||
@@ -86,43 +86,43 @@ A directed connection between two nodes in a graph, representing a typed relatio
|
||||
A vertex in a knowledge graph representing an entity or concept. Nodes carry typed properties, a confidence score, and provenance linking back to the source document.
|
||||
|
||||
**Property**
|
||||
An attribute or characteristic of an entity or relationship, such as name, date, URI, confidence score, or source URL.
|
||||
An attribute or characteristic of an entity or relationship: name, date, URI, confidence score, source URL.
|
||||
|
||||
**Temporal Graph**
|
||||
A knowledge graph where nodes and edges carry `valid_from` / `valid_until` time windows, enabling point-in-time queries and historical state reconstruction.
|
||||
|
||||
**Triplet**
|
||||
The atomic unit of knowledge: a `(subject, predicate, object)` triple (e.g., `(Apple_Inc, founded_by, Steve_Jobs)`). The building block of RDF and SPARQL-based storage.
|
||||
The atomic unit of knowledge: a `(subject, predicate, object)` triple: e.g., `(Apple_Inc, founded_by, Steve_Jobs)`. The building block of RDF and SPARQL-based storage.
|
||||
|
||||
|
||||
## Entity Recognition & Extraction
|
||||
|
||||
**Coreference Resolution**
|
||||
Determining when multiple expressions in text refer to the same entity (e.g., "Apple" and "the company" both referring to Apple Inc.). Handled by `CoreferenceResolver` in `semantica.semantic_extract`.
|
||||
Determining when multiple expressions in text refer to the same entity: e.g., "Apple" and "the company" both referring to Apple Inc. Handled by `CoreferenceResolver` in `semantica.semantic_extract`.
|
||||
|
||||
**Entity Resolution**
|
||||
Determining when two entity mentions across different documents refer to the same real-world entity. Also called entity linking or deduplication. Uses similarity scoring, blocking, and semantic embeddings.
|
||||
|
||||
**Event Detection**
|
||||
Identifying and classifying events in text (acquisitions, partnerships, product launches, regulatory decisions). Handled by `EventDetector` in `semantica.semantic_extract`.
|
||||
Identifying and classifying events in text: acquisitions, partnerships, product launches, regulatory decisions. Handled by `EventDetector` in `semantica.semantic_extract`.
|
||||
|
||||
**Named Entity Recognition (NER)**
|
||||
Identifying and classifying named entities in text into predefined categories (persons, organizations, locations, dates, products, and custom types). Three modes: pattern-based, ML-based, and LLM-based.
|
||||
Identifying and classifying named entities in text into predefined categories: persons, organizations, locations, dates, products, and custom types. Three modes: pattern-based, ML-based, and LLM-based.
|
||||
|
||||
**Relationship Extraction**
|
||||
Identifying and extracting typed semantic relationships between entities (such as `(Google, acquired, DeepMind)`) from raw text.
|
||||
Identifying and extracting typed semantic relationships between entities: e.g., `(Google, acquired, DeepMind)`: from raw text.
|
||||
|
||||
|
||||
## Ontology & Schema
|
||||
|
||||
**Axiom**
|
||||
A statement accepted as true in an ontology, used to define logical constraints (e.g., "every Person must have a name", "Organization can have at most one CEO at a time").
|
||||
A statement accepted as true in an ontology, used to define logical constraints: e.g., "every Person must have a name", "Organization can have at most one CEO at a time".
|
||||
|
||||
**Class**
|
||||
A category or type of entity in an ontology (`Person`, `Organization`, `Location`). Classes form a hierarchy and carry constraints validated by SHACL.
|
||||
A category or type of entity in an ontology: `Person`, `Organization`, `Location`. Classes form a hierarchy and carry constraints validated by SHACL.
|
||||
|
||||
**Ontology**
|
||||
A formal specification of domain concepts, relationships, and constraints, typically expressed in OWL. Semantica can auto-generate ontologies from knowledge graphs or import existing OWL/RDF/Turtle files.
|
||||
A formal specification of domain concepts, relationships, and constraints: typically expressed in OWL. Semantica can auto-generate ontologies from knowledge graphs or import existing OWL/RDF/Turtle files.
|
||||
|
||||
**Ontology Hub**
|
||||
Semantica's v0.5.0 visual browser UI for the full ontology lifecycle: visual class editor, SHACL Studio, alignment authoring, health dashboard, and version-controlled diffs.
|
||||
@@ -140,13 +140,13 @@ A W3C standard for representing controlled vocabularies, taxonomies, and thesaur
|
||||
## Storage & Retrieval
|
||||
|
||||
**Embedding**
|
||||
A dense numerical vector that represents text, images, or other data in a continuous semantic space. Entities with similar meaning produce vectors that are close together, enabling similarity search and semantic matching.
|
||||
A dense numerical vector that represents text, images, or other data in a continuous semantic space. Entities with similar meaning produce vectors that are close together: enabling similarity search and semantic matching.
|
||||
|
||||
**Graph Database**
|
||||
A database optimized for storing and querying graph-structured data using node and edge primitives. Semantica supports Neo4j, FalkorDB, Apache AGE, and Amazon Neptune.
|
||||
|
||||
**Hybrid Search**
|
||||
A retrieval strategy combining vector similarity search with keyword or metadata filtering, achieving higher accuracy than either approach alone.
|
||||
A retrieval strategy combining vector similarity search with keyword or metadata filtering: higher accuracy than either approach alone.
|
||||
|
||||
**Triplet Store**
|
||||
A database designed specifically for storing and querying RDF `(subject, predicate, object)` triples. Semantica supports embedded Oxigraph as well as Blazegraph, Apache Jena, and RDF4J.
|
||||
@@ -158,19 +158,19 @@ A database optimized for storing and searching high-dimensional embedding vector
|
||||
## Graph Analytics
|
||||
|
||||
**Centrality**
|
||||
A measure of a node's importance in the graph. Common metrics include PageRank (link-based importance), betweenness centrality (bridge nodes), and closeness centrality (average distance to all others).
|
||||
A measure of a node's importance in the graph. Common metrics: PageRank (link-based importance), betweenness centrality (bridge nodes), closeness centrality (average distance to all others).
|
||||
|
||||
**Community Detection**
|
||||
Identifying groups of densely connected nodes (clusters that share more internal links than external ones). Used for finding subject communities, fraud rings, and organizational clusters.
|
||||
Identifying groups of densely connected nodes: clusters that share more internal links than external ones. Used for finding subject communities, fraud rings, and organizational clusters.
|
||||
|
||||
**Distance Band**
|
||||
A classification of a node's semantic proximity to a target (`near`, `mid`, or `far`) based on embedding distance thresholds. Part of Distance Intelligence (v0.5.0).
|
||||
A classification of a node's semantic proximity to a target: `near`, `mid`, or `far`, based on embedding distance thresholds. Part of Distance Intelligence (v0.5.0).
|
||||
|
||||
**Distance Intelligence**
|
||||
Semantica's v0.5.0 feature for semantic neighborhood exploration, including N×N distance matrices, ego-mode visualization centered on a single entity, and distance band classification across the graph.
|
||||
Semantica's v0.5.0 feature for semantic neighborhood exploration: N×N distance matrices, ego-mode visualization centered on a single entity, and distance band classification across the graph.
|
||||
|
||||
**PageRank**
|
||||
An algorithm measuring node importance based on the structure of incoming relationships; originally designed for web pages, but applicable to any directed graph.
|
||||
An algorithm measuring node importance based on the structure of incoming relationships: originally designed for web pages, applicable to any directed graph.
|
||||
|
||||
|
||||
## Query Languages & Standards
|
||||
@@ -194,13 +194,13 @@ The W3C query language for RDF data. Semantica's `SparqlReasoner` uses SPARQL fo
|
||||
Handling contradictory facts from multiple sources in the same knowledge graph. Semantica's `ConflictDetector` surfaces conflicts; resolution strategies include prefer-most-recent, prefer-most-reliable, majority-vote, and flag-for-review.
|
||||
|
||||
**Data Provenance**
|
||||
Complete information about the origin, history, and lineage of every fact (source document, extraction method, timestamp, confidence score). W3C PROV-O compliant in Semantica.
|
||||
Complete information about the origin, history, and lineage of every fact: source document, extraction method, timestamp, confidence score. W3C PROV-O compliant in Semantica.
|
||||
|
||||
**Deduplication**
|
||||
Identifying and merging duplicate entity records. Semantica v2 strategies (`blocking_v2`, `hybrid_v2`, `semantic_v2`) are up to 7x faster than v1.
|
||||
|
||||
**W3C PROV-O**
|
||||
The W3C provenance ontology standard. Semantica tracks lineage across all modules in PROV-O compliant format, suitable for HIPAA, SOX, GDPR, and FDA 21 CFR Part 11 compliance.
|
||||
The W3C provenance ontology standard. Semantica tracks lineage across all modules in PROV-O compliant format: suitable for HIPAA, SOX, GDPR, and FDA 21 CFR Part 11 compliance.
|
||||
|
||||
|
||||
## Security Terms
|
||||
@@ -214,7 +214,7 @@ A vulnerability in XML parsers that allows attackers to read arbitrary files or
|
||||
|
||||
## See Also
|
||||
|
||||
- [Core Concepts](/concepts): deeper explanation of key ideas with code examples.
|
||||
- [Getting Started](/getting-started): first working examples with no prior graph experience required.
|
||||
- [Modules Guide](/modules): all 27 modules explained with code and pipeline chains.
|
||||
- [API Reference](/reference/context): complete technical reference for every class and method.
|
||||
- [Core Concepts](/concepts) — Deeper explanation of key ideas with code examples.
|
||||
- [Getting Started](/getting-started) — First working examples: no prior graph experience required.
|
||||
- [Modules Guide](/modules) — All 27 modules explained with code and pipeline chains.
|
||||
- [API Reference](/reference/context) — Complete technical reference for every class and method.
|
||||
|
||||
+10
-10
@@ -9,9 +9,9 @@ icon: "scale-balanced"
|
||||
|
||||
## Roles
|
||||
|
||||
- **Maintainers**: Semantica team. Review and merge PRs, manage releases and code quality, set project direction and community standards.
|
||||
- **Contributors**: submit code, documentation, and bug reports. Help with issues and reviews. Recognized in [CONTRIBUTORS.md](https://github.com/semantica-agi/semantica/blob/main/CONTRIBUTORS.md).
|
||||
- **Community Members**: use Semantica, provide feedback, share use cases, and participate in GitHub Discussions and Discord.
|
||||
- **Maintainers** — Semantica team: review and merge PRs, manage releases and code quality, set project direction and community standards.
|
||||
- **Contributors** — Submit code, documentation, and bug reports. Help with issues and reviews. Recognized in [CONTRIBUTORS.md](https://github.com/semantica-agi/semantica/blob/main/CONTRIBUTORS.md).
|
||||
- **Community Members** — Use Semantica, provide feedback, share use cases, and participate in GitHub Discussions and Discord.
|
||||
|
||||
|
||||
## Decision Process
|
||||
@@ -65,11 +65,11 @@ Semantica follows **Semantic Versioning** (`MAJOR.MINOR.PATCH`):
|
||||
|
||||
## Project Goals
|
||||
|
||||
- **Usability**: easy to use and understand with sensible defaults, clear documentation, and minimal ceremony.
|
||||
- **Reliability**: production-ready quality tested across Python versions, platforms, and real-world workloads.
|
||||
- **Performance**: efficient and scalable from single-machine notebooks to enterprise graph databases.
|
||||
- **Extensibility**: easy to extend with plugins and custom modules via the `PluginRegistry` pattern.
|
||||
- **Community**: welcoming and inclusive. All backgrounds and experience levels contribute and are recognized.
|
||||
- **Usability** — Easy to use and understand: sensible defaults, clear documentation, minimal ceremony.
|
||||
- **Reliability** — Production-ready quality: tested across Python versions, platforms, and real-world workloads.
|
||||
- **Performance** — Efficient and scalable: from single-machine notebooks to enterprise graph databases.
|
||||
- **Extensibility** — Easy to extend with plugins and custom modules via the `PluginRegistry` pattern.
|
||||
- **Community** — Welcoming and inclusive: all backgrounds and experience levels contribute and are recognized.
|
||||
|
||||
|
||||
## License
|
||||
@@ -79,5 +79,5 @@ MIT License: see [LICENSE](https://github.com/semantica-agi/semantica/blob/main/
|
||||
|
||||
## See Also
|
||||
|
||||
- [Contributing](/contributing-guide): how to submit changes.
|
||||
- [Community](/community): community guidelines and channels.
|
||||
- [Contributing](/contributing-guide) — How to submit changes.
|
||||
- [Community](/community) — Community guidelines and channels.
|
||||
|
||||
@@ -102,8 +102,9 @@ The `Decision` dataclass that backs this node has the following fields — these
|
||||
from semantica.context import Decision
|
||||
from datetime import datetime
|
||||
|
||||
# Constructing a Decision explicitly (alternative to record_decision)
|
||||
d = Decision(
|
||||
decision_id = None, # required arg — None/"" auto-generates a UUID
|
||||
decision_id = "dec_001", # UUID — auto-generated if omitted via record_decision
|
||||
category = "threat_classification",
|
||||
scenario = "Unattributed C2 cluster",
|
||||
reasoning = "Infrastructure overlaps APT29 ASN",
|
||||
@@ -116,29 +117,9 @@ d = Decision(
|
||||
valid_until = "2025-09-30T23:59:59", # ISO datetime
|
||||
metadata = {"source_feed": "isac_partner_b"},
|
||||
)
|
||||
graph.add_decision(d)
|
||||
```
|
||||
|
||||
To actually store a decision built this way, pass its fields to `ContextGraph.add_decision()` as keyword arguments — this is the alternative to `record_decision()` for cases where you want `valid_from`/`valid_until` or extra metadata fields alongside the required ones:
|
||||
|
||||
```python
|
||||
decision_id = graph.add_decision(
|
||||
category = "threat_classification",
|
||||
scenario = "Unattributed C2 cluster",
|
||||
reasoning = "Infrastructure overlaps APT29 ASN",
|
||||
outcome = "classified_as_apt29_cluster",
|
||||
confidence = 0.88, # float 0.0–1.0
|
||||
decision_maker = "cti_pipeline_v2",
|
||||
# optional fields:
|
||||
valid_from = "2025-07-01T00:00:00", # ISO datetime
|
||||
valid_until = "2025-09-30T23:59:59", # ISO datetime
|
||||
source_feed = "isac_partner_b", # extra kwargs are stored as metadata
|
||||
)
|
||||
```
|
||||
|
||||
<Warning>
|
||||
Only pass keyword arguments to `add_decision()`, not a pre-built `Decision` object. `add_decision(Decision(...))` stores the node directly and skips the indexing step that `record_decision()` performs, so the decision becomes invisible to `find_precedents()`, `get_causal_chain()`, and `get_decision_insights()`, and `trace_decision_causality()` raises `ValueError` if you call it on one. The keyword-argument form above does not have this problem — it delegates to `record_decision()` internally. Note that, like `record_decision()`, it always generates its own `decision_id` (returned from the call); there is no way to force a specific ID.
|
||||
</Warning>
|
||||
|
||||
## Searching Precedents Before Deciding
|
||||
|
||||
Before making a significant call, the system should search past decisions for similar scenarios. This is how you prevent the same cluster being classified differently across two agent runs — the second agent finds the first agent's decision and uses it as a prior.
|
||||
@@ -156,7 +137,7 @@ for p in precedents:
|
||||
print(" Similarity: {:.3f}".format(p.metadata.get("similarity_score", 0)))
|
||||
```
|
||||
|
||||
Hybrid search blends two signals: lexical overlap between the query and each decision's `scenario`, `reasoning`, and `entities` text (weight 0.7 — word-level Jaccard similarity, with a character-bigram fallback for CJK-style queries), and structural similarity based on how many other nodes each decision connects to in the graph (weight 0.3, only computed when the graph was built with `advanced_analytics=True`). The result is a ranked list of `Decision` objects, filtered to those scoring at least `similarity_threshold` (default 0.5) — because the match is lexical rather than embedding-based, precedents phrased very differently from the query may not surface even if they describe a similar scenario.
|
||||
Hybrid search blends two signals: semantic similarity over the `scenario` and `reasoning` text (weight 0.7), and structural graph proximity via Node2Vec embeddings (weight 0.3). The result is a ranked list of `Decision` objects — the most similar past decisions float to the top regardless of how differently they were phrased.
|
||||
|
||||
## Building a Causal Chain
|
||||
|
||||
@@ -281,13 +262,8 @@ d = Decision(
|
||||
)
|
||||
|
||||
if engine.check_compliance(d, "cti_confidence_gate"):
|
||||
# Pass fields as kwargs, not the Decision object itself — see the
|
||||
# warning above. add_decision() generates its own decision_id.
|
||||
decision_id = graph.add_decision(
|
||||
category=d.category, scenario=d.scenario, reasoning=d.reasoning,
|
||||
outcome=d.outcome, confidence=d.confidence, decision_maker=d.decision_maker,
|
||||
)
|
||||
engine.record_policy_application(decision_id, "cti_confidence_gate", "1.0")
|
||||
graph.add_decision(d)
|
||||
engine.record_policy_application(d.decision_id, "cti_confidence_gate", "1.0")
|
||||
print("Decision recorded — policy compliant.")
|
||||
else:
|
||||
print("Decision blocked — confidence 0.62 below policy minimum 0.80.")
|
||||
@@ -614,7 +590,7 @@ if engine.check_compliance(d, "lending_policy_v3"):
|
||||
decision_maker=d.decision_maker,
|
||||
)
|
||||
graph.add_causal_relationship(stress_id, loan_id, "INFLUENCED")
|
||||
engine.record_policy_application(loan_id, "lending_policy_v3", "3.0")
|
||||
engine.record_policy_application(d.decision_id, "lending_policy_v3", "3.0")
|
||||
print("Loan decision recorded — policy compliant.")
|
||||
|
||||
# SR 11-7 explainability report
|
||||
|
||||
+42
-55
@@ -1,9 +1,9 @@
|
||||
---
|
||||
title: "GraphRAG: Graph-Augmented Retrieval"
|
||||
title: "GraphRAG — Graph-Augmented Retrieval"
|
||||
description: "Go beyond vector search: retrieve facts, trace reasoning paths, and ground LLM responses in your knowledge graph."
|
||||
---
|
||||
|
||||
GraphRAG combines vector similarity with knowledge graph traversal so retrieval finds structurally connected facts, not just text that sounds related. When a `ContextGraph` is attached to `AgentContext`, every retrieval call automatically blends semantic search with multi-hop graph expansion, and `query_with_reasoning()` returns an auditable reasoning path alongside the LLM answer.
|
||||
GraphRAG combines vector similarity with knowledge graph traversal so retrieval finds structurally connected facts, not just text that sounds related. When a `ContextGraph` is attached to `AgentContext`, every retrieval call automatically blends semantic search with multi-hop graph expansion — and `query_with_reasoning()` returns an auditable reasoning path alongside the LLM answer.
|
||||
|
||||
## What Is GraphRAG?
|
||||
|
||||
@@ -11,7 +11,7 @@ GraphRAG (Graph-Augmented Retrieval-Augmented Generation) enhances traditional R
|
||||
|
||||
**GraphRAG vs. traditional vector-only RAG:** Vector RAG finds documents similar to your query text. GraphRAG finds documents similar to your query AND documents connected to those through entity relationships, even if they don't mention your query terms directly.
|
||||
|
||||
**The role of graph traversal:** Starting from entities found in vector-similar documents, GraphRAG expands outward through relationship edges to discover related facts. This reveals connections that pure text similarity would miss, like finding that a threat actor targets healthcare by following the path: Actor → Tool → Victim Organization → Industry Sector.
|
||||
**The role of graph traversal:** Starting from entities found in vector-similar documents, GraphRAG expands outward through relationship edges to discover related facts. This reveals connections that pure text similarity would miss — like finding that a threat actor targets healthcare by following the path: Actor → Tool → Victim Organization → Industry Sector.
|
||||
|
||||
## Why Use GraphRAG?
|
||||
|
||||
@@ -96,7 +96,7 @@ context = AgentContext(
|
||||
)
|
||||
```
|
||||
|
||||
Now ingest your documents. `store()` with `extract_entities=True` runs the full extraction pipeline internally (Named Entity Recognition, relation extraction, and entity linking) and populates both the vector index and the graph simultaneously:
|
||||
Now ingest your documents. `store()` with `extract_entities=True` runs the full extraction pipeline internally — Named Entity Recognition (NER), relation extraction, and entity linking — and populates both the vector index and the graph simultaneously:
|
||||
|
||||
```python
|
||||
intel_documents = [
|
||||
@@ -132,17 +132,16 @@ stats = context.store(
|
||||
print("Graph built: {} nodes, {} edges".format(
|
||||
stats["graph_nodes"], stats["graph_edges"]
|
||||
))
|
||||
# Graph built: 18 nodes, 14 edges
|
||||
# Nodes: APT29, HAMMERTOSS, NATO, LifeCare, AS59796, CISA Sector 6, ...
|
||||
# Edges: deployed, observed_on, classified_as, targets, operates_in, ...
|
||||
```
|
||||
|
||||
`store()` returns a dict with `stored_count`, `memory_ids`, `graph_nodes`, and
|
||||
`graph_edges`. The extracted nodes (APT29, HAMMERTOSS, LifeCare, AS59796, …) and
|
||||
edges (`deployed`, `observed_on`, `classified_as`, …) now span all four documents.
|
||||
|
||||
The graph now contains a connected subgraph linking APT29 to healthcare infrastructure across four document boundaries, something that would be invisible to a pure vector search.
|
||||
The graph now contains a connected subgraph linking APT29 to healthcare infrastructure across four document boundaries — something that would be invisible to a pure vector search.
|
||||
|
||||
## Retrieving the relevant subgraph
|
||||
|
||||
With the graph populated, a plain `retrieve()` call already does more than vector search. When `use_graph=True`, the retriever seeds the graph traversal from the top-k vector matches and expands outward by following edges. Expansion depth is set once, by `max_expansion_hops` on the `AgentContext` constructor:
|
||||
With the graph populated, a plain `retrieve()` call already does more than vector search. When `use_graph=True`, the retriever seeds the graph traversal from the top-k vector matches and expands outward by following edges, collecting connected facts within `max_hops`:
|
||||
|
||||
```python
|
||||
results = context.retrieve(
|
||||
@@ -150,6 +149,7 @@ results = context.retrieve(
|
||||
use_graph=True,
|
||||
max_results=10,
|
||||
expand_graph=True,
|
||||
max_hops=3,
|
||||
)
|
||||
|
||||
for r in results:
|
||||
@@ -169,25 +169,17 @@ Notice the top results: while pure vector search might rank connected facts lowe
|
||||
When you know specifically which entity you want to anchor the traversal to, pass `anchor_node`:
|
||||
|
||||
```python
|
||||
# Anchor on APT29 explicitly: proximity scores are calculated from this node
|
||||
# Anchor on APT29 explicitly — proximity scores are calculated from this node
|
||||
apt29_intel = context.retrieve(
|
||||
"C2 infrastructure beaconing patterns",
|
||||
use_graph=True,
|
||||
anchor_node="APT29",
|
||||
proximity_weight=0.7, # strongly favour nodes close to APT29
|
||||
max_hops=3, # with an anchor, this bounds the proximity radius
|
||||
max_hops=3,
|
||||
max_results=8,
|
||||
)
|
||||
```
|
||||
|
||||
<Note>
|
||||
`max_hops` on `retrieve()` only takes effect when `anchor_node` is set: it
|
||||
bounds the proximity radius used for scoring and drops results farther than
|
||||
`max_hops` from the anchor. Without an `anchor_node` it is ignored. It does
|
||||
**not** change how far graph expansion reaches: that is fixed by
|
||||
`max_expansion_hops` on the constructor.
|
||||
</Note>
|
||||
|
||||
## Getting a grounded LLM answer with a reasoning path
|
||||
|
||||
`retrieve()` gives you the grounded context. `query_with_reasoning()` goes one step further: it passes that subgraph context to an LLM and returns the answer together with the multi-hop path the retrieval system traced through the graph. That path is your audit trail.
|
||||
@@ -195,7 +187,7 @@ apt29_intel = context.retrieve(
|
||||
```python
|
||||
from semantica.llms import LiteLLM
|
||||
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
|
||||
result = context.query_with_reasoning(
|
||||
"What are APT29's known TTPs against healthcare infrastructure, "
|
||||
@@ -205,7 +197,7 @@ result = context.query_with_reasoning(
|
||||
max_hops=3,
|
||||
)
|
||||
|
||||
# The LLM answer, grounded in graph-retrieved context, not training memory
|
||||
# The LLM answer — grounded in graph-retrieved context, not training memory
|
||||
print(result["response"])
|
||||
|
||||
# The multi-hop trace: APT29 → deployed → HAMMERTOSS → observed_on → LifeCare → ...
|
||||
@@ -221,7 +213,7 @@ for src in result["sources"]:
|
||||
print(" [{:.3f}] {}".format(src["score"], src["content"][:80]))
|
||||
```
|
||||
|
||||
The `reasoning_path` field is what separates GraphRAG from a black-box LLM call. When an analyst asks "how do you know APT29 targeted healthcare?", you can show them the exact traversal the system made across your own documents, not a claim the model generated from training data.
|
||||
The `reasoning_path` field is what separates GraphRAG from a black-box LLM call. When an analyst asks "how do you know APT29 targeted healthcare?", you can show them the exact traversal the system made across your own documents — not a claim the model generated from training data.
|
||||
|
||||
The full return structure from `query_with_reasoning()`:
|
||||
|
||||
@@ -240,11 +232,11 @@ The full return structure from `query_with_reasoning()`:
|
||||
|
||||
<Tabs>
|
||||
|
||||
<Tab title="Defense: CTI/Threat">
|
||||
<Tab title="Defense — CTI/Threat">
|
||||
|
||||
Multi-INT intelligence fusion: OSINT threat feeds, NVD CVE data, and HUMINT summaries ingested into a single graph, then queried with multi-hop reasoning to trace C2 infrastructure chains and attribute campaigns to specific actors.
|
||||
|
||||
In classified environments the graph can be partitioned by data handling caveat: each `AgentContext` operates over the subset of documents cleared for the querying user. The `reasoning_path` output doubles as a sanitisable audit trail for downgraded reporting.
|
||||
In classified environments the graph can be partitioned by data handling caveat — each `AgentContext` operates over the subset of documents cleared for the querying user. The `reasoning_path` output doubles as a sanitisable audit trail for downgraded reporting.
|
||||
|
||||
```python
|
||||
from semantica.context import AgentContext, ContextGraph
|
||||
@@ -281,7 +273,7 @@ context.store(
|
||||
link_entities=True,
|
||||
)
|
||||
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
result = context.query_with_reasoning(
|
||||
"Trace the C2 infrastructure chain for APT29 operations targeting "
|
||||
"ITAR-controlled contractors in 2025. Include IP ranges, ASNs, and TTPs.",
|
||||
@@ -308,11 +300,11 @@ proximate = context.retrieve(
|
||||
|
||||
</Tab>
|
||||
|
||||
<Tab title="Security: SOC/Incident">
|
||||
<Tab title="Security — SOC/Incident">
|
||||
|
||||
Security operations: real-time alert triage against a graph containing hosts, CVEs, user accounts, runbooks, and historical incidents. GraphRAG retrieves the relevant runbook and similar past incidents in a single call, reducing mean-time-to-respond.
|
||||
|
||||
The `decision_tracking=True` flag records every triage query as an auditable decision, with the full context that was provided to the LLM. That's essential for post-incident review and SOC metrics.
|
||||
The `decision_tracking=True` flag records every triage query as an auditable decision, with the full context that was provided to the LLM — essential for post-incident review and SOC metrics.
|
||||
|
||||
```python
|
||||
from semantica.context import AgentContext, ContextGraph
|
||||
@@ -351,7 +343,7 @@ Parent: wmiprvse.exe
|
||||
Sigma match: T1053.005 Scheduled Task/Job
|
||||
"""
|
||||
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
triage = soc_context.query_with_reasoning(
|
||||
"Triage this SIEM alert and identify the correct response runbook:\n{}".format(alert_text),
|
||||
llm_provider=llm,
|
||||
@@ -377,7 +369,7 @@ for inc in similar:
|
||||
|
||||
</Tab>
|
||||
|
||||
<Tab title="Life Science: Clinical/Pharma">
|
||||
<Tab title="Life Science — Clinical/Pharma">
|
||||
|
||||
Clinical decision support: FDA drug labels, clinical guidelines, and trial summaries ingested into a graph where drug-enzyme-metabolite-interaction chains become traversable paths. A three-hop query (drug → enzyme → metabolite → contraindication) surfaces interaction risks that no single document would make explicit.
|
||||
|
||||
@@ -425,7 +417,7 @@ Patient: 68F, AF, CKD stage 3b (eGFR 32). On warfarin (INR target 2.0–3.0).
|
||||
Presenting for elective hip replacement. Concurrent: amiodarone 200mg, atorvastatin 40mg.
|
||||
"""
|
||||
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
answer = clinical_context.query_with_reasoning(
|
||||
"What is the evidence-based warfarin bridging protocol for this patient "
|
||||
"given CKD and amiodarone interaction risk?\n\n{}".format(patient_context),
|
||||
@@ -451,7 +443,7 @@ contra_chain = clinical_context.retrieve(
|
||||
|
||||
</Tab>
|
||||
|
||||
<Tab title="Banking: Risk/Compliance">
|
||||
<Tab title="Banking — Risk/Compliance">
|
||||
|
||||
Regulatory compliance: Basel III (CRE20), BCBS 239, SR 11-7, and EBA IRRBB guidelines ingested as a graph where regulation articles cross-reference each other as edges. Multi-hop queries traverse those cross-references automatically, so a question about commercial real estate RWA pulls the relevant CRE20 paragraphs and the BCBS 239 data quality requirements that govern their calculation in a single call.
|
||||
|
||||
@@ -474,17 +466,12 @@ compliance_context = AgentContext(
|
||||
retention_days=2555, # 7-year regulatory retention
|
||||
)
|
||||
|
||||
# In production the text comes from a parsed file, e.g. FileIngestor().ingest_file(path).text;
|
||||
# inline strings here for brevity
|
||||
basel_cre20_text = (
|
||||
"CRE20.32: For income-producing real estate where repayment depends on "
|
||||
"property cash flows, RWA = exposure × risk weight, where risk weight "
|
||||
"is determined by LTV bucket per Table CRE20.3..."
|
||||
)
|
||||
bcbs239_text = (
|
||||
"Principle 3: Risk data should be accurate and have a single authoritative source. "
|
||||
"Where data is aggregated across systems, reconciliation must be documented..."
|
||||
)
|
||||
# In production these come from ingest_file() — shown as strings here for brevity
|
||||
basel_cre20_text = "CRE20.32: For income-producing real estate where repayment depends on "
|
||||
"property cash flows, RWA = exposure × risk weight, where risk weight "
|
||||
"is determined by LTV bucket per Table CRE20.3..."
|
||||
bcbs239_text = "Principle 3: Risk data should be accurate and have a single authoritative source. "
|
||||
"Where data is aggregated across systems, reconciliation must be documented..."
|
||||
|
||||
compliance_context.store(
|
||||
[
|
||||
@@ -495,7 +482,7 @@ compliance_context.store(
|
||||
extract_relationships=True,
|
||||
)
|
||||
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
answer = compliance_context.query_with_reasoning(
|
||||
"Under Basel III CRE20, what are the RWA calculation requirements for "
|
||||
"commercial real estate exposures with LTV > 80%? "
|
||||
@@ -509,7 +496,7 @@ print(answer["response"])
|
||||
print("Regulatory sources cited: {}".format(answer["num_sources"]))
|
||||
print("Confidence: {:.1%}".format(answer["confidence"]))
|
||||
|
||||
# The reasoning path is the audit log: show it to the regulator
|
||||
# The reasoning path is the audit log — show it to the regulator
|
||||
print("\n--- Reasoning Path (audit log) ---")
|
||||
print(answer["reasoning_path"])
|
||||
```
|
||||
@@ -537,18 +524,18 @@ The `hybrid_alpha` parameter set in the `AgentContext` constructor establishes a
|
||||
When targeting a specific `anchor_node`, you can apply `proximity_weight` in `retrieve()` to dynamically blend structural distance from the anchor into the final score:
|
||||
|
||||
```python
|
||||
# Anchor node provided: let vector semantics lead, graph proximity only slightly boosts
|
||||
# Anchor node provided — let vector semantics lead, graph proximity only slightly boosts
|
||||
results = context.retrieve(
|
||||
query, use_graph=True, anchor_node="APT29", proximity_weight=0.2
|
||||
)
|
||||
|
||||
# Known-entity tracing: topology drives the retrieval
|
||||
# Known-entity tracing — topology drives the retrieval
|
||||
results = context.retrieve(
|
||||
query, use_graph=True, anchor_node="APT29", proximity_weight=0.8
|
||||
)
|
||||
```
|
||||
|
||||
Each additional expansion hop exponentially increases the subgraph size. Practical defaults by domain:
|
||||
Each additional hop in `max_hops` exponentially increases the subgraph size. Practical defaults by domain:
|
||||
|
||||
```text
|
||||
General Q&A max_expansion_hops=2 (95% of useful facts within 2 hops)
|
||||
@@ -557,7 +544,7 @@ Drug interactions max_expansion_hops=3 (drug → enzyme → metabolite
|
||||
Regulatory cross-ref max_expansion_hops=2 (rule → article → article)
|
||||
```
|
||||
|
||||
Expansion depth is a constructor setting only (`max_expansion_hops`); there is no per-call override on `retrieve()`. `query_with_reasoning()` does take a per-call `max_hops` argument.
|
||||
Set globally in the constructor; override per call with the `max_hops` argument to `retrieve()`.
|
||||
|
||||
## How GraphRAG works internally
|
||||
|
||||
@@ -589,9 +576,9 @@ The vector search and graph traversal run independently, then their scores are f
|
||||
|
||||
## Related Guides
|
||||
|
||||
- [Semantic Extraction](/guides/semantic-extraction): build the graph from raw unstructured text
|
||||
- [Agent Memory](/guides/agent-memory): store, retrieve, and persist agent memories
|
||||
- [Context Graphs](/guides/context-graphs): build and traverse the knowledge graph directly
|
||||
- [Reasoning](/guides/reasoning): derive new facts and run inference rules over the graph
|
||||
- [Decision Intelligence](/guides/decision-intelligence): causal chains, policy enforcement, decision tracking
|
||||
- [LLM Integrations](/guides/llm-integrations): connect Groq, OpenAI, Anthropic, HuggingFace, and 100+ more
|
||||
- [Semantic Extraction](/guides/semantic-extraction) — build the graph from raw unstructured text
|
||||
- [Agent Memory](/guides/agent-memory) — store, retrieve, and persist agent memories
|
||||
- [Context Graphs](/guides/context-graphs) — build and traverse the knowledge graph directly
|
||||
- [Reasoning](reasoning) — derive new facts and run inference rules over the graph
|
||||
- [Decision Intelligence](/guides/decision-intelligence) — causal chains, policy enforcement, decision tracking
|
||||
- [LLM Integrations](/guides/llm-integrations) — connect Groq, OpenAI, Anthropic, HuggingFace, and 100+ more
|
||||
|
||||
@@ -275,20 +275,20 @@ print(data)
|
||||
|
||||
**LiteLLM** is a universal adapter that provides a single interface to over 100 different LLM providers, including Anthropic Claude, Azure OpenAI, AWS Bedrock, Google Vertex AI, and local Ollama instances. It acts as a translation layer, converting your unified API calls into provider-specific requests, enabling easy switching between providers without code changes.
|
||||
|
||||
`LiteLLM` is the Swiss Army knife. It wraps the `litellm` library, which speaks to every major provider using a unified completion API. The model string encodes both provider and model name: `"anthropic/claude-sonnet-5"`, `"azure/gpt-4o"`, `"bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0"`, `"ollama/llama3.2"`. Change the string, change the provider — no other code changes needed.
|
||||
`LiteLLM` is the Swiss Army knife. It wraps the `litellm` library, which speaks to every major provider using a unified completion API. The model string encodes both provider and model name: `"anthropic/claude-sonnet-4-20250514"`, `"azure/gpt-4o"`, `"bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0"`, `"ollama/llama3.2"`. Change the string, change the provider — no other code changes needed.
|
||||
|
||||
```python
|
||||
from semantica.llms import LiteLLM
|
||||
|
||||
# Anthropic Claude — highest accuracy for complex reasoning
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
# Reads ANTHROPIC_API_KEY from environment
|
||||
|
||||
# Azure OpenAI — compliance and data-residency requirements
|
||||
llm = LiteLLM(model="azure/gpt-4o", api_key="YOUR_AZURE_KEY")
|
||||
|
||||
# AWS Bedrock — existing cloud agreement, no new vendor
|
||||
llm = LiteLLM(model="bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0")
|
||||
llm = LiteLLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
|
||||
|
||||
# Google Vertex AI
|
||||
llm = LiteLLM(model="vertex_ai/gemini-1.5-pro")
|
||||
@@ -306,7 +306,7 @@ The environment-variable convention for each provider: `ANTHROPIC_API_KEY`, `AZU
|
||||
import os
|
||||
|
||||
PROVIDER_MAP = {
|
||||
"prod": "anthropic/claude-sonnet-5",
|
||||
"prod": "anthropic/claude-sonnet-4-20250514",
|
||||
"staging": "openai/gpt-4o-mini",
|
||||
"local": "ollama/llama3.2",
|
||||
"azure": "azure/gpt-4o",
|
||||
@@ -378,7 +378,7 @@ print("FAST: {} (conf={:.0%})".format(fast_result["response"], fast_result["con
|
||||
|
||||
# Tier 2: deep answer with Claude if confidence is below threshold
|
||||
if fast_result["confidence"] < 0.85:
|
||||
deep_llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
deep_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
deep_result = context.query_with_reasoning(
|
||||
query, llm_provider=deep_llm, max_results=15, max_hops=3
|
||||
)
|
||||
@@ -574,7 +574,7 @@ print("TRIAGE: {} (conf={:.0%})".format(triage["response"], triage["confidence"]
|
||||
|
||||
# Tier 2: escalate to Claude for deep analysis if Tier 1 is uncertain
|
||||
if triage["confidence"] < 0.88:
|
||||
deep_llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
deep_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
deep = context.query_with_reasoning(
|
||||
"Full MITRE ATT&CK analysis of this alert: identify the attack chain, "
|
||||
"blast radius, affected systems, and recommended containment steps.",
|
||||
@@ -630,7 +630,7 @@ for d in drugs:
|
||||
# trastuzumab (conf=0.98), pertuzumab (conf=0.97), docetaxel (conf=0.96)
|
||||
|
||||
# Report synthesis with Claude — switch to azure/gpt-4o for HIPAA by changing one string
|
||||
report_llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
report_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
# For HIPAA-constrained Azure deployment:
|
||||
# report_llm = LiteLLM(model="azure/gpt-4o", api_key="YOUR_AZURE_KEY")
|
||||
|
||||
@@ -682,7 +682,7 @@ question = (
|
||||
|
||||
# Two-provider consensus — same query, same graph, different LLMs
|
||||
gpt4o = OpenAI(model="gpt-4o", api_key="YOUR_OAI_KEY")
|
||||
claude = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
claude = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
|
||||
answer_a = context.query_with_reasoning(question, llm_provider=gpt4o, max_results=10)
|
||||
answer_b = context.query_with_reasoning(question, llm_provider=claude, max_results=10)
|
||||
|
||||
@@ -197,7 +197,7 @@ reasoning_agent.load("./pipeline/enriched_intel/")
|
||||
# All memories, graph nodes, and vector embeddings from both ingestion agents are now available.
|
||||
|
||||
# Use a high-capability model for the synthesis step
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
|
||||
synthesis = reasoning_agent.query_with_reasoning(
|
||||
"Summarize the APT29 exploitation of CVE-2024-3400: affected products, "
|
||||
@@ -428,7 +428,7 @@ tier1.store(
|
||||
|
||||
# --- Tier 2: deep investigation when Tier 1 confidence is low ---
|
||||
if triage["confidence"] < 0.90:
|
||||
deep_llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
deep_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
|
||||
investigation = tier2.query_with_reasoning(
|
||||
"Full MITRE ATT&CK analysis of incident {}. "
|
||||
@@ -533,7 +533,7 @@ t1.start(); t2.start()
|
||||
t1.join(); t2.join()
|
||||
|
||||
# Chief agent synthesizes across literature and experimental data
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
|
||||
synthesis = chief.query_with_reasoning(
|
||||
"Identify the top two candidate compounds for KRAS G12C NSCLC that show "
|
||||
@@ -576,7 +576,7 @@ credit_officer = make_desk_agent()
|
||||
committee_chair = make_desk_agent()
|
||||
|
||||
app_id = "LOAN-2025-88421"
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-5")
|
||||
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
|
||||
|
||||
# --- Risk Desk: PD/LGD/EL analysis ---
|
||||
risk_desk.store(
|
||||
|
||||
@@ -477,7 +477,7 @@ regs = [
|
||||
]
|
||||
|
||||
# Use an LLM to extract the conceptual model from regulatory prose
|
||||
llm_gen = LLMOntologyGenerator(provider="anthropic", model="claude-sonnet-5")
|
||||
llm_gen = LLMOntologyGenerator(provider="anthropic", model="claude-sonnet-4-20250514")
|
||||
ontology = llm_gen.generate_ontology_from_text(
|
||||
"\n\n".join(r.text[:8000] for r in regs) # token-safe excerpt per document
|
||||
)
|
||||
|
||||
@@ -127,7 +127,7 @@ engine = ExecutionEngine(max_workers=4, retry_on_failure=True)
|
||||
result = engine.execute_pipeline(pipeline)
|
||||
|
||||
print(f"Success: {result.success}")
|
||||
print(f"Output: {result.output}") # the final step's return value, e.g. {"node_count": ..., "edge_count": ...}
|
||||
print(f"Output: {result.output}") # {"node_count": 312, "edge_count": 847}
|
||||
print(f"Duration: {result.metrics['execution_time']:.2f}s")
|
||||
print(f"Steps completed: {result.metrics['steps_executed']}")
|
||||
```
|
||||
@@ -197,9 +197,7 @@ engine = ExecutionEngine(
|
||||
max_workers = 4,
|
||||
retry_on_failure = True,
|
||||
)
|
||||
# ExecutionEngine builds its own FailureHandler; replace it with the configured one
|
||||
engine.failure_handler = handler
|
||||
# The engine now calls engine.failure_handler.get_retry_policy(step.step_type) on failure
|
||||
# The engine uses handler.get_retry_policy(step.step_type) when a step fails
|
||||
```
|
||||
|
||||
`handler.classify_error()` distinguishes `ValidationError` (low severity, usually don't retry), `ProcessingError` (high severity), and timeout/connection errors (medium severity, always retry). You can inspect the classification:
|
||||
|
||||
@@ -100,15 +100,14 @@ ner = NamedEntityRecognizer(
|
||||
methods=["llm", "ml", "pattern"],
|
||||
confidence_threshold=0.75,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
entities = ner.extract_entities(report)
|
||||
|
||||
for e in entities:
|
||||
print("[{:>5.2f}] {:15s} {}".format(e.confidence, e.label, e.text))
|
||||
|
||||
# Illustrative output — exact labels and scores depend on the method and model.
|
||||
# Abbreviated:
|
||||
# Expected output (abbreviated):
|
||||
# [ 0.94] THREAT_ACTOR GAMMA-7
|
||||
# [ 0.91] THREAT_ACTOR DELTA-3
|
||||
# [ 0.97] MALWARE HAMMERTOSS
|
||||
@@ -263,18 +262,16 @@ from semantica.semantic_extract import TripletExtractor
|
||||
tri = TripletExtractor(
|
||||
method="llm",
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
include_temporal=True, # attach time context to triplets when available
|
||||
include_provenance=True, # embed source document reference in each triplet
|
||||
validate=False, # return raw triplets; validate explicitly below
|
||||
)
|
||||
|
||||
# Feed in the entities and relations you already extracted — the extractor
|
||||
# uses them to constrain what it produces
|
||||
# uses them to constrain and validate what it produces
|
||||
triplets = tri.extract_triplets(report, entities, relations)
|
||||
|
||||
# Filter malformed triplets before serialisation
|
||||
# (extract_triplets validates automatically unless validate=False, as above)
|
||||
valid = tri.validate_triplets(triplets)
|
||||
print("Valid: {}/{}".format(len(valid), len(triplets)))
|
||||
|
||||
@@ -323,7 +320,7 @@ def ingest_intel_report(
|
||||
methods=[method, "pattern"],
|
||||
confidence_threshold=0.70,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
entities = ner.extract_entities(text)
|
||||
classified = ner.classify_entities(entities)
|
||||
@@ -338,7 +335,7 @@ def ingest_intel_report(
|
||||
relation_types=["deployed", "targets", "exploits", "operates_from", "provided_to"],
|
||||
confidence_threshold=0.65,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
relations = rel.extract_relations(text, entities)
|
||||
|
||||
@@ -350,10 +347,9 @@ def ingest_intel_report(
|
||||
tri = TripletExtractor(
|
||||
method=method,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
include_temporal=True,
|
||||
include_provenance=True,
|
||||
validate=False, # keep raw triplets so the summary can report rejections
|
||||
)
|
||||
triplets = tri.extract_triplets(text, entities, relations)
|
||||
valid = tri.validate_triplets(triplets)
|
||||
@@ -381,7 +377,6 @@ def ingest_intel_report(
|
||||
"coref_chains": len(chains),
|
||||
"relations": len(relations),
|
||||
"events": len(events),
|
||||
"triplets_total": len(triplets),
|
||||
"triplets_valid": len(valid),
|
||||
"graph_nodes": graph_stats.get("graph_nodes", 0),
|
||||
"graph_edges": graph_stats.get("graph_edges", 0),
|
||||
@@ -407,7 +402,7 @@ for text, doc_id in reports:
|
||||
summary["relations"],
|
||||
summary["events"],
|
||||
summary["triplets_valid"],
|
||||
summary["triplets_total"],
|
||||
len(summary["rdf_turtle"]),
|
||||
))
|
||||
```
|
||||
|
||||
@@ -426,7 +421,7 @@ ner = NamedEntityRecognizer(
|
||||
methods=["llm", "pattern"],
|
||||
confidence_threshold=0.75,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
entities = ner.extract_entities(fintel_text)
|
||||
grouped = ner.classify_entities(entities)
|
||||
@@ -443,14 +438,14 @@ rel = RelationExtractor(
|
||||
relation_types=["operates_from", "deployed", "targets", "exploits"],
|
||||
confidence_threshold=0.70,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
relations = rel.extract_relations(fintel_text, entities)
|
||||
|
||||
tri = TripletExtractor(
|
||||
method="llm",
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
include_temporal=True,
|
||||
include_provenance=True,
|
||||
)
|
||||
@@ -549,14 +544,14 @@ rel = RelationExtractor(
|
||||
relation_types=["treats", "causes_adverse_event", "has_efficacy", "evaluated_in"],
|
||||
confidence_threshold=0.65,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
relations = rel.extract_relations(paper, entities)
|
||||
|
||||
tri = TripletExtractor(
|
||||
method="llm",
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
triplet_types=["treats", "has_efficacy", "causes_adverse_event"],
|
||||
include_temporal=True,
|
||||
include_provenance=True,
|
||||
@@ -600,7 +595,7 @@ ner = NamedEntityRecognizer(
|
||||
methods=["llm", "ml", "pattern"],
|
||||
confidence_threshold=0.70,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
entities = ner.extract_entities(credit_memo)
|
||||
grouped = ner.classify_entities(entities)
|
||||
@@ -617,14 +612,14 @@ rel = RelationExtractor(
|
||||
relation_types=["guaranteed_by", "secured_by", "classified_as", "exposed_to"],
|
||||
confidence_threshold=0.65,
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
)
|
||||
relations = rel.extract_relations(credit_memo, entities)
|
||||
|
||||
tri = TripletExtractor(
|
||||
method="llm",
|
||||
provider="anthropic",
|
||||
llm_model="claude-sonnet-5",
|
||||
llm_model="claude-sonnet-4-6",
|
||||
include_temporal=True,
|
||||
include_provenance=True,
|
||||
)
|
||||
|
||||
@@ -707,22 +707,6 @@ report_dict = report.to_dict()
|
||||
|
||||
---
|
||||
|
||||
## Resource limits
|
||||
|
||||
Live SHACL validation in the Explorer enforces four resource limits, all configurable
|
||||
through environment variables. When a limit trips, the error message names the
|
||||
variable that controls it.
|
||||
|
||||
| Environment variable | Default | What it bounds |
|
||||
| --- | --- | --- |
|
||||
| `SEMANTICA_MAX_SHACL_TURTLE_BYTES` | `262144` (256 KB) | Size of the submitted SHACL Turtle |
|
||||
| `SEMANTICA_MAX_SHACL_TRIPLES` | `1000` | Triple count of the parsed shapes graph |
|
||||
| `SEMANTICA_MAX_SHACL_TIMEOUT` | `15.0` | Validation timeout in seconds |
|
||||
| `SEMANTICA_MAX_SHACL_CONCURRENCY` | `4` | Concurrent validations per process |
|
||||
|
||||
The first three are surfaced in the validation error message when exceeded; the
|
||||
concurrency limit applies as a semaphore and does not appear in responses.
|
||||
|
||||
## Using SHACL validation as a CI/CD gate
|
||||
|
||||
Call this function as a pre-publish gate; exit code 1 blocks the pipeline.
|
||||
|
||||
+304
-25
@@ -1,31 +1,109 @@
|
||||
---
|
||||
title: "Welcome to Semantica"
|
||||
description: "The Context and Semantic Layer for AI in High-Stakes Domains: Context Graphs · Decision Intelligence · Full Provenance"
|
||||
title: "Semantica"
|
||||
description: "The Accountability and Context Layer for AI: Context Graphs · Decision Intelligence · Full Provenance"
|
||||
---
|
||||
|
||||
```bash
|
||||
pip install semantica
|
||||
```
|
||||
|
||||
Most AI agents run on embeddings, not meaning. A similarity score has no structure, no relationships, and no way to explain why a result came back.
|
||||
Your AI agent just made a decision. Now someone needs to explain it.
|
||||
|
||||
Semantica is the semantic and context layer underneath your LLM, vector store, and agent framework: deterministic infrastructure, not a model. Graph construction, reasoning, and provenance all run without an LLM in the loop. It turns fragmented enterprise data into a structured, queryable context graph and knowledge graph, governed by ontologies, taxonomies, and controlled vocabularies (OWL, SHACL, SKOS), so your data's meaning is explicit rather than approximated by an embedding.
|
||||
*What did it know at the time? Which facts shaped the outcome? Where did those facts come from? Has it made the same call before: and did that go well?*
|
||||
|
||||
Provenance and audit trails aren't a bolt-on. They fall out naturally once your data has that structure, so the same graph that powers retrieval and reasoning also gives you a straight answer when a regulator asks why.
|
||||
If your stack can't answer those questions with a traceable record, you have a gap. Not a capability gap: an **accountability gap**. It's the reason AI hasn't landed at scale in healthcare, finance, legal, and government. And it's why teams building for those markets keep rebuilding the same guardrails from scratch.
|
||||
|
||||
## What you get
|
||||
**Semantica closes that gap.** It's the context and accountability layer that sits beneath your existing agent framework: not a replacement for LangChain or LlamaIndex, but the infrastructure that makes their outputs trustworthy.
|
||||
|
||||
- **[Context graphs](/guides/context-graphs)**: a persistent, queryable graph of everything your agent knows, decides, and reasons about
|
||||
- **Decision intelligence**: `record_decision()` captures the full lifecycle and causal chain of every decision
|
||||
- **[Full provenance](/guides/provenance)**: every fact links back to its source, W3C PROV-O compliant and audit-ready for HIPAA, SOX, and GDPR
|
||||
- **[Explainable reasoning](/guides/reasoning)**: forward chaining, Datalog, and SPARQL, each with a derivation path you can inspect
|
||||
- **Temporal intelligence**: Allen interval algebra and point-in-time snapshots, so the graph knows not just *what* but *when*
|
||||
|
||||
## The Problem Every Production AI Team Hits
|
||||
|
||||
Powerful agents aren't automatically trustworthy ones. Five structural blind spots make modern AI systems impossible to deploy in regulated environments:
|
||||
|
||||
**No memory structure** — agents store embeddings, not meaning
|
||||
- No way to ask *why* a fact was recalled
|
||||
- No link from a recalled fact back to its source document
|
||||
- Context is a black box that resets on every run
|
||||
|
||||
**No decision trail** — agents act continuously but record nothing
|
||||
- No history to hand to a regulator or auditor
|
||||
- No way to replay or reproduce a past decision
|
||||
- Debugging means re-running, not reviewing
|
||||
|
||||
**No provenance** — outputs can't be traced to source facts
|
||||
- In healthcare, finance, and legal: this is a hard compliance blocker
|
||||
- No lineage from inference back to the original document
|
||||
- Impossible to demonstrate what the agent actually relied on
|
||||
|
||||
**No reasoning transparency** — black-box answers with no explanation
|
||||
- Impossible to validate the reasoning path
|
||||
- Impossible to contest a specific conclusion
|
||||
- No basis for improving or correcting future behavior
|
||||
|
||||
**No conflict detection** — contradictory facts silently coexist in vector stores
|
||||
- No detection when two sources disagree
|
||||
- Outputs become inconsistent and unpredictable over time
|
||||
- Silent failures compound as the knowledge base grows
|
||||
|
||||
<Note>
|
||||
These aren't edge cases. They're why enterprise AI pilots stall: and why your compliance team keeps saying *not yet*.
|
||||
</Note>
|
||||
|
||||
|
||||
## What Semantica Adds to Your Stack
|
||||
|
||||
Semantica gives every agent the infrastructure it needs to be accountable. Drop it into your existing setup in minutes:
|
||||
|
||||
**Context Graphs** — a structured, queryable graph of everything your agent knows, decides, and reasons about
|
||||
- Persistent across agent runs: no context loss between sessions
|
||||
- Queryable with SPARQL and full graph algorithms
|
||||
- Temporal model with `valid_from` / `valid_until` on nodes and edges
|
||||
- Point-in-time snapshots of the full knowledge state
|
||||
|
||||
**Decision Intelligence** — every decision is a first-class object in your system
|
||||
- `record_decision()` captures full lifecycle and causal chain
|
||||
- Hybrid precedent search over past decisions for consistency
|
||||
- `analyze_decision_impact()` shows downstream consequences
|
||||
- Causal chain visualization from trigger to outcome
|
||||
|
||||
**Full Provenance** — every fact links to its source document and ingestion event
|
||||
- W3C PROV-O compliant lineage across all modules
|
||||
- Full traceability from raw input to final inference
|
||||
- `recorded_at` stamping with OWL-Time export
|
||||
- Audit-ready for HIPAA, SOX, GDPR, FDA 21 CFR Part 11
|
||||
|
||||
**Reasoning Engines** — explainable reasoning paths, not black boxes
|
||||
- Forward chaining, Rete, deductive, abductive
|
||||
- SPARQL query-based inference over RDF graphs
|
||||
- Datalog with recursive Horn clause rules
|
||||
- Every conclusion backed by a traceable derivation path
|
||||
|
||||
**Temporal Intelligence** — your graph knows not just *what*, but *when*
|
||||
- Allen interval algebra: all 13 temporal relations
|
||||
- Point-in-time queries over historical graph states
|
||||
- Temporal provenance stamping on every fact
|
||||
- OWL-Time export for standards-compliant archiving
|
||||
|
||||
**Ontology Hub** — full ontology lifecycle in the browser
|
||||
- Visual editor for schema design and editing
|
||||
- SHACL Studio for constraint authoring and validation
|
||||
- Alignment authoring across multiple ontologies
|
||||
- Health dashboard and version control built in
|
||||
|
||||
<Tip>
|
||||
Works alongside any LLM provider and any agent framework, and ingests directly from enterprise data platforms like Databricks, SAP, Salesforce, and Snowflake. Add it to an existing stack without changing your architecture.
|
||||
Works alongside any LLM provider and any agent framework: add it to an existing stack without changing your architecture.
|
||||
</Tip>
|
||||
|
||||
## Try it
|
||||
<img src="/assets/img/diagrams/architecture-overview.svg" alt="Semantica four-layer architecture: Ingestion → Processing → Intelligence → Application" style={{ width: '100%', borderRadius: '12px', margin: '24px 0' }} />
|
||||
|
||||
|
||||
## See It In Action
|
||||
|
||||
One pip install. A few lines to connect your agent. Everything else becomes traceable.
|
||||
|
||||
```bash
|
||||
pip install semantica
|
||||
```
|
||||
|
||||
<CodeGroup>
|
||||
|
||||
@@ -107,28 +185,229 @@ decision_id = context.record_decision(
|
||||
|
||||
</CodeGroup>
|
||||
|
||||
## Start here
|
||||
- [Full Quickstart](/quickstart) — Step-by-step pipeline walkthrough
|
||||
- [Cookbook](/cookbook) — 40+ real-world Jupyter notebooks
|
||||
- [Join Discord](https://discord.gg/sV34vps5hH) — Community chat and support
|
||||
|
||||
|
||||
## Built for Where Mistakes Have Consequences
|
||||
|
||||
Semantica was designed for domains where every decision must be explainable and every fact must be traceable.
|
||||
|
||||
<Warning>
|
||||
**This is system-level explainability, not foundation-model explainability.** Semantica does not expose, reconstruct, or explain what happens *inside* the LLM/foundation model — its internal reasoning or chain-of-thought stays opaque, as it does for any external system. What Semantica explains is *outside* the model: the context and data fed in, the decision produced, its provenance, the relevant relationships, the policies applied, and the full execution trail. See [Core Concepts](/concepts) for the full scope note.
|
||||
</Warning>
|
||||
|
||||
**Healthcare & Life Sciences**
|
||||
- Clinical decision support with full audit trails
|
||||
- Drug interaction and contraindication graphs
|
||||
- Patient safety event tracking and root-cause analysis
|
||||
- HIPAA-compliant provenance chains out of the box
|
||||
|
||||
**Finance & Risk**
|
||||
- Fraud detection knowledge graphs
|
||||
- Risk assessment trails built to survive an audit
|
||||
- SOX, GDPR, and MiFID II compliance infrastructure
|
||||
- Model decision lineage for regulatory reporting
|
||||
|
||||
**Legal & Compliance**
|
||||
- Evidence-backed research with every cited fact provenance-linked
|
||||
- Contract analysis with traceable clause extraction
|
||||
- Regulatory change tracking across jurisdictions
|
||||
- Full reasoning paths ready for court-admissible documentation
|
||||
|
||||
**Cybersecurity**
|
||||
- Threat attribution graphs linking actors, TTPs, and indicators
|
||||
- Incident response timelines with full event provenance
|
||||
- Security audit trails across the complete kill chain
|
||||
- MITRE ATT&CK-aligned knowledge graph integration
|
||||
|
||||
**Government & Defense**
|
||||
- Policy decision trails from brief to outcome
|
||||
- Classified information handling with provenance chains
|
||||
- Chain-of-custody scrutiny for intelligence reporting
|
||||
- Air-gapped deployment with local LLM support
|
||||
|
||||
**Critical Infrastructure**
|
||||
- Power grid state tracking with temporal intelligence
|
||||
- Transportation safety event graphs
|
||||
- Emergency response coordination with decision audit trails
|
||||
- Consequence modeling for high-stakes operational decisions
|
||||
|
||||
|
||||
## Start Here
|
||||
|
||||
<Steps>
|
||||
<Step title="Install">
|
||||
<Step title="Install Semantica">
|
||||
```bash
|
||||
pip install semantica
|
||||
```
|
||||
Optional extras: `[all]`, `[neo4j]`, `[pinecone]`. See [Installation](/installation).
|
||||
See [Installation](/installation) for optional extras (`[all]`, `[neo4j]`, `[pinecone]`) and environment setup.
|
||||
</Step>
|
||||
<Step title="Build a pipeline">
|
||||
Follow the [Quickstart](/quickstart) to ingest documents, extract entities, build a graph, and record a decision in 5 minutes.
|
||||
<Step title="Run the Quickstart">
|
||||
Build a complete knowledge graph pipeline in [5 minutes](/quickstart):
|
||||
- Ingest documents from any source
|
||||
- Extract entities and relationships
|
||||
- Build and query the graph
|
||||
- Record and trace a decision
|
||||
</Step>
|
||||
<Step title="Learn the model">
|
||||
[Core Concepts](/concepts) covers knowledge graphs vs. vector stores, GraphRAG, and how provenance and decisions fit together.
|
||||
<Step title="Learn the mental model">
|
||||
[Core Concepts](/concepts) covers:
|
||||
- Knowledge graphs vs. vector stores: when to use each
|
||||
- What GraphRAG is and how Semantica implements it
|
||||
- How provenance and decision tracking work together
|
||||
- The accountability layer architecture
|
||||
</Step>
|
||||
<Step title="Go deep">
|
||||
Every module has a [reference page](/reference/context) with full API docs and runnable examples.
|
||||
<Step title="Go deep on any module">
|
||||
Every module has a dedicated [reference page](/reference/context) with:
|
||||
- Full class and method documentation
|
||||
- Parameter tables with types and defaults
|
||||
- Runnable code examples for each feature
|
||||
</Step>
|
||||
</Steps>
|
||||
|
||||
More: the [Cookbook](/cookbook) for real-world notebooks, [Discord](https://discord.gg/sV34vps5hH) for help.
|
||||
- [Installation](/installation) — Get Semantica installed in under a minute
|
||||
- [Quickstart](/quickstart) — Build a complete knowledge graph pipeline in 5 minutes
|
||||
- [Core Concepts](/concepts) — The mental model behind the API
|
||||
- [API Reference](/reference/context) — Exact module, class, and method details
|
||||
- [Cookbook](/cookbook) — Domain notebooks for real-world use cases
|
||||
- [Changelog](https://github.com/semantica-agi/semantica/releases) — Release history
|
||||
|
||||
|
||||
## Full Capabilities
|
||||
|
||||
<AccordionGroup>
|
||||
|
||||
<Accordion title="Context & Decision Intelligence" icon="brain">
|
||||
|
||||
### Context Graphs
|
||||
|
||||
- Structured, persistent graph of entities, relationships, and decisions
|
||||
- Temporal model with `valid_from` / `valid_until` on every node and edge
|
||||
- Point-in-time queries across historical graph states
|
||||
- Distance Intelligence: semantic neighborhoods and N×N distance matrices
|
||||
|
||||
### Decision Tracking
|
||||
|
||||
- `record_decision()` with full lifecycle management and causal chains
|
||||
- Hybrid similarity search over past decisions for consistency enforcement
|
||||
- `analyze_decision_impact()` and `analyze_decision_influence()` for consequence modeling
|
||||
- Ego-mode exploration for targeted neighborhood investigation
|
||||
|
||||
<Accordion title="Full module list">
|
||||
`semantica.ingest`, `semantica.parse`, `semantica.split`, `semantica.normalize`, `semantica.semantic_extract`, `semantica.kg`, `semantica.ontology`, `semantica.reasoning`, `semantica.embeddings`, `semantica.vector_store`, `semantica.graph_store`, `semantica.triplet_store`, `semantica.context`, `semantica.provenance`, `semantica.change_management`, `semantica.deduplication`, `semantica.conflicts`, `semantica.export`, `semantica.visualization`, `semantica.pipeline`, `semantica.seed`, `semantica.llms`, `semantica.mcp_server`, `semantica.explorer`, `semantica.evals`, `semantica.utils`, `semantica.core`. See the [API Reference](/reference/context) for full docs on each.
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Knowledge Engineering" icon="diagram-project">
|
||||
|
||||
### Entity & Relation Extraction
|
||||
|
||||
- Named entity recognition: pattern, ML, or LLM methods
|
||||
- Typed triplet extraction via LLM or rule-based pipelines
|
||||
- Event extraction with temporal and causal linking
|
||||
|
||||
### Ontology & Schema
|
||||
|
||||
- Ontology Hub: visual editor, SHACL Studio, alignments, health dashboard
|
||||
- Deduplication v2: `blocking_v2`, `hybrid_v2`, `semantic_v2`: up to 7x faster
|
||||
- Datalog reasoning: recursive Horn clause rules with fixpoint semantics
|
||||
- SPARQL reasoning: query-based inference over RDF graphs
|
||||
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Provenance & Auditability" icon="shield-check">
|
||||
|
||||
### Lineage Tracking
|
||||
|
||||
- W3C PROV-O lineage across all modules: every fact has a source
|
||||
- `recorded_at` stamping with full OWL-Time export
|
||||
- Change management with SHA-256 checksums and version control
|
||||
- Full audit trails from ingestion event to final inference
|
||||
|
||||
### Compliance Infrastructure
|
||||
|
||||
- HIPAA: patient data handling with audit-ready provenance chains
|
||||
- SOX / MiFID II: financial decision records with full traceability
|
||||
- GDPR: data lineage for subject access and right-to-erasure workflows
|
||||
- FDA 21 CFR Part 11: electronic records and signature compliance
|
||||
|
||||
</Accordion>
|
||||
|
||||
<Accordion title="Data Ingestion & Export" icon="database">
|
||||
|
||||
### Ingestion Formats
|
||||
|
||||
- Documents: PDF, DOCX, HTML, PPTX, Docling layout analysis
|
||||
- Structured data: JSON, CSV, Excel, Parquet, XML
|
||||
- Sources: web crawl, SQL, Snowflake, feeds, email, code repositories, MCP
|
||||
|
||||
### Vector Stores
|
||||
|
||||
- FAISS, Pinecone, Weaviate, Qdrant, Milvus, PgVector, in-memory
|
||||
|
||||
### Graph Stores
|
||||
|
||||
- Neo4j, FalkorDB, Apache AGE, Amazon Neptune
|
||||
|
||||
### Export Formats
|
||||
|
||||
- RDF: Turtle, JSON-LD, N-Triples, RDF/XML
|
||||
- Tabular: Parquet, CSV, Arrow
|
||||
- Graph: GraphML, GEXF, DOT, ArangoDB AQL
|
||||
- Ontology: OWL, SKOS, SHACL
|
||||
|
||||
</Accordion>
|
||||
|
||||
</AccordionGroup>
|
||||
|
||||
|
||||
## Module Reference
|
||||
|
||||
| Module | What it provides |
|
||||
| :-------- | :----------------- |
|
||||
| `semantica.context` | Context graphs, agent memory, decision tracking, causal analysis, precedent search |
|
||||
| `semantica.kg` | KG construction, graph algorithms, temporal model, Allen interval algebra |
|
||||
| `semantica.semantic_extract` | NER, relation extraction, event extraction, triplet generation |
|
||||
| `semantica.reasoning` | Forward chaining, Rete, deductive, abductive, SPARQL, Datalog |
|
||||
| `semantica.ontology` | SHACL, SKOS, alignments, diff/migration, auto-generation, OWL/RDF |
|
||||
| `semantica.explorer` | FastAPI Knowledge Explorer, Ontology Hub, Distance Intelligence, SHACL Studio |
|
||||
| `semantica.mcp_server` | MCP stdio server: 15 tools for Claude Desktop, VS Code, Cursor, Windsurf, Cline |
|
||||
| `semantica.vector_store` | FAISS, Pinecone, Weaviate, Qdrant, Milvus, PgVector |
|
||||
| `semantica.graph_store` | Neo4j, FalkorDB, Apache AGE, Amazon Neptune |
|
||||
| `semantica.triplet_store` | In-memory and persistent RDF triple store with SPARQL |
|
||||
| `semantica.ingest` | Files, web, feeds, databases, Snowflake, Parquet, XML, MCP |
|
||||
| `semantica.parse` | Document parsing: PDF, DOCX, HTML, PPTX, Docling layout analysis |
|
||||
| `semantica.split` | Text chunking: sentence, paragraph, token, semantic boundary strategies |
|
||||
| `semantica.normalize` | Text normalization, entity canonicalization, whitespace and encoding cleanup |
|
||||
| `semantica.embeddings` | Sentence-Transformers, FastEmbed, OpenAI, BGE, Ollama local embeddings |
|
||||
| `semantica.pipeline` | Pipeline DSL, parallel workers, retry policies, failure handling |
|
||||
| `semantica.export` | RDF, Parquet, ArangoDB AQL, CSV, OWL, Arrow, GraphML, GEXF, DOT |
|
||||
| `semantica.visualization` | Programmatic graph rendering: force, hierarchical, circular, spring layouts |
|
||||
| `semantica.deduplication` | Entity deduplication v1/v2, similarity scoring, blocking, merging |
|
||||
| `semantica.conflicts` | Conflict detection and resolution across overlapping knowledge sources |
|
||||
| `semantica.provenance` | W3C PROV-O lineage tracking, source attribution, audit trails |
|
||||
| `semantica.change_management` | Version control with SHA-256 checksums, diff, rollback |
|
||||
| `semantica.llms` | Groq, OpenAI, Anthropic, Gemini, Ollama, DeepSeek, Novita AI, LiteLLM, HuggingFace |
|
||||
| `semantica.seed` | Foundation graph seeding from CSV, JSON, SQL, API, and RDF sources |
|
||||
| `semantica.evals` | Evaluation harness: KG quality, extraction F1, pipeline benchmarking, regression tracking |
|
||||
| `semantica.core` | Orchestration, ConfigManager, LifecycleManager, PluginRegistry, MethodRegistry |
|
||||
| `semantica.utils` | Logging, validation, progress tracking, hash utilities, nested dict helpers |
|
||||
|
||||
|
||||
## Why Semantica?
|
||||
|
||||
**Open Source, MIT** — No vendor lock-in. No paywalled features.
|
||||
- Full source available on GitHub
|
||||
- Every line auditable by your security team
|
||||
- Fork, extend, and self-host with no restrictions
|
||||
- No telemetry, no usage reporting
|
||||
|
||||
**Production Ready** — Built for teams that can't afford surprises.
|
||||
- 1,000+ passing tests with full regression coverage
|
||||
- `PipelineValidator` catches configuration errors at startup
|
||||
- `FailureHandler` with exponential backoff and dead-letter queues
|
||||
- Ongoing security hardening: fixes shipped in every release ([CHANGELOG](https://github.com/semantica-agi/semantica/blob/main/CHANGELOG.md))
|
||||
|
||||
**Modular by Design** — Import only what you need.
|
||||
- Use `NERExtractor` without a graph store
|
||||
- Use `ContextGraph` without vector storage
|
||||
- Every component independently swappable and testable
|
||||
- No framework lock-in: works with any agent stack
|
||||
|
||||
@@ -183,6 +183,6 @@ Install the [Microsoft Visual C++ Redistributable](https://aka.ms/vs/17/release/
|
||||
|
||||
## Next Steps
|
||||
|
||||
- [Getting Started](/getting-started): understand what Semantica does before you build.
|
||||
- [Build the Pipeline](/quickstart): follow the end-to-end workflow with code.
|
||||
- [Browse Examples](/cookbook): see notebook examples organized by use case.
|
||||
- [Getting Started](/getting-started) — Understand what Semantica does before you build.
|
||||
- [Build the Pipeline](/quickstart) — Follow the end-to-end workflow with code.
|
||||
- [Browse Examples](/cookbook) — See notebook examples organized by use case.
|
||||
|
||||
@@ -12,13 +12,13 @@ icon: "link"
|
||||
pip install "semantica[langchain]"
|
||||
```
|
||||
|
||||
Requires `langchain-core >= 0.3`. If langchain-core is not installed, the integration still imports. Every class carries the full Semantica API and degrades gracefully (`build()` returns `None`; branch on `LANGCHAIN_AVAILABLE`).
|
||||
Requires `langchain-core >= 0.3`. If langchain-core is not installed, the integration still imports — every class carries the full Semantica API and degrades gracefully (`build()` returns `None`; branch on `LANGCHAIN_AVAILABLE`).
|
||||
|
||||
## Components at a Glance
|
||||
|
||||
- **SemanticaRetriever** (`BaseRetriever`): hybrid-search seeds retrieval, then graph edges are walked `hops` steps (default 2) for GraphRAG-style results.
|
||||
- **SemanticaVectorStore** (`VectorStore`): `add_texts` / `similarity_search` / `similarity_search_with_score` / `from_texts` over `HybridSearch`.
|
||||
- **SemanticaKGTool** / **SemanticaDecisionTool** (`BaseTool` subclasses): `semantica_query_graph` and `semantica_query_decisions` for LangGraph / tool-calling agents.
|
||||
- **SemanticaRetriever** — `BaseRetriever`: hybrid-search seeds retrieval, then graph edges are walked `hops` steps (default 2) for GraphRAG-style results.
|
||||
- **SemanticaVectorStore** — `VectorStore`: `add_texts` / `similarity_search` / `similarity_search_with_score` / `from_texts` over `HybridSearch`.
|
||||
- **SemanticaKGTool** / **SemanticaDecisionTool** — `BaseTool` subclasses: `semantica_query_graph` and `semantica_query_decisions` for LangGraph / tool-calling agents.
|
||||
|
||||
## Component Details
|
||||
|
||||
|
||||
@@ -9,9 +9,9 @@ Whether you're running your first pipeline or deploying Semantica in production,
|
||||
|
||||
## Learning Paths
|
||||
|
||||
- **Beginner (1–2 hrs)**: new to Semantica and knowledge graphs. [Start with Installation →](/installation)
|
||||
- **Intermediate (4–6 hrs)**: comfortable with basics, building real applications. [Start with Modules →](/modules)
|
||||
- **Advanced (8+ hrs)**: enterprise deployments, customization, and extension. [Start with Architecture →](/architecture)
|
||||
- **Beginner (1–2 hrs)** — New to Semantica and knowledge graphs. [Start with Installation →](/installation)
|
||||
- **Intermediate (4–6 hrs)** — Comfortable with basics, building real applications. [Start with Modules →](/modules)
|
||||
- **Advanced (8+ hrs)** — Enterprise deployments, customization, and extension. [Start with Architecture →](/architecture)
|
||||
|
||||
<Tabs>
|
||||
<Tab title="Beginner (1–2 hrs)">
|
||||
@@ -116,7 +116,7 @@ pip install "semantica[gpu]" # GPU acceleration
|
||||
|
||||
<Accordion title="AuthenticationError" icon="lock">
|
||||
|
||||
Set your API key as an environment variable (never hardcode keys in source files):
|
||||
Set your API key as an environment variable — never hardcode keys in source files:
|
||||
|
||||
```bash
|
||||
export OPENAI_API_KEY="sk-..."
|
||||
@@ -236,6 +236,6 @@ The `blocking_v2`, `hybrid_v2`, and `semantic_v2` strategies reduce O(n²) compa
|
||||
- **Graph exports**: encrypt sensitive exports at rest; use the v0.5.0 SSRF-safe `base_url` validation when configuring custom LLM gateways
|
||||
- **XML ingestion**: always use `XMLIngestor` (v0.5.0), which uses the XXE-safe lxml backend; never parse untrusted XML with the standard library parser
|
||||
|
||||
- [Cookbook](/cookbook): interactive Jupyter notebooks from beginner to advanced.
|
||||
- [FAQ](/faq): common questions answered.
|
||||
- [API Reference](/reference/core): complete technical documentation.
|
||||
- [Cookbook](/cookbook) — Interactive Jupyter notebooks from beginner to advanced.
|
||||
- [FAQ](/faq) — Common questions answered.
|
||||
- [API Reference](/reference/core) — Complete technical documentation.
|
||||
|
||||
+135
-176
@@ -5,32 +5,30 @@ icon: "puzzle-piece"
|
||||
---
|
||||
|
||||
<Info>
|
||||
Jump to the [Module Index](#module-index) for a quick reference.
|
||||
Looking for a quick reference? Jump to the [Module Index](#module-index) at the bottom.
|
||||
</Info>
|
||||
|
||||
<Tip>
|
||||
The [Choose the Right Module](/choose-your-module) guide maps 35+ developer goals to modules with code examples; start there if you're orienting for the first time.
|
||||
Not sure which module to use? The [Choose the Right Module](/choose-your-module) guide maps 35+ developer goals to modules with code examples — start there if you're orienting for the first time.
|
||||
</Tip>
|
||||
|
||||
Semantica is organized into **27 modules** across six logical layers. Each module is independently importable: you never pay for what you don't use.
|
||||
|
||||
## Architecture Overview
|
||||
|
||||
- **Input Layer**: data ingestion and preparation. Modules: `ingest`, `parse`, `split`, `normalize`
|
||||
- **Core Processing**: intelligence and understanding. Modules: `semantic_extract`, `kg`, `ontology`, `reasoning`
|
||||
- **Storage**: persistent data storage. Modules: `embeddings`, `vector_store`, `graph_store`, `triplet_store`
|
||||
- **Quality Assurance**: data quality and consistency. Modules: `deduplication`, `conflicts`
|
||||
- **Context & Memory**: agent memory and decision tracking. Modules: `context`, `provenance`, `change_management`
|
||||
- **Output & Orchestration**: export, visualization, and workflows. Modules: `export`, `visualization`, `pipeline`, `explorer`
|
||||
- **Input Layer** — Data ingestion and preparation. Modules: `ingest`, `parse`, `split`, `normalize`
|
||||
- **Core Processing** — Intelligence and understanding. Modules: `semantic_extract`, `kg`, `ontology`, `reasoning`
|
||||
- **Storage** — Persistent data storage. Modules: `embeddings`, `vector_store`, `graph_store`, `triplet_store`
|
||||
- **Quality Assurance** — Data quality and consistency. Modules: `deduplication`, `conflicts`
|
||||
- **Context & Memory** — Agent memory and decision tracking. Modules: `context`, `provenance`, `change_management`
|
||||
- **Output & Orchestration** — Export, visualization, and workflows. Modules: `export`, `visualization`, `pipeline`, `explorer`
|
||||
|
||||
|
||||
## Input Layer
|
||||
|
||||
### Ingest
|
||||
|
||||
Loads data from files, web, databases, and streams. Each ingestor returns its own
|
||||
result type (`FileIngestor` → `FileObject`, `WebIngestor` → `WebContent`, …);
|
||||
document-oriented ones expose a `.text` payload and `.metadata`.
|
||||
Loads data from files, web, databases, and streams into a unified `SourceDocument` format.
|
||||
|
||||
```python
|
||||
from semantica.ingest import FileIngestor, WebIngestor, ParquetIngestor, XMLIngestor, DatabricksIngestor
|
||||
@@ -39,7 +37,7 @@ from semantica.ingest import FileIngestor, WebIngestor, ParquetIngestor, XMLInge
|
||||
ingestor = FileIngestor()
|
||||
documents = ingestor.ingest_directory("data/")
|
||||
|
||||
# Web page: returns a WebContent with .text, .title, .links, .metadata
|
||||
# Web crawl
|
||||
web_ingestor = WebIngestor()
|
||||
page = web_ingestor.ingest_url("https://example.com")
|
||||
|
||||
@@ -51,7 +49,7 @@ sources = parquet.ingest("data/events.parquet")
|
||||
xml = XMLIngestor()
|
||||
sources = xml.ingest("data/records/", schema_path="schema.xsd")
|
||||
|
||||
# Enterprise lakehouse/warehouse: Unity Catalog + Delta Lake, or a Snowflake warehouse
|
||||
# Enterprise lakehouse/warehouse — Unity Catalog + Delta Lake, or a Snowflake warehouse
|
||||
databricks = DatabricksIngestor(host="...", token="...", http_path="...")
|
||||
customers = databricks.ingest_table("customers")
|
||||
```
|
||||
@@ -59,7 +57,7 @@ customers = databricks.ingest_table("customers")
|
||||
**Available ingestors:** `FileIngestor`, `WebIngestor`, `ParquetIngestor`, `XMLIngestor`, `RESTIngestor`, `PublicAPIIngestor`, `DBIngestor`, `DatabricksIngestor`, `SnowflakeIngestor`, `EmailIngestor`, `FeedIngestor`, `MCPIngestor`, `OntologyIngestor`, `RepoIngestor`, `StreamIngestor`, `ArrowIngestor`, `CloudStorageIngestor`
|
||||
|
||||
<Note>
|
||||
`DuckDBIngestor`, `ElasticIngestor`, `GDriveIngestor`, `HuggingFaceIngestor`, `MongoIngestor`, and `PandasIngestor` also ship but aren't re-exported from the top-level `semantica.ingest` namespace yet; import them directly, e.g. `from semantica.ingest.duckdb_ingestor import DuckDBIngestor`.
|
||||
`DuckDBIngestor`, `ElasticIngestor`, `GDriveIngestor`, `HuggingFaceIngestor`, `MongoIngestor`, and `PandasIngestor` also ship but aren't re-exported from the top-level `semantica.ingest` namespace yet — import them directly, e.g. `from semantica.ingest.duckdb_ingestor import DuckDBIngestor`.
|
||||
</Note>
|
||||
|
||||
### Parse
|
||||
@@ -69,13 +67,13 @@ Extracts structured text and layout metadata from raw documents.
|
||||
```python
|
||||
from semantica.parse import DocumentParser, DoclingParser
|
||||
|
||||
# Standard parser: all common formats. parse() takes a path, returns a dict
|
||||
# Standard parser: all common formats
|
||||
parser = DocumentParser()
|
||||
parsed = parser.parse("document.pdf") # {"full_text": ..., "metadata": ..., ...}
|
||||
parsed = parser.parse_document("document.pdf")
|
||||
|
||||
# Advanced parser (pip install semantica[parse-docling]): tables, OCR, layout
|
||||
parser = DoclingParser(export_format="markdown", enable_ocr=True)
|
||||
parsed = parser.parse("data/annual_report.pdf") # dict with full_text, tables, pages
|
||||
# Advanced parser: multi-column PDFs, merged-cell tables, OCR
|
||||
parser = DoclingParser(extract_tables=True, extract_images=True, output_format="markdown")
|
||||
parsed = parser.parse("data/annual_report.pdf")
|
||||
```
|
||||
|
||||
**Available parsers:** `DocumentParser`, `DoclingParser`, `CodeParser`, `CSVParser`, `DocxParser`, `EmailParser`, `ExcelParser`, `HTMLParser`, `ImageParser`, `JSONParser`, `MCPParser`, `MediaParser`, `PDFParser`, `PPTXParser`, `StructuredDataParser`, `WebParser`, `XMLParser`
|
||||
@@ -87,12 +85,11 @@ Chunks text for embedding and RAG pipelines with awareness of semantic boundarie
|
||||
```python
|
||||
from semantica.split import TextSplitter
|
||||
|
||||
# chunk_size / chunk_overlap are constructor arguments
|
||||
splitter = TextSplitter(method="semantic_transformer", chunk_size=1000, chunk_overlap=200)
|
||||
chunks = splitter.split(text)
|
||||
splitter = TextSplitter(method="semantic_transformer")
|
||||
chunks = splitter.split(text, chunk_size=1000, chunk_overlap=200)
|
||||
```
|
||||
|
||||
**Chunking methods:** `recursive`, `token`, `sentence`, `paragraph`, `semantic_transformer`, `entity_aware`, `relation_aware`, `graph_based`, `ontology_aware`, `hierarchical`, `community_detection`, `centrality_based`, `llm`
|
||||
**Chunking strategies:** `recursive`, `semantic_transformer`, `entity_aware`, `relation_aware`, `sliding_window`, `structural`
|
||||
|
||||
### Normalize
|
||||
|
||||
@@ -118,18 +115,17 @@ Named entity recognition, relation extraction, and triplet generation.
|
||||
```python
|
||||
from semantica.semantic_extract import NERExtractor, RelationExtractor, TripletExtractor
|
||||
|
||||
# LLM method: provider + llm_model select the backend; the API key comes from the env
|
||||
ner = NERExtractor(method="llm", provider="groq", llm_model="llama-3.3-70b-versatile")
|
||||
entities = ner.extract("Apple Inc. was founded by Steve Jobs.") # list[Entity]
|
||||
ner = NERExtractor(method="llm", llm_provider=llm)
|
||||
entities = ner.extract("Apple Inc. was founded by Steve Jobs.")
|
||||
|
||||
rel = RelationExtractor(method="llm", provider="groq", llm_model="llama-3.3-70b-versatile")
|
||||
relationships = rel.extract(text, entities=entities) # list[Relation]
|
||||
rel = RelationExtractor(method="llm", llm_provider=llm)
|
||||
relationships = rel.extract(text, entities=entities)
|
||||
|
||||
trip = TripletExtractor(method="pattern")
|
||||
triplets = trip.extract(text) # list[Triplet]
|
||||
trip = TripletExtractor(method="llm", llm_provider=llm)
|
||||
triplets = trip.extract(text)
|
||||
```
|
||||
|
||||
**Extraction methods:** `"pattern"` (no API key), `"ml"` (local spaCy model), `"llm"` (any of the 9 supported providers)
|
||||
**Extraction methods:** `"pattern"` (no API key), `"ml"` (local model), `"llm"` (any of the 8 supported providers)
|
||||
|
||||
**Additional extractors:** `CoreferenceResolver`, `EventDetector`, `SemanticAnalyzer`, `SemanticNetworkExtractor`
|
||||
|
||||
@@ -141,17 +137,17 @@ Graph construction, graph algorithms, temporal model, and distance intelligence.
|
||||
from semantica.kg import GraphBuilder, GraphAnalyzer, TemporalGraphQuery, SimilarityCalculator
|
||||
from datetime import datetime
|
||||
|
||||
# Build: build() takes a {"entities": ..., "relationships": ...} dict
|
||||
# Build
|
||||
builder = GraphBuilder(merge_entities=True)
|
||||
kg = builder.build({"entities": entities, "relationships": relationships})
|
||||
kg = builder.build(entities=entities, relationships=relationships)
|
||||
|
||||
# Temporal graphs (v0.4.0)
|
||||
query_engine = TemporalGraphQuery(enable_temporal_reasoning=True)
|
||||
snapshot = query_engine.query_at_time(kg, query="", at_time=datetime(2021, 6, 15))
|
||||
|
||||
# Semantic similarity (v0.5.0): operates on embedding vectors
|
||||
calc = SimilarityCalculator(method="cosine")
|
||||
score = calc.cosine_similarity(vec_a, vec_b)
|
||||
# Semantic similarity (v0.5.0)
|
||||
calc = SimilarityCalculator()
|
||||
scores = calc.calculate_similarity(entity_a, entity_b)
|
||||
```
|
||||
|
||||
**Graph algorithms available:** centrality calculation, community detection, connectivity analysis, entity resolution, link prediction, path finding, similarity calculation
|
||||
@@ -179,23 +175,19 @@ Derives new facts from existing knowledge using multiple inference strategies.
|
||||
```python
|
||||
from semantica.reasoning import Reasoner, DatalogReasoner
|
||||
|
||||
# Forward chaining: facts and rules as predicate(args) / IF-THEN strings
|
||||
# Rule-based reasoning
|
||||
engine = Reasoner()
|
||||
engine.add_fact("Manager(Alice)")
|
||||
engine.add_rule("IF Manager(?x) THEN HasAuthority(?x)")
|
||||
results = engine.forward_chain() # list[InferenceResult] with .conclusion, .rule_used
|
||||
engine.apply_transitivity("located_in")
|
||||
engine.apply_symmetry("knows")
|
||||
result = engine.infer()
|
||||
|
||||
# Datalog: recursive Horn clause rules (v0.4.0)
|
||||
datalog = DatalogReasoner()
|
||||
datalog.add_fact("parent(tom, bob)")
|
||||
datalog.add_fact("parent(bob, ann)")
|
||||
datalog.add_rule("ancestor(X, Y) :- parent(X, Y).")
|
||||
datalog = DatalogEngine()
|
||||
datalog.add_rule("ancestor(X, Z) :- parent(X, Y), ancestor(Y, Z).")
|
||||
datalog.derive_all()
|
||||
results = datalog.query("ancestor(tom, ?Z)") # [{"Z": "bob"}, {"Z": "ann"}], order not guaranteed
|
||||
results = datalog.query("ancestor(alice, ?)")
|
||||
```
|
||||
|
||||
**Engines:** `Reasoner` (forward/backward chaining), `ReteEngine`, `SPARQLReasoner`, `DatalogReasoner`, `TemporalReasoningEngine`, `GraphReasoner` (LLM)
|
||||
**Engines:** forward chaining, Rete network, deductive, abductive, SPARQL, Datalog: all produce explainable inference paths
|
||||
|
||||
|
||||
## Storage
|
||||
@@ -207,9 +199,9 @@ Generates and manages vector embeddings for semantic similarity.
|
||||
```python
|
||||
from semantica.embeddings import EmbeddingGenerator
|
||||
|
||||
generator = EmbeddingGenerator()
|
||||
embeddings = generator.generate_embeddings(["text1", "text2"]) # np.ndarray
|
||||
similarity = generator.compare_embeddings(embeddings[0], embeddings[1])
|
||||
generator = EmbeddingGenerator(model="sentence-transformers")
|
||||
embeddings = generator.generate(["text1", "text2"])
|
||||
similarity = generator.similarity(embeddings[0], embeddings[1])
|
||||
```
|
||||
|
||||
**Supported models:** Sentence-Transformers, FastEmbed, OpenAI, BGE
|
||||
@@ -223,18 +215,12 @@ Multi-backend vector database with hybrid search support.
|
||||
```python
|
||||
from semantica.vector_store import VectorStore
|
||||
|
||||
store = VectorStore(backend="faiss", dimension=768)
|
||||
|
||||
# Raw vectors
|
||||
ids = store.store_vectors(embeddings) # returns generated ids
|
||||
hits = store.search_vectors(query_vector, k=10)
|
||||
|
||||
# Or store text and let the store embed it
|
||||
store.add_documents(["Apple was founded in 1976.", "Google was founded in 1998."])
|
||||
results = store.search("tech company founding dates", limit=10)
|
||||
store = VectorStore(backend="faiss", dimension=768)
|
||||
store.add_vectors(embeddings, ids)
|
||||
results = store.search(query_vector, top_k=10)
|
||||
```
|
||||
|
||||
**Backends:** FAISS, Pinecone, Weaviate, Qdrant, Milvus, PgVector, SQLite, in-memory
|
||||
**Backends:** FAISS, Pinecone, Weaviate, Qdrant, Milvus, PgVector, in-memory
|
||||
|
||||
**Search modes:** semantic top-k, hybrid (vector + keyword), metadata-filtered
|
||||
|
||||
@@ -246,8 +232,8 @@ Connects to graph databases for persistent, query-able storage.
|
||||
from semantica.graph_store import GraphStore
|
||||
|
||||
store = GraphStore(backend="neo4j")
|
||||
store.add_nodes([{"id": "acme", "type": "Organization", "properties": {"name": "Acme"}}])
|
||||
store.add_edges([{"source": "alice", "target": "acme", "type": "works_for"}])
|
||||
store.add_nodes(entities)
|
||||
store.add_edges(relationships)
|
||||
results = store.query("MATCH (n)-[r]->(m) RETURN n, r, m")
|
||||
```
|
||||
|
||||
@@ -260,9 +246,9 @@ RDF triple-based storage with SPARQL query support.
|
||||
```python
|
||||
from semantica.triplet_store import TripletStore
|
||||
|
||||
store = TripletStore(backend="oxigraph")
|
||||
store.add_triplets(triplets) # list of Triplet objects (or add_triplet for one)
|
||||
results = store.execute_query("SELECT ?s ?p ?o WHERE { ?s ?p ?o }")
|
||||
store = TripletStore(backend="blazegraph")
|
||||
store.add_triplets(subject, predicate, obj)
|
||||
results = store.sparql("SELECT ?s ?p ?o WHERE { ?s ?p ?o }")
|
||||
```
|
||||
|
||||
**Backends:** Oxigraph (embedded), Blazegraph, Apache Jena, RDF4J
|
||||
@@ -275,18 +261,15 @@ results = store.execute_query("SELECT ?s ?p ?o WHERE { ?s ?p ?o }")
|
||||
Detects, scores, and merges duplicate entities across sources.
|
||||
|
||||
```python
|
||||
from semantica.deduplication import DuplicateDetector, EntityMerger
|
||||
from semantica.deduplication import EntityResolver
|
||||
|
||||
detector = DuplicateDetector(similarity_threshold=0.85)
|
||||
candidates = detector.detect_duplicates(entities)
|
||||
|
||||
merger = EntityMerger()
|
||||
operations = merger.merge_duplicates(entities, strategy="keep_most_complete")
|
||||
resolver = EntityResolver()
|
||||
merged = resolver.resolve(entities, strategy="semantic_v2")
|
||||
```
|
||||
|
||||
**v2 candidate-generation modes** (`blocking_v2`, `hybrid_v2`, `semantic_v2`) are up to 7x faster than v1.
|
||||
**v2 strategies** (`blocking_v2`, `hybrid_v2`, `semantic_v2`) are up to 7x faster than v1.
|
||||
|
||||
**Components:** `DuplicateDetector`, `EntityMerger`, `ClusterBuilder`, `MergeStrategyManager`
|
||||
**Components:** `EntityResolver`, `DuplicateDetector`, `EntityMerger`, `SimilarityCalculator`, `ClusterBuilder`
|
||||
|
||||
**`DuplicateDetector` options:** `max_results`, `top_k_per_entity`, `min_similarity`, `sort_by`
|
||||
|
||||
@@ -295,13 +278,14 @@ operations = merger.merge_duplicates(entities, strategy="keep_most_complete")
|
||||
Detects and resolves fact conflicts across overlapping knowledge sources.
|
||||
|
||||
```python
|
||||
from semantica.conflicts import ConflictDetector, ConflictResolver
|
||||
from semantica.conflicts import ConflictDetector
|
||||
|
||||
conflicts = ConflictDetector().detect_conflicts(entities) # list of entity dicts
|
||||
resolved = ConflictResolver().resolve_conflicts(conflicts, strategy="most_recent")
|
||||
detector = ConflictDetector()
|
||||
conflicts = detector.detect_conflicts(kg)
|
||||
resolved = detector.resolve(conflicts, strategy="most_recent")
|
||||
```
|
||||
|
||||
**Detection types:** value conflicts, type conflicts, relationship conflicts, temporal conflicts, logical conflicts
|
||||
**Detection types:** value conflicts, type conflicts, temporal conflicts, logical conflicts
|
||||
|
||||
**Resolution strategies:** prefer most recent, prefer most reliable source, majority vote, flag for manual review
|
||||
|
||||
@@ -314,7 +298,6 @@ Agent context graphs, decision tracking, causal chains, and precedent search.
|
||||
|
||||
```python
|
||||
from semantica.context import AgentContext, ContextGraph
|
||||
from semantica.vector_store import VectorStore
|
||||
|
||||
context = AgentContext(
|
||||
vector_store=VectorStore(backend="faiss", dimension=768),
|
||||
@@ -345,7 +328,7 @@ W3C PROV-O compliant lineage tracking across all modules.
|
||||
from semantica.provenance import ProvenanceManager
|
||||
|
||||
manager = ProvenanceManager()
|
||||
manager.track_entity("entity_1", source="document.pdf", metadata={"type": "person"})
|
||||
manager.track_entity("entity_1", "document.pdf", "person")
|
||||
lineage = manager.get_lineage("entity_1")
|
||||
```
|
||||
|
||||
@@ -381,8 +364,8 @@ RDFExporter().export(graph, file_path="graph.ttl", format="turtle")
|
||||
# Analytics
|
||||
ParquetExporter().export(graph, file_path="output/graph.parquet")
|
||||
|
||||
# ArangoDB: writes AQL INSERT statements to the given path
|
||||
ArangoAQLExporter().export(graph, file_path="graph.aql")
|
||||
# ArangoDB
|
||||
aql = ArangoAQLExporter().export(graph)
|
||||
```
|
||||
|
||||
**Export formats:** RDF (Turtle, JSON-LD, N-Triples, XML), Parquet, ArangoDB AQL, CSV, OWL, Arrow, LPG, YAML, distance matrices
|
||||
@@ -407,24 +390,16 @@ viz.visualize_network(graph, output="html", file_path="graph.html")
|
||||
Pipeline DSL with parallel workers, retry policies, and failure handling.
|
||||
|
||||
```python
|
||||
from semantica.pipeline import PipelineBuilder, ExecutionEngine
|
||||
from semantica.ingest import FileIngestor
|
||||
from semantica.semantic_extract import NERExtractor
|
||||
from semantica.pipeline import Pipeline
|
||||
|
||||
builder = PipelineBuilder()
|
||||
|
||||
# Each step type dispatches to a handler you register (or supply explicitly)
|
||||
builder.register_step_handler("ingest", lambda data, **c: FileIngestor().ingest(c["source"]))
|
||||
builder.register_step_handler("extract", lambda docs, **c: NERExtractor(method="pattern").extract(docs[0].text))
|
||||
|
||||
builder.add_step("ingest", step_type="ingest", source="data/")
|
||||
builder.add_step("extract", step_type="extract")
|
||||
|
||||
pipeline = builder.connect_steps("ingest", "extract").build(name="docs_to_entities")
|
||||
result = ExecutionEngine().execute_pipeline(pipeline)
|
||||
pipeline = Pipeline()
|
||||
pipeline.add_step("ingest", FileIngestor())
|
||||
pipeline.add_step("extract", NERExtractor())
|
||||
pipeline.add_step("build", GraphBuilder())
|
||||
result = pipeline.run("data/")
|
||||
```
|
||||
|
||||
**Components:** `PipelineBuilder`, `Pipeline`, `ExecutionEngine`, `FailureHandler`, `PipelineValidator`, `ParallelismManager`, `ResourceScheduler`
|
||||
**Components:** `Pipeline`, `PipelineBuilder`, `ExecutionEngine`, `FailureHandler`, `PipelineValidator`, `ParallelismManager`, `ResourceScheduler`
|
||||
|
||||
### Explorer
|
||||
|
||||
@@ -453,7 +428,7 @@ llm = OpenAI(model="gpt-4o", api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = LiteLLM(model="anthropic/claude-opus-4-7", api_key=os.getenv("ANTHROPIC_API_KEY"))
|
||||
```
|
||||
|
||||
**Supported providers:** OpenAI, Anthropic, Google Gemini, Groq, Ollama, DeepSeek, Novita AI, HuggingFace, plus LiteLLM (100+ models via one interface)
|
||||
**Supported providers:** OpenAI, Anthropic, Google Gemini, Groq, Ollama, DeepSeek, Novita AI, LiteLLM (20+ models via one interface)
|
||||
|
||||
### MCP Server
|
||||
|
||||
@@ -463,50 +438,51 @@ Exposes Semantica as an MCP stdio server for IDE and agent integrations.
|
||||
python -m semantica.mcp_server
|
||||
```
|
||||
|
||||
**Integrations:** Claude Desktop, VS Code, Cursor, Windsurf, Cline. 15 MCP tools are exposed.
|
||||
**Integrations:** Claude Desktop, VS Code, Cursor, Windsurf, Cline: 15 MCP tools exposed
|
||||
|
||||
### Seed
|
||||
|
||||
Bootstrap knowledge graphs from verified structured sources: fixed-point reference data, controlled vocabularies, and domain anchors.
|
||||
|
||||
```python
|
||||
from semantica.seed import SeedDataManager
|
||||
from semantica.seed import SeedManager
|
||||
|
||||
seed = SeedDataManager()
|
||||
seed = SeedManager()
|
||||
seed.populate(kg, dataset="companies", count=100)
|
||||
|
||||
# Load trusted reference data from CSV / JSON / a database / an API
|
||||
seed_data = seed.load_from_csv("seed_data/industries.csv", entity_type="Industry")
|
||||
|
||||
# Merge seed data with extraction output (seed values win on conflict by default)
|
||||
combined = seed.integrate_with_extracted(
|
||||
{"entities": seed_data, "relationships": []},
|
||||
{"entities": extracted_entities, "relationships": extracted_relationships},
|
||||
merge_strategy="seed_first",
|
||||
)
|
||||
# Load domain seeds from file or built-in datasets
|
||||
seed.load_from_file("seed_data/industries.json")
|
||||
seed.inject(kg) # merges seed nodes without duplicating existing entities
|
||||
```
|
||||
|
||||
**Use cases:** anchoring extraction with known entities, pre-populating ontology classes, deterministic test graph generation.
|
||||
|
||||
### Evals
|
||||
|
||||
Scores decision-intelligence outputs (decision records, audit trails, reasoning
|
||||
text) with a registry of deterministic and model-backed evaluators plus a small
|
||||
run harness.
|
||||
Evaluation framework for measuring KG quality, extraction accuracy, and pipeline performance.
|
||||
|
||||
```python
|
||||
from semantica.evals import evaluate, list_evaluators
|
||||
from semantica.evals import KGEvaluator, ExtractionEvaluator, PipelineEvaluator, RegressionTracker
|
||||
|
||||
list_evaluators()
|
||||
# ['decision_scores', 'exact_match', 'keyword_check', 'length_range',
|
||||
# 'levenshtein', 'llm_as_judge', 'numeric_range', 'regex_match', 'rouge',
|
||||
# 'temporal_range']
|
||||
# KG quality
|
||||
report = KGEvaluator().evaluate(kg, ontology=ontology)
|
||||
print(f"Completeness: {report.completeness:.2%} Consistency: {report.consistency:.2%}")
|
||||
|
||||
cases = [("apple", "aple"), ("night", "nacht")]
|
||||
summary = evaluate(cases, evaluators=["levenshtein"])
|
||||
print(summary.total, summary.passed, summary.pass_rate)
|
||||
# Extraction accuracy
|
||||
report = ExtractionEvaluator().evaluate_ner(predictions=extracted, gold_standard=annotated)
|
||||
print(f"Precision: {report.precision:.3f} Recall: {report.recall:.3f} F1: {report.f1:.3f}")
|
||||
|
||||
# Pipeline throughput and latency
|
||||
metrics = PipelineEvaluator().benchmark(pipeline, data="data/", bench_runs=5)
|
||||
print(f"Throughput: {metrics.docs_per_second:.1f} docs/sec")
|
||||
|
||||
# Regression tracking across runs
|
||||
tracker = RegressionTracker(db_path="eval_history.db")
|
||||
run_id = tracker.record_run(pipeline_version="v1.2.0", metrics=metrics)
|
||||
diff = tracker.compare(run_id, baseline_run_id="run_abc123")
|
||||
```
|
||||
|
||||
**Public API:** `evaluate(cases, evaluators, config=None)`, `list_evaluators()`, `get_evaluator(name)`, and the `EvalMetric` / `CaseResult` / `EvalSummary` result types. See the [Evals reference](/reference/evals).
|
||||
**Components:** `KGEvaluator`, `ExtractionEvaluator`, `PipelineEvaluator`, `RegressionTracker`
|
||||
|
||||
### Core
|
||||
|
||||
@@ -515,20 +491,20 @@ Base classes, shared data models, and the plugin registry used across all module
|
||||
```python
|
||||
from semantica.core import Semantica, PluginRegistry, ConfigManager
|
||||
|
||||
# ConfigManager loads a Config; Config.get() does dotted lookups
|
||||
config = ConfigManager().load_from_file("config.yaml")
|
||||
batch = config.get("processing.batch_size", default=32)
|
||||
|
||||
# Top-level orchestrator: pass the Config object (or a dict), not a path
|
||||
sem = Semantica(config=config)
|
||||
# Top-level orchestrator
|
||||
sem = Semantica(config_path="config.yaml")
|
||||
sem.initialize()
|
||||
|
||||
# Plugin registry: register custom components under a name
|
||||
# Plugin registry: register custom components
|
||||
registry = PluginRegistry()
|
||||
registry.register_plugin("my_ingestor", MyCustomIngestor, version="1.0.0")
|
||||
registry.register("my_ingestor", MyCustomIngestor)
|
||||
|
||||
# Config management
|
||||
config = ConfigManager(config_path="config.yaml")
|
||||
batch = config.get("processing.batch_size", default=32)
|
||||
```
|
||||
|
||||
**Components:** `Semantica`, `PluginRegistry`, `ConfigManager`, `Config`, `LifecycleManager`, `HealthStatus`, `MethodRegistry`
|
||||
**Components:** `Semantica`, `PluginRegistry`, `ConfigManager`, `LifecycleManager`, `HealthMonitor`, `Config`
|
||||
|
||||
### Utils
|
||||
|
||||
@@ -556,13 +532,11 @@ from semantica.semantic_extract import NERExtractor, RelationExtractor
|
||||
from semantica.kg import GraphBuilder
|
||||
|
||||
sources = FileIngestor().ingest("data/")
|
||||
text = DocumentParser().parse(sources[0].path)["full_text"]
|
||||
ner = NERExtractor(method="llm", provider="groq", llm_model="llama-3.3-70b-versatile")
|
||||
rel = RelationExtractor(method="llm", provider="groq", llm_model="llama-3.3-70b-versatile")
|
||||
entities = ner.extract(text)
|
||||
relationships = rel.extract(text, entities=entities)
|
||||
parsed = DocumentParser().parse(sources[0])
|
||||
entities = NERExtractor(method="llm", llm_provider=llm).extract(parsed)
|
||||
relationships = RelationExtractor(method="llm", llm_provider=llm).extract(parsed, entities=entities)
|
||||
graph = GraphBuilder(merge_entities=True).build(
|
||||
{"entities": entities, "relationships": relationships}
|
||||
entities=entities, relationships=relationships
|
||||
)
|
||||
```
|
||||
|
||||
@@ -581,20 +555,16 @@ from semantica.vector_store import VectorStore
|
||||
context = AgentContext(
|
||||
vector_store=VectorStore(backend="faiss", dimension=768),
|
||||
knowledge_graph=ContextGraph(advanced_analytics=True),
|
||||
graph_expansion=True,
|
||||
)
|
||||
context.load_graph("company_kg.json")
|
||||
|
||||
# store() extracts entities and populates the graph + vector index
|
||||
context.store([{"content": "Steve Wozniak co-founded Apple with Steve Jobs."}])
|
||||
|
||||
# retrieve() blends vector similarity with multi-hop graph traversal
|
||||
results = context.retrieve(
|
||||
result = context.query(
|
||||
"What companies did Apple alumni found?",
|
||||
use_graph=True,
|
||||
expand_graph=True,
|
||||
mode="graphrag",
|
||||
reasoning=True,
|
||||
)
|
||||
for r in results:
|
||||
print(f"[{r['score']:.3f}] {r['content']} (source: {r['source']})")
|
||||
for claim in result.claims:
|
||||
print(f"{claim.text} → {claim.source_node}")
|
||||
```
|
||||
|
||||
**Best for:** question-answering systems, RAG with source attribution, research assistants
|
||||
@@ -636,22 +606,18 @@ precedents = context.find_precedents("model selection", limit=5)
|
||||
|
||||
```python
|
||||
from semantica.ingest import FileIngestor
|
||||
from semantica.parse import DocumentParser
|
||||
from semantica.semantic_extract import NERExtractor
|
||||
from semantica.kg import GraphBuilder
|
||||
from semantica.provenance import ProvenanceManager
|
||||
from semantica.export import RDFExporter
|
||||
|
||||
sources = FileIngestor().ingest("records/")
|
||||
ner = NERExtractor(method="llm", provider="groq", llm_model="llama-3.3-70b-versatile")
|
||||
entities = ner.extract(DocumentParser().parse(sources[0].path)["full_text"])
|
||||
graph = GraphBuilder(merge_entities=True).build({"entities": entities, "relationships": []})
|
||||
|
||||
entities = NERExtractor(method="llm", llm_provider=llm).extract(sources)
|
||||
graph = GraphBuilder(merge_entities=True).build(entities=entities, relationships=[])
|
||||
prov = ProvenanceManager()
|
||||
prov.track_entity("entity_id", source="records/filing.pdf", metadata={"extractor": "llm"})
|
||||
lineage = prov.get_lineage("entity_id")
|
||||
lineage = prov.get_entity_lineage("entity_id")
|
||||
|
||||
RDFExporter().export(graph, file_path="audit.ttl", format="turtle")
|
||||
RDFExporter(include_provenance=True).export(graph, file_path="audit.ttl", format="turtle")
|
||||
```
|
||||
|
||||
**Best for:** HIPAA, SOX, GDPR, FDA 21 CFR Part 11 deployments
|
||||
@@ -666,25 +632,18 @@ RDFExporter().export(graph, file_path="audit.ttl", format="turtle")
|
||||
from semantica.ingest import WebIngestor
|
||||
from semantica.normalize import TextNormalizer
|
||||
from semantica.semantic_extract import NERExtractor, RelationExtractor
|
||||
from semantica.graph_store import GraphStore
|
||||
from semantica.kg import GraphBuilder
|
||||
from semantica.graph_store import Neo4jStore
|
||||
|
||||
ingestor = WebIngestor()
|
||||
pages = WebIngestor(max_depth=2).ingest("https://example.com")
|
||||
normalizer = TextNormalizer()
|
||||
ner = NERExtractor(method="pattern")
|
||||
rel = RelationExtractor(method="pattern")
|
||||
store = Neo4jStore(uri="bolt://localhost:7687", user="neo4j", password="password")
|
||||
|
||||
# The generic GraphStore wrapper exposes the add_nodes/add_edges interface
|
||||
# GraphBuilder persists through; a raw Neo4jStore does not
|
||||
store = GraphStore(backend="neo4j", uri="bolt://localhost:7687", user="neo4j", password="password")
|
||||
builder = GraphBuilder(merge_entities=True, graph_store=store)
|
||||
|
||||
for url in ["https://example.com/a", "https://example.com/b"]:
|
||||
page = ingestor.ingest_url(url) # WebContent, has .text
|
||||
for page in pages:
|
||||
text = normalizer.normalize_text(page.text)
|
||||
entities = ner.extract(text)
|
||||
relationships = rel.extract(text, entities=entities)
|
||||
builder.build({"entities": entities, "relationships": relationships})
|
||||
entities = NERExtractor().extract(text)
|
||||
relationships = RelationExtractor().extract(text, entities=entities)
|
||||
store.add_nodes(entities)
|
||||
store.add_edges(relationships)
|
||||
```
|
||||
|
||||
**Best for:** competitive intelligence, news monitoring, research aggregation
|
||||
@@ -733,8 +692,8 @@ versioner.create_snapshot(kg, "2024-Q1", author="user@example.com", description=
|
||||
| [vector_store](/reference/vector_store) | Vector database | `VectorStore` |
|
||||
| [graph_store](/reference/graph_store) | Graph database | `GraphStore` |
|
||||
| [triplet_store](/reference/triplet_store) | RDF triple store | `TripletStore` |
|
||||
| [deduplication](/reference/deduplication) | Entity resolution | `DuplicateDetector`, `EntityMerger`, `ClusterBuilder`, `MergeStrategyManager` |
|
||||
| [conflicts](/reference/conflicts) | Conflict resolution | `ConflictDetector`, `ConflictResolver`, `SourceTracker` |
|
||||
| [deduplication](/reference/deduplication) | Entity resolution | `EntityResolver`, `DuplicateDetector`, `ClusterBuilder`, `MergeStrategyManager` |
|
||||
| [conflicts](/reference/conflicts) | Conflict resolution | `ConflictDetector` |
|
||||
| [context](/reference/context) | Agent context & decisions | `AgentContext`, `ContextGraph` |
|
||||
| [provenance](/reference/provenance) | W3C PROV-O lineage | `ProvenanceManager` |
|
||||
| [change_management](/reference/change_management) | Version control | `TemporalVersionManager` |
|
||||
@@ -744,11 +703,11 @@ versioner.create_snapshot(kg, "2024-Q1", author="user@example.com", description=
|
||||
| [explorer](/reference/explorer) | Knowledge Explorer UI | `semantica-explorer --graph <file>` |
|
||||
| [llms](/reference/llms) | LLM providers | `Groq`, `OpenAI`, `create_provider` |
|
||||
| [mcp_server](/reference/mcp_server) | MCP stdio server | `python -m semantica.mcp_server` |
|
||||
| [seed](/reference/seed) | KG bootstrapping from structured sources | `SeedDataManager` |
|
||||
| [evals](/reference/evals) | Decision-intelligence evaluation | `evaluate`, `list_evaluators`, `EvalSummary` |
|
||||
| [seed](/reference/seed) | KG bootstrapping from structured sources | `SeedManager` |
|
||||
| [evals](/reference/evals) | Quality evaluation | `KGEvaluator`, `ExtractionEvaluator`, `PipelineEvaluator`, `RegressionTracker` |
|
||||
| [core](/reference/core) | Base classes & registry | `Semantica`, `ConfigManager`, `PluginRegistry`, `LifecycleManager` |
|
||||
| [utils](/reference/utils) | Shared utilities | `helpers`, `validators` |
|
||||
|
||||
- [Getting Started](/getting-started): your first knowledge graph in 5 minutes.
|
||||
- [Cookbook](/cookbook): 40+ domain notebooks with real-world examples.
|
||||
- [API Reference](/reference/context): full technical documentation.
|
||||
- [Getting Started](/getting-started) — Your first knowledge graph in 5 minutes.
|
||||
- [Cookbook](/cookbook) — 40+ domain notebooks with real-world examples.
|
||||
- [API Reference](/reference/context) — Full technical documentation.
|
||||
|
||||
@@ -76,5 +76,5 @@ By contributing to Semantica, you agree that your contributions will be licensed
|
||||
|
||||
## See Also
|
||||
|
||||
- [Contributing](/contributing-guide): how to contribute to the project.
|
||||
- [Citation](/citation): how to cite Semantica in research.
|
||||
- [Contributing](/contributing-guide) — How to contribute to the project.
|
||||
- [Citation](/citation) — How to cite Semantica in research.
|
||||
|
||||
+5
-5
@@ -5,7 +5,7 @@ icon: "rocket"
|
||||
---
|
||||
|
||||
<Info>
|
||||
**v0.6.7**: first-class LangChain integration, SAP OData ingestor, human-editable Markdown persistence for `ContextGraph`, and a structured Action layer for the reasoning engine. <a href="https://github.com/semantica-agi/semantica/releases" style={{color:"#10B981",fontWeight:600,textDecoration:"none"}}>What's new →</a>
|
||||
**v0.6.7** — first-class LangChain integration, SAP OData ingestor, human-editable Markdown persistence for `ContextGraph`, and a structured Action layer for the reasoning engine. <a href="https://github.com/semantica-agi/semantica/releases" style={{color:"#10B981",fontWeight:600,textDecoration:"none"}}>What's new →</a>
|
||||
</Info>
|
||||
|
||||
This guide walks you through the end-to-end pipeline for building your first knowledge graph. Start here after installation. An LLM API key is optional: pattern-based extraction works out of the box.
|
||||
@@ -454,7 +454,7 @@ pip install --upgrade semantica
|
||||
|
||||
## Next Steps
|
||||
|
||||
- [Core Concepts](/concepts): knowledge graphs, ontologies, and reasoning engines (the mental model behind Semantica).
|
||||
- [Module Reference](/modules): every module explained with key classes and common chains.
|
||||
- [API Reference](/reference/context): complete documentation for every module, class, and parameter.
|
||||
- [Cookbook](/cookbook): 40+ interactive Jupyter notebooks with real-world datasets.
|
||||
- [Core Concepts](/concepts) — Knowledge graphs, ontologies, reasoning engines: the mental model behind Semantica.
|
||||
- [Module Reference](/modules) — Every module explained with key classes and common chains.
|
||||
- [API Reference](/reference/context) — Complete documentation for every module, class, and parameter.
|
||||
- [Cookbook](/cookbook) — 40+ interactive Jupyter notebooks with real-world datasets.
|
||||
|
||||
+21
-21
@@ -30,28 +30,28 @@ icon: "brain"
|
||||
|
||||
## What You Get
|
||||
|
||||
- **AgentContext**: memory, decision tracking, and graph-backed retrieval behind one API
|
||||
- **AgentContext** — Memory, decision tracking, and graph-backed retrieval behind one API
|
||||
- Conversation history and checkpoint diffing
|
||||
- Persist and restore full context state to disk
|
||||
- **ContextGraph**: thread-safe in-memory knowledge graph
|
||||
- **ContextGraph** — Thread-safe in-memory knowledge graph
|
||||
- PageRank, centrality, community detection, temporal validity
|
||||
- Cross-graph navigation and link traversal
|
||||
- **AgentMemory**: embedding-backed memory with retention policy
|
||||
- **AgentMemory** — Embedding-backed memory with retention policy
|
||||
- LRU eviction at configurable `max_memory_size`
|
||||
- Per-conversation history isolation
|
||||
- **DecisionRecorder**: records decisions with causal chains and confidence scores
|
||||
- **DecisionRecorder** — Records decisions with causal chains and confidence scores
|
||||
- Temporal validity windows (`valid_from` / `valid_until`)
|
||||
- Cross-system context capture on every decision
|
||||
- **PolicyEngine**: versioned policy storage in the knowledge graph
|
||||
- **PolicyEngine** — Versioned policy storage in the knowledge graph
|
||||
- Compliance checking against recorded decisions
|
||||
- Policy exception tracking with approver audit trail
|
||||
- **EntityLinker**: maps entity text to stable URIs
|
||||
- **EntityLinker** — Maps entity text to stable URIs
|
||||
- Creates typed links between entity IDs
|
||||
- Prevents "Apple", "Apple Inc.", "AAPL" becoming separate nodes
|
||||
- **ContextRetriever**: fuses vector similarity, graph traversal, and agent memory
|
||||
- **ContextRetriever** — Fuses vector similarity, graph traversal, and agent memory
|
||||
- Richer context than pure vector search
|
||||
- Configurable `hybrid_alpha` and expansion hops
|
||||
- **CausalChainAnalyzer**: traces upstream causes and downstream effects of any decision
|
||||
- **CausalChainAnalyzer** — Traces upstream causes and downstream effects of any decision
|
||||
- Explainability paths with relationship types
|
||||
- Configurable depth and direction
|
||||
|
||||
@@ -273,7 +273,7 @@ icon: "brain"
|
||||
</Tip>
|
||||
|
||||
<Tip>
|
||||
**Persist your context between runs.** `VectorStore` does not auto-persist; passing `index_path=` to its constructor is a no-op. Call `context.save("agent_state/")` to write memory, the vector index, and the graph to disk, and `context.load("agent_state/")` on the next process to restore them. See the "Persist & Restore" tab under [Real-World Patterns](#real-world-patterns) below.
|
||||
**Persist your context between runs.** `VectorStore` does not auto-persist — passing `index_path=` to its constructor is a no-op. Call `context.save("agent_state/")` to write memory, the vector index, and the graph to disk, and `context.load("agent_state/")` on the next process to restore them. See the "Persist & Restore" tab under [Real-World Patterns](#real-world-patterns) below.
|
||||
</Tip>
|
||||
|
||||
### Memory Methods
|
||||
@@ -449,7 +449,7 @@ print("Nodes: {}, Edges: {}".format(stats["node_count"], stats["edge_count"]))
|
||||
`ContextGraph` exposes a full Distance Intelligence API for exploring semantic neighborhoods and blending proximity into retrieval.
|
||||
|
||||
<Info>
|
||||
Full Distance Intelligence reference (distance matrices, API endpoints, embedding cache, Explorer UI) is covered in the dedicated [Distance Intelligence](/reference/distance) page. This section documents the context-layer API.
|
||||
Full Distance Intelligence reference — distance matrices, API endpoints, embedding cache, Explorer UI — is covered in the dedicated [Distance Intelligence](/reference/distance) page. This section documents the context-layer API.
|
||||
</Info>
|
||||
|
||||
### Neighbors with Distance Metadata
|
||||
@@ -480,7 +480,7 @@ for n in neighbors:
|
||||
| Added field | Type | Description |
|
||||
| :---------- | :---- | :----------- |
|
||||
| `distance_band` | `str` | `"direct"` (1 hop) / `"near"` (2) / `"mid-range"` (3–4) / `"distant"` (5+) |
|
||||
| `confidence_decay` | `float` | `edge_weight ^ hop_count`; decays with each hop |
|
||||
| `confidence_decay` | `float` | `edge_weight ^ hop_count` — decays with each hop |
|
||||
| `path_to_anchor` | `List[str]` | Shortest path from anchor node to this neighbor |
|
||||
| `hop_count` | `int` | BFS depth from anchor |
|
||||
|
||||
@@ -659,7 +659,7 @@ if not receipt.complete:
|
||||
```
|
||||
|
||||
<Warning>
|
||||
Check the receipt. The call returning is not proof the data is gone. FAISS,
|
||||
Check the receipt — the call returning is not proof the data is gone. FAISS,
|
||||
Milvus, and Weaviate expose no delete method, so erasure cannot be completed on
|
||||
those backends today; the receipt reports `unsupported` rather than a success it
|
||||
did not achieve.
|
||||
@@ -687,9 +687,9 @@ At least one store is required; a store that is not supplied reports
|
||||
|
||||
| Status | Meaning |
|
||||
| :--- | :--- |
|
||||
| `erased` | Reached, data removed. On the vectors leg this means the store accepted the delete for the ids given; backends offer no portable existence check, so it is not a count of embeddings that were really there |
|
||||
| `erased` | Reached, data removed. On the vectors leg this means the store accepted the delete for the ids given — backends offer no portable existence check, so it is not a count of embeddings that were really there |
|
||||
| `not_found` | Reached, held nothing for this entity |
|
||||
| `not_configured` | No such store was bound: normal, not a failure |
|
||||
| `not_configured` | No such store was bound — normal, not a failure |
|
||||
| `unsupported` | The store cannot delete at all; retrying will not help |
|
||||
| `failed` | The store was reached and the deletion did not succeed |
|
||||
|
||||
@@ -721,7 +721,7 @@ receipt.to_dict()
|
||||
# }
|
||||
```
|
||||
|
||||
Erasure runs outward-in: vectors, then memory, then the graph. The tombstone is
|
||||
Erasure runs outward-in — vectors, then memory, then the graph. The tombstone is
|
||||
the durable attestation that an erasure happened, so it is written last: a crash
|
||||
mid-cascade leaves the node present and the receipt incomplete, rather than a
|
||||
tombstone claiming more than actually happened. A store that raises is recorded
|
||||
@@ -1087,10 +1087,10 @@ class EntityLink:
|
||||
</Tab>
|
||||
</Tabs>
|
||||
|
||||
- [Vector Store](/reference/vector_store): embedding storage backend for memory retrieval.
|
||||
- [Knowledge Graph](/reference/kg): graph algorithms and analytics used inside ContextGraph.
|
||||
- [Reasoning](/guides/reasoning): logical inference layered on top of context.
|
||||
- [Provenance](/guides/provenance): W3C PROV-O lineage for every stored fact.
|
||||
- [Vector Store](/reference/vector_store) — Embedding storage backend for memory retrieval.
|
||||
- [Knowledge Graph](/reference/kg) — Graph algorithms and analytics used inside ContextGraph.
|
||||
- [Reasoning](reasoning) — Logical inference layered on top of context.
|
||||
- [Provenance](provenance) — W3C PROV-O lineage for every stored fact.
|
||||
|
||||
- [Context Module](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/19_Context_Module.ipynb): memory and decision tracking · Intermediate
|
||||
- [Advanced Context Engineering](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb): production FAISS + Neo4j setup · Advanced
|
||||
- [Context Module](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/19_Context_Module.ipynb) — Memory and decision tracking · Intermediate
|
||||
- [Advanced Context Engineering](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb) — Production FAISS + Neo4j setup · Advanced
|
||||
|
||||
@@ -129,7 +129,7 @@ from semantica.llms import Groq, OpenAI, LiteLLM, HuggingFaceLLM
|
||||
from semantica.llms import LiteLLM
|
||||
|
||||
llm = LiteLLM(
|
||||
model="anthropic/claude-sonnet-5",
|
||||
model="anthropic/claude-sonnet-4-20250514",
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
temperature=0.0,
|
||||
)
|
||||
@@ -198,7 +198,7 @@ llm = Groq(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.1-8b-instant")
|
||||
# Method 3: Multiple providers via LiteLLM
|
||||
providers = {
|
||||
"fast": LiteLLM(model="groq/llama-3.1-8b-instant", api_key=os.getenv("GROQ_API_KEY")),
|
||||
"smart": LiteLLM(model="anthropic/claude-sonnet-5", api_key=os.getenv("ANTHROPIC_API_KEY"))
|
||||
"smart": LiteLLM(model="anthropic/claude-sonnet-4-20250514", api_key=os.getenv("ANTHROPIC_API_KEY"))
|
||||
}
|
||||
```
|
||||
|
||||
@@ -252,7 +252,7 @@ from semantica.llms import LiteLLM
|
||||
# pip install "semantica[llm-litellm]"
|
||||
|
||||
# Anthropic Claude
|
||||
llm = LiteLLM(model="anthropic/claude-opus-4-7", api_key=os.getenv("ANTHROPIC_API_KEY"))
|
||||
llm = LiteLLM(model="anthropic/claude-opus-4-5", api_key=os.getenv("ANTHROPIC_API_KEY"))
|
||||
|
||||
# Google Gemini
|
||||
llm = LiteLLM(model="gemini/gemini-1.5-pro", api_key=os.getenv("GOOGLE_API_KEY"))
|
||||
@@ -267,7 +267,7 @@ llm = LiteLLM(model="deepseek/deepseek-chat", api_key=os.getenv("DEEP
|
||||
llm = LiteLLM(model="azure/gpt-4o", api_key=os.getenv("AZURE_API_KEY"))
|
||||
|
||||
# AWS Bedrock
|
||||
llm = LiteLLM(model="bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0")
|
||||
llm = LiteLLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
|
||||
|
||||
# Novita AI
|
||||
llm = LiteLLM(model="novita/deepseek/deepseek-v3.2", api_key=os.getenv("NOVITA_API_KEY"))
|
||||
@@ -297,12 +297,12 @@ from semantica.llms import LiteLLM
|
||||
|
||||
# Pattern: LiteLLM(model="<provider>/<model-name>")
|
||||
providers = {
|
||||
"Anthropic": LiteLLM(model="anthropic/claude-opus-4-7", api_key=os.getenv("ANTHROPIC_API_KEY")),
|
||||
"Anthropic": LiteLLM(model="anthropic/claude-opus-4-5", api_key=os.getenv("ANTHROPIC_API_KEY")),
|
||||
"Gemini": LiteLLM(model="gemini/gemini-1.5-pro", api_key=os.getenv("GOOGLE_API_KEY")),
|
||||
"Ollama": LiteLLM(model="ollama/llama3.2:3b", api_base="http://localhost:11434"),
|
||||
"DeepSeek": LiteLLM(model="deepseek/deepseek-chat", api_key=os.getenv("DEEPSEEK_API_KEY")),
|
||||
"Azure": LiteLLM(model="azure/gpt-4o", api_key=os.getenv("AZURE_API_KEY")),
|
||||
"Bedrock": LiteLLM(model="bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0"),
|
||||
"Bedrock": LiteLLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0"),
|
||||
"Cohere": LiteLLM(model="cohere/command-r-plus", api_key=os.getenv("COHERE_API_KEY")),
|
||||
"Novita AI": LiteLLM(model="novita/deepseek/deepseek-v3.2", api_key=os.getenv("NOVITA_API_KEY")),
|
||||
}
|
||||
@@ -416,7 +416,7 @@ for text in texts:
|
||||
| :---------- | :--------------------------- | :----------- |
|
||||
| **Entity Extraction** | `Groq("llama-3.3-70b-versatile")` | Fast, good accuracy for structured tasks |
|
||||
| **Relation Extraction** | `OpenAI("gpt-4o")` | Best at complex relationship reasoning |
|
||||
| **Complex Analysis** | `LiteLLM("anthropic/claude-sonnet-5")` | Highest reasoning capability |
|
||||
| **Complex Analysis** | `LiteLLM("anthropic/claude-sonnet-4-20250514")` | Highest reasoning capability |
|
||||
| **High Volume/Cost** | `LiteLLM("deepseek/deepseek-chat")` | Lowest cost per token |
|
||||
|
||||
### Error Handling
|
||||
|
||||
@@ -22,7 +22,6 @@ icon: "sitemap"
|
||||
| `LLMOntologyGenerator` | LLM-powered ontology generation for complex domains |
|
||||
| `SHACLGenerator` | Generate SHACL shapes from an ontology or KG schema |
|
||||
| `OntologyValidator` | Validate any graph against SHACL shapes: returns `SHACLValidationReport` |
|
||||
| `OntologyQualityGate` | Run deterministic ontology/KG quality checks for CI |
|
||||
| `OWLGenerator` | Serialize ontologies to Turtle, RDF/XML, JSON-LD |
|
||||
| `NamespaceManager` | IRI generation, prefix management, and namespace binding |
|
||||
| `OntologyEvaluator` | Coverage, completeness, and granularity quality metrics |
|
||||
@@ -82,38 +81,9 @@ engine.export_owl(ontology, "ontology.ttl", format="turtle")
|
||||
| :------ | :----------- |
|
||||
| `from_data(data)` | Run the 5-stage pipeline on entity/relationship data |
|
||||
| `validate_graph(kg, ontology=...)` | Check a knowledge graph against generated SHACL shapes |
|
||||
| `quality_check(ontology, graph_data=...)` | Return a deterministic quality report and CI-friendly pass/fail result |
|
||||
| `export_owl(ontology, path, format)` | Serialize to `"turtle"`, `"xml"`, or `"json-ld"` |
|
||||
| `evaluate(ontology, kg)` | Compute coverage, completeness, and granularity metrics |
|
||||
|
||||
### Ontology Quality Gate
|
||||
|
||||
Use the quality gate before export or deployment to catch structural issues
|
||||
without adding a runtime dependency:
|
||||
|
||||
```python
|
||||
from semantica.ontology import ontology_quality_check
|
||||
|
||||
report = ontology_quality_check(
|
||||
ontology,
|
||||
graph_data=kg,
|
||||
thresholds={"min_coverage": 0.8},
|
||||
)
|
||||
|
||||
if not report.passed:
|
||||
for issue in report.issues:
|
||||
print(issue.code, issue.message)
|
||||
```
|
||||
|
||||
The report checks class/property coverage, orphan schema elements, domain and
|
||||
range references, and unresolved KG relationship endpoints. It includes
|
||||
machine-readable issue codes, severity, counts, metrics, and threshold
|
||||
failures. The first version reports findings only; it does not auto-fix data.
|
||||
|
||||
### Thresholds
|
||||
|
||||
`min_coverage` (default `0.0`) sets the minimum required `coverage` score, the average of class and property coverage from `0.0` to `1.0`; the gate fails below it. `max_errors` (default `0.0`) caps how many `error`/`critical` issues are allowed before the gate fails. `max_warnings` (default `None`) caps `warning` issues the same way, and `None` means warnings alone never fail the gate. `fail_on_warnings` is a separate parameter, not a `thresholds` key, passed to `OntologyQualityGate(...)` or `.check(...)` directly; when `True`, a single warning fails the gate regardless of `max_warnings`.
|
||||
|
||||
## OntologyGenerator (5-Stage Pipeline)
|
||||
|
||||
**`OntologyGenerator`** auto-generates a formal ontology from your knowledge graph entities and relationships:
|
||||
|
||||
@@ -323,7 +323,7 @@ all_facts = datalog.derive_all()
|
||||
|
||||
# Query with variable pattern: variables start with uppercase or ?
|
||||
results = datalog.query("ancestor(alice, ?Z)")
|
||||
# → a list of binding dicts: [{"Z": "bob"}, {"Z": "charlie"}, {"Z": "dave"}] (order not guaranteed)
|
||||
# → [{"Z": "bob"}, {"Z": "charlie"}, {"Z": "dave"}]
|
||||
|
||||
# Clear and start over
|
||||
datalog.clear()
|
||||
|
||||
+2
-2
@@ -236,7 +236,7 @@ def _() -> list[str]:
|
||||
cwd=DOCS,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=600,
|
||||
timeout=300,
|
||||
)
|
||||
# Clean up zip regardless of outcome
|
||||
zip_path = os.path.join(DOCS, "export_ci_check.zip")
|
||||
@@ -263,7 +263,7 @@ def _() -> list[str]:
|
||||
except FileNotFoundError:
|
||||
return ["npx not found — skipping Mintlify export check (Node.js required)"]
|
||||
except subprocess.TimeoutExpired:
|
||||
return ["mintlify export timed out after 600 s"]
|
||||
return ["mintlify export timed out after 300 s"]
|
||||
|
||||
|
||||
# ── Summary ───────────────────────────────────────────────────────────────────
|
||||
|
||||
Generated
-653
@@ -33,9 +33,7 @@
|
||||
"devDependencies": {
|
||||
"@babel/core": "^7.29.6",
|
||||
"@eslint/js": "^9.39.4",
|
||||
"@testing-library/react": "^16.3.3",
|
||||
"@types/babel__core": "^7.20.5",
|
||||
"@types/jsdom": "^21.1.7",
|
||||
"@types/node": "^24.12.0",
|
||||
"@types/react": "^19.2.14",
|
||||
"@types/react-dom": "^19.2.3",
|
||||
@@ -45,34 +43,12 @@
|
||||
"eslint-plugin-react-hooks": "^7.0.1",
|
||||
"eslint-plugin-react-refresh": "^0.5.2",
|
||||
"globals": "^17.4.0",
|
||||
"jsdom": "^26.1.0",
|
||||
"tsx": "^4.21.0",
|
||||
"typescript": "~5.9.3",
|
||||
"typescript-eslint": "^8.57.0",
|
||||
"vite": "^6.4.2"
|
||||
}
|
||||
},
|
||||
"node_modules/@asamuzakjp/css-color": {
|
||||
"version": "3.2.0",
|
||||
"resolved": "https://registry.npmmirror.com/@asamuzakjp/css-color/-/css-color-3.2.0.tgz",
|
||||
"integrity": "sha512-K1A6z8tS3XsmCMM86xoWdn7Fkdn9m6RSVtocUrJYIwZnFVkng/PvkEoWtOWmP+Scc6saYWHWZYbndEEXxl24jw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@csstools/css-calc": "^2.1.3",
|
||||
"@csstools/css-color-parser": "^3.0.9",
|
||||
"@csstools/css-parser-algorithms": "^3.0.4",
|
||||
"@csstools/css-tokenizer": "^3.0.3",
|
||||
"lru-cache": "^10.4.3"
|
||||
}
|
||||
},
|
||||
"node_modules/@asamuzakjp/css-color/node_modules/lru-cache": {
|
||||
"version": "10.4.3",
|
||||
"resolved": "https://registry.npmmirror.com/lru-cache/-/lru-cache-10.4.3.tgz",
|
||||
"integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ==",
|
||||
"dev": true,
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/@babel/code-frame": {
|
||||
"version": "7.29.0",
|
||||
"resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.29.0.tgz",
|
||||
@@ -364,121 +340,6 @@
|
||||
"node": ">=6.9.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@csstools/color-helpers": {
|
||||
"version": "5.1.0",
|
||||
"resolved": "https://registry.npmmirror.com/@csstools/color-helpers/-/color-helpers-5.1.0.tgz",
|
||||
"integrity": "sha512-S11EXWJyy0Mz5SYvRmY8nJYTFFd1LCNV+7cXyAgQtOOuzb4EsgfqDufL+9esx72/eLhsRdGZwaldu/h+E4t4BA==",
|
||||
"dev": true,
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/csstools"
|
||||
},
|
||||
{
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/csstools"
|
||||
}
|
||||
],
|
||||
"license": "MIT-0",
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/@csstools/css-calc": {
|
||||
"version": "2.1.4",
|
||||
"resolved": "https://registry.npmmirror.com/@csstools/css-calc/-/css-calc-2.1.4.tgz",
|
||||
"integrity": "sha512-3N8oaj+0juUw/1H3YwmDDJXCgTB1gKU6Hc/bB502u9zR0q2vd786XJH9QfrKIEgFlZmhZiq6epXl4rHqhzsIgQ==",
|
||||
"dev": true,
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/csstools"
|
||||
},
|
||||
{
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/csstools"
|
||||
}
|
||||
],
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@csstools/css-parser-algorithms": "^3.0.5",
|
||||
"@csstools/css-tokenizer": "^3.0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/@csstools/css-color-parser": {
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmmirror.com/@csstools/css-color-parser/-/css-color-parser-3.1.0.tgz",
|
||||
"integrity": "sha512-nbtKwh3a6xNVIp/VRuXV64yTKnb1IjTAEEh3irzS+HkKjAOYLTGNb9pmVNntZ8iVBHcWDA2Dof0QtPgFI1BaTA==",
|
||||
"dev": true,
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/csstools"
|
||||
},
|
||||
{
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/csstools"
|
||||
}
|
||||
],
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@csstools/color-helpers": "^5.1.0",
|
||||
"@csstools/css-calc": "^2.1.4"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@csstools/css-parser-algorithms": "^3.0.5",
|
||||
"@csstools/css-tokenizer": "^3.0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/@csstools/css-parser-algorithms": {
|
||||
"version": "3.0.5",
|
||||
"resolved": "https://registry.npmmirror.com/@csstools/css-parser-algorithms/-/css-parser-algorithms-3.0.5.tgz",
|
||||
"integrity": "sha512-DaDeUkXZKjdGhgYaHNJTV9pV7Y9B3b644jCLs9Upc3VeNGg6LWARAT6O+Q+/COo+2gg/bM5rhpMAtf70WqfBdQ==",
|
||||
"dev": true,
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/csstools"
|
||||
},
|
||||
{
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/csstools"
|
||||
}
|
||||
],
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@csstools/css-tokenizer": "^3.0.4"
|
||||
}
|
||||
},
|
||||
"node_modules/@csstools/css-tokenizer": {
|
||||
"version": "3.0.4",
|
||||
"resolved": "https://registry.npmmirror.com/@csstools/css-tokenizer/-/css-tokenizer-3.0.4.tgz",
|
||||
"integrity": "sha512-Vd/9EVDiu6PPJt9yAh6roZP6El1xHrdvIVGjyBsHR0RYwNHgL7FJPyIIW4fANJNG6FtyZfvlRPpFI4ZM/lubvw==",
|
||||
"dev": true,
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/csstools"
|
||||
},
|
||||
{
|
||||
"type": "opencollective",
|
||||
"url": "https://opencollective.com/csstools"
|
||||
}
|
||||
],
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/@egjs/hammerjs": {
|
||||
"version": "2.0.17",
|
||||
"resolved": "https://registry.npmjs.org/@egjs/hammerjs/-/hammerjs-2.0.17.tgz",
|
||||
@@ -1612,63 +1473,6 @@
|
||||
"react": "^18 || ^19"
|
||||
}
|
||||
},
|
||||
"node_modules/@testing-library/dom": {
|
||||
"version": "10.4.1",
|
||||
"resolved": "https://registry.npmmirror.com/@testing-library/dom/-/dom-10.4.1.tgz",
|
||||
"integrity": "sha512-o4PXJQidqJl82ckFaXUeoAW+XysPLauYI43Abki5hABd853iMhitooc6znOnczgbTYmEP6U6/y1ZyKAIsvMKGg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@babel/code-frame": "^7.10.4",
|
||||
"@babel/runtime": "^7.12.5",
|
||||
"@types/aria-query": "^5.0.1",
|
||||
"aria-query": "5.3.0",
|
||||
"dom-accessibility-api": "^0.5.9",
|
||||
"lz-string": "^1.5.0",
|
||||
"picocolors": "1.1.1",
|
||||
"pretty-format": "^27.0.2"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/@testing-library/react": {
|
||||
"version": "16.3.3",
|
||||
"resolved": "https://registry.npmmirror.com/@testing-library/react/-/react-16.3.3.tgz",
|
||||
"integrity": "sha512-Uo193NgQbPMz6lrrhtRQQFcMC6Re/ELLFbbuVL30WDlZxlpZf9/lMHTAVxPRLw1q1iu9OJmR1c2BLiENRstdBg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@babel/runtime": "^7.12.5"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@testing-library/dom": "^10.0.0",
|
||||
"@types/react": "^18.0.0 || ^19.0.0",
|
||||
"@types/react-dom": "^18.0.0 || ^19.0.0",
|
||||
"react": "^18.0.0 || ^19.0.0",
|
||||
"react-dom": "^18.0.0 || ^19.0.0"
|
||||
},
|
||||
"peerDependenciesMeta": {
|
||||
"@types/react": {
|
||||
"optional": true
|
||||
},
|
||||
"@types/react-dom": {
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/@types/aria-query": {
|
||||
"version": "5.0.4",
|
||||
"resolved": "https://registry.npmmirror.com/@types/aria-query/-/aria-query-5.0.4.tgz",
|
||||
"integrity": "sha512-rfT93uj5s0PRL7EzccGMs3brplhcrghnDoV26NqKhCAS1hVo+WdNsPvE/yb6ilfr5hi2MEk6d5EWJTKdxg8jVw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true
|
||||
},
|
||||
"node_modules/@types/babel__core": {
|
||||
"version": "7.20.5",
|
||||
"resolved": "https://registry.npmjs.org/@types/babel__core/-/babel__core-7.20.5.tgz",
|
||||
@@ -1810,18 +1614,6 @@
|
||||
"@types/unist": "*"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/jsdom": {
|
||||
"version": "21.1.7",
|
||||
"resolved": "https://registry.npmmirror.com/@types/jsdom/-/jsdom-21.1.7.tgz",
|
||||
"integrity": "sha512-yOriVnggzrnQ3a9OKOCxaVuSug3w3/SbOj5i7VwXWZEyUNl3bLF9V3MfxGbZKuwqJOQyRfqXyROBB1CoZLFWzA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/node": "*",
|
||||
"@types/tough-cookie": "*",
|
||||
"parse5": "^7.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/json-schema": {
|
||||
"version": "7.0.15",
|
||||
"resolved": "https://registry.npmjs.org/@types/json-schema/-/json-schema-7.0.15.tgz",
|
||||
@@ -1873,13 +1665,6 @@
|
||||
"@types/react": "^19.2.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@types/tough-cookie": {
|
||||
"version": "4.0.5",
|
||||
"resolved": "https://registry.npmmirror.com/@types/tough-cookie/-/tough-cookie-4.0.5.tgz",
|
||||
"integrity": "sha512-/Ad8+nIOV7Rl++6f1BdKxFSMgmoqEoYbHRpPcx3JEfv8VRsQe9Z4mCXeJBzxs7mbHY/XOZZuXlRNfhpVPbs6ZA==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/@types/trusted-types": {
|
||||
"version": "2.0.7",
|
||||
"resolved": "https://registry.npmjs.org/@types/trusted-types/-/trusted-types-2.0.7.tgz",
|
||||
@@ -2225,16 +2010,6 @@
|
||||
"acorn": "^6.0.0 || ^7.0.0 || ^8.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/agent-base": {
|
||||
"version": "7.1.4",
|
||||
"resolved": "https://registry.npmmirror.com/agent-base/-/agent-base-7.1.4.tgz",
|
||||
"integrity": "sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 14"
|
||||
}
|
||||
},
|
||||
"node_modules/ajv": {
|
||||
"version": "6.15.0",
|
||||
"resolved": "https://registry.npmjs.org/ajv/-/ajv-6.15.0.tgz",
|
||||
@@ -2252,42 +2027,6 @@
|
||||
"url": "https://github.com/sponsors/epoberezkin"
|
||||
}
|
||||
},
|
||||
"node_modules/ansi-regex": {
|
||||
"version": "5.0.1",
|
||||
"resolved": "https://registry.npmmirror.com/ansi-regex/-/ansi-regex-5.0.1.tgz",
|
||||
"integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=8"
|
||||
}
|
||||
},
|
||||
"node_modules/ansi-styles": {
|
||||
"version": "5.2.0",
|
||||
"resolved": "https://registry.npmmirror.com/ansi-styles/-/ansi-styles-5.2.0.tgz",
|
||||
"integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=10"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/chalk/ansi-styles?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/aria-query": {
|
||||
"version": "5.3.0",
|
||||
"resolved": "https://registry.npmmirror.com/aria-query/-/aria-query-5.3.0.tgz",
|
||||
"integrity": "sha512-b0P0sZPKtyu8HkeRAfCq0IfURZK+SuwMjY1UXGBU27wpAiTwQAIlq56IbIO+ytk/JjS1fMR14ee5WBBfKi5J6A==",
|
||||
"dev": true,
|
||||
"license": "Apache-2.0",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"dequal": "^2.0.3"
|
||||
}
|
||||
},
|
||||
"node_modules/attr-accept": {
|
||||
"version": "2.2.5",
|
||||
"resolved": "https://registry.npmjs.org/attr-accept/-/attr-accept-2.2.5.tgz",
|
||||
@@ -2520,20 +2259,6 @@
|
||||
"license": "MIT",
|
||||
"peer": true
|
||||
},
|
||||
"node_modules/cssstyle": {
|
||||
"version": "4.6.0",
|
||||
"resolved": "https://registry.npmmirror.com/cssstyle/-/cssstyle-4.6.0.tgz",
|
||||
"integrity": "sha512-2z+rWdzbbSZv6/rhtvzvqeZQHrBaqgogqt85sqFNbabZOuFbCVFb8kPeEtZjiKkbrm395irpNKiYeFeLiQnFPg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@asamuzakjp/css-color": "^3.2.0",
|
||||
"rrweb-cssom": "^0.8.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/csstype": {
|
||||
"version": "3.2.3",
|
||||
"resolved": "https://registry.npmjs.org/csstype/-/csstype-3.2.3.tgz",
|
||||
@@ -2645,20 +2370,6 @@
|
||||
"node": ">=12"
|
||||
}
|
||||
},
|
||||
"node_modules/data-urls": {
|
||||
"version": "5.0.0",
|
||||
"resolved": "https://registry.npmmirror.com/data-urls/-/data-urls-5.0.0.tgz",
|
||||
"integrity": "sha512-ZYP5VBHshaDAiVZxjbRVcFJpc+4xGgT0bK3vzy1HLN8jTO975HEbuYzZJcHoQEY5K1a0z8YayJkyVETa08eNTg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"whatwg-mimetype": "^4.0.0",
|
||||
"whatwg-url": "^14.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/debug": {
|
||||
"version": "4.4.3",
|
||||
"resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz",
|
||||
@@ -2676,13 +2387,6 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/decimal.js": {
|
||||
"version": "10.6.0",
|
||||
"resolved": "https://registry.npmmirror.com/decimal.js/-/decimal.js-10.6.0.tgz",
|
||||
"integrity": "sha512-YpgQiITW3JXGntzdUmyUR1V812Hn8T1YVXhCu+wO3OpS4eU9l4YdD3qjyiKdV6mvV29zapkMeD390UVEf2lkUg==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/decode-named-character-reference": {
|
||||
"version": "1.3.0",
|
||||
"resolved": "https://registry.npmjs.org/decode-named-character-reference/-/decode-named-character-reference-1.3.0.tgz",
|
||||
@@ -2745,14 +2449,6 @@
|
||||
"@babel/runtime": "^7.9.2"
|
||||
}
|
||||
},
|
||||
"node_modules/dom-accessibility-api": {
|
||||
"version": "0.5.16",
|
||||
"resolved": "https://registry.npmmirror.com/dom-accessibility-api/-/dom-accessibility-api-0.5.16.tgz",
|
||||
"integrity": "sha512-X7BJ2yElsnOJ30pZF4uIIDfBEVgF4XEBxL9Bxhy6dnrm5hkzqmsWHGTiHqRiITNhMyFLyAiWndIJP7Z1NTteDg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true
|
||||
},
|
||||
"node_modules/dompurify": {
|
||||
"version": "3.4.13",
|
||||
"resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.4.13.tgz",
|
||||
@@ -2770,19 +2466,6 @@
|
||||
"dev": true,
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/entities": {
|
||||
"version": "6.0.1",
|
||||
"resolved": "https://registry.npmmirror.com/entities/-/entities-6.0.1.tgz",
|
||||
"integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==",
|
||||
"dev": true,
|
||||
"license": "BSD-2-Clause",
|
||||
"engines": {
|
||||
"node": ">=0.12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/fb55/entities?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/esbuild": {
|
||||
"version": "0.28.1",
|
||||
"resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.28.1.tgz",
|
||||
@@ -3375,19 +3058,6 @@
|
||||
"react-is": "^16.7.0"
|
||||
}
|
||||
},
|
||||
"node_modules/html-encoding-sniffer": {
|
||||
"version": "4.0.0",
|
||||
"resolved": "https://registry.npmmirror.com/html-encoding-sniffer/-/html-encoding-sniffer-4.0.0.tgz",
|
||||
"integrity": "sha512-Y22oTqIU4uuPgEemfz7NDJz6OeKf12Lsu+QC+s3BVpda64lTiMYCyGwg5ki4vFxkMwQdeZDl2adZoqUgdFuTgQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"whatwg-encoding": "^3.1.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/html-url-attributes": {
|
||||
"version": "3.0.1",
|
||||
"resolved": "https://registry.npmjs.org/html-url-attributes/-/html-url-attributes-3.0.1.tgz",
|
||||
@@ -3398,47 +3068,6 @@
|
||||
"url": "https://opencollective.com/unified"
|
||||
}
|
||||
},
|
||||
"node_modules/http-proxy-agent": {
|
||||
"version": "7.0.2",
|
||||
"resolved": "https://registry.npmmirror.com/http-proxy-agent/-/http-proxy-agent-7.0.2.tgz",
|
||||
"integrity": "sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"agent-base": "^7.1.0",
|
||||
"debug": "^4.3.4"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 14"
|
||||
}
|
||||
},
|
||||
"node_modules/https-proxy-agent": {
|
||||
"version": "7.0.6",
|
||||
"resolved": "https://registry.npmmirror.com/https-proxy-agent/-/https-proxy-agent-7.0.6.tgz",
|
||||
"integrity": "sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"agent-base": "^7.1.2",
|
||||
"debug": "4"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 14"
|
||||
}
|
||||
},
|
||||
"node_modules/iconv-lite": {
|
||||
"version": "0.6.3",
|
||||
"resolved": "https://registry.npmmirror.com/iconv-lite/-/iconv-lite-0.6.3.tgz",
|
||||
"integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"safer-buffer": ">= 2.1.2 < 3.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=0.10.0"
|
||||
}
|
||||
},
|
||||
"node_modules/ignore": {
|
||||
"version": "5.3.2",
|
||||
"resolved": "https://registry.npmjs.org/ignore/-/ignore-5.3.2.tgz",
|
||||
@@ -3544,13 +3173,6 @@
|
||||
"url": "https://github.com/sponsors/sindresorhus"
|
||||
}
|
||||
},
|
||||
"node_modules/is-potential-custom-element-name": {
|
||||
"version": "1.0.1",
|
||||
"resolved": "https://registry.npmmirror.com/is-potential-custom-element-name/-/is-potential-custom-element-name-1.0.1.tgz",
|
||||
"integrity": "sha512-bCYeRA2rVibKZd+s2625gGnGF/t7DSqDs4dP7CrLA1m7jKWz6pps0LpYLJN8Q64HtmPKJ1hrN3nzPNKFEKOUiQ==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/isexe": {
|
||||
"version": "2.0.0",
|
||||
"resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz",
|
||||
@@ -3564,46 +3186,6 @@
|
||||
"integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==",
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/jsdom": {
|
||||
"version": "26.1.0",
|
||||
"resolved": "https://registry.npmmirror.com/jsdom/-/jsdom-26.1.0.tgz",
|
||||
"integrity": "sha512-Cvc9WUhxSMEo4McES3P7oK3QaXldCfNWp7pl2NNeiIFlCoLr3kfq9kb1fxftiwk1FLV7CvpvDfonxtzUDeSOPg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"cssstyle": "^4.2.1",
|
||||
"data-urls": "^5.0.0",
|
||||
"decimal.js": "^10.5.0",
|
||||
"html-encoding-sniffer": "^4.0.0",
|
||||
"http-proxy-agent": "^7.0.2",
|
||||
"https-proxy-agent": "^7.0.6",
|
||||
"is-potential-custom-element-name": "^1.0.1",
|
||||
"nwsapi": "^2.2.16",
|
||||
"parse5": "^7.2.1",
|
||||
"rrweb-cssom": "^0.8.0",
|
||||
"saxes": "^6.0.0",
|
||||
"symbol-tree": "^3.2.4",
|
||||
"tough-cookie": "^5.1.1",
|
||||
"w3c-xmlserializer": "^5.0.0",
|
||||
"webidl-conversions": "^7.0.0",
|
||||
"whatwg-encoding": "^3.1.1",
|
||||
"whatwg-mimetype": "^4.0.0",
|
||||
"whatwg-url": "^14.1.1",
|
||||
"ws": "^8.18.0",
|
||||
"xml-name-validator": "^5.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"canvas": "^3.0.0"
|
||||
},
|
||||
"peerDependenciesMeta": {
|
||||
"canvas": {
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/jsesc": {
|
||||
"version": "3.1.0",
|
||||
"resolved": "https://registry.npmjs.org/jsesc/-/jsesc-3.1.0.tgz",
|
||||
@@ -3739,17 +3321,6 @@
|
||||
"react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/lz-string": {
|
||||
"version": "1.5.0",
|
||||
"resolved": "https://registry.npmmirror.com/lz-string/-/lz-string-1.5.0.tgz",
|
||||
"integrity": "sha512-h5bgJWpxJNswbU7qCrV0tIKQCaS3blPDrqKWx+QxzuzL1zGUzij9XCWLrSLsJPu5t+eWA/ycetzYAO5IOMcWAQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"bin": {
|
||||
"lz-string": "bin/bin.js"
|
||||
}
|
||||
},
|
||||
"node_modules/markdown-table": {
|
||||
"version": "3.0.4",
|
||||
"resolved": "https://registry.npmjs.org/markdown-table/-/markdown-table-3.0.4.tgz",
|
||||
@@ -4712,13 +4283,6 @@
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/nwsapi": {
|
||||
"version": "2.2.27",
|
||||
"resolved": "https://registry.npmmirror.com/nwsapi/-/nwsapi-2.2.27.tgz",
|
||||
"integrity": "sha512-gQPNF78qebCQ6tvVFBYrvJdBNOrYZm90ZlXgpIFm06p6qHDHq/XC4TnJftN6OMbxVE0UTBAoRgcsDeJBBooITw==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/object-assign": {
|
||||
"version": "4.1.1",
|
||||
"resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz",
|
||||
@@ -4818,19 +4382,6 @@
|
||||
"integrity": "sha512-CmBKiL6NNo/OqgmMn95Fk9Whlp2mtvIv+KNpQKN2F4SjvrEesubTRWGYSg+BnWZOnlCaSTU1sMpsBOzgbYhnsA==",
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/parse5": {
|
||||
"version": "7.3.0",
|
||||
"resolved": "https://registry.npmmirror.com/parse5/-/parse5-7.3.0.tgz",
|
||||
"integrity": "sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"entities": "^6.0.0"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://github.com/inikulin/parse5?sponsor=1"
|
||||
}
|
||||
},
|
||||
"node_modules/path-exists": {
|
||||
"version": "4.0.0",
|
||||
"resolved": "https://registry.npmjs.org/path-exists/-/path-exists-4.0.0.tgz",
|
||||
@@ -4954,30 +4505,6 @@
|
||||
"node": ">= 0.8.0"
|
||||
}
|
||||
},
|
||||
"node_modules/pretty-format": {
|
||||
"version": "27.5.1",
|
||||
"resolved": "https://registry.npmmirror.com/pretty-format/-/pretty-format-27.5.1.tgz",
|
||||
"integrity": "sha512-Qb1gy5OrP5+zDf2Bvnzdl3jsTf1qXVMazbvCoKhtKqVs4/YK4ozX4gKQJJVyNe+cajNPn0KoC0MC3FUmaHWEmQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"ansi-regex": "^5.0.1",
|
||||
"ansi-styles": "^5.0.0",
|
||||
"react-is": "^17.0.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": "^10.13.0 || ^12.13.0 || ^14.15.0 || >=15.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/pretty-format/node_modules/react-is": {
|
||||
"version": "17.0.2",
|
||||
"resolved": "https://registry.npmmirror.com/react-is/-/react-is-17.0.2.tgz",
|
||||
"integrity": "sha512-w2GsyukL62IJnlaff/nRegPQR94C/XXamvMWmSHRJ4y7Ts/4ocGRmTHvOs8PSE6pB3dWOrD/nueuU5sduBsQ4w==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true
|
||||
},
|
||||
"node_modules/prop-types": {
|
||||
"version": "15.8.1",
|
||||
"resolved": "https://registry.npmjs.org/prop-types/-/prop-types-15.8.1.tgz",
|
||||
@@ -5290,33 +4817,6 @@
|
||||
"fsevents": "~2.3.2"
|
||||
}
|
||||
},
|
||||
"node_modules/rrweb-cssom": {
|
||||
"version": "0.8.0",
|
||||
"resolved": "https://registry.npmmirror.com/rrweb-cssom/-/rrweb-cssom-0.8.0.tgz",
|
||||
"integrity": "sha512-guoltQEx+9aMf2gDZ0s62EcV8lsXR+0w8915TC3ITdn2YueuNjdAYh/levpU9nFaoChh9RUS5ZdQMrKfVEN9tw==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/safer-buffer": {
|
||||
"version": "2.1.2",
|
||||
"resolved": "https://registry.npmmirror.com/safer-buffer/-/safer-buffer-2.1.2.tgz",
|
||||
"integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/saxes": {
|
||||
"version": "6.0.0",
|
||||
"resolved": "https://registry.npmmirror.com/saxes/-/saxes-6.0.0.tgz",
|
||||
"integrity": "sha512-xAg7SOnEhrm5zI3puOOKyy1OMcMlIJZYNJY7xLBwSze0UjhPLnWfj2GF2EpT0jmzaJKIWKHLsaSSajf35bcYnA==",
|
||||
"dev": true,
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"xmlchars": "^2.2.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=v12.22.7"
|
||||
}
|
||||
},
|
||||
"node_modules/scheduler": {
|
||||
"version": "0.27.0",
|
||||
"resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.27.0.tgz",
|
||||
@@ -5424,13 +4924,6 @@
|
||||
"inline-style-parser": "0.2.7"
|
||||
}
|
||||
},
|
||||
"node_modules/symbol-tree": {
|
||||
"version": "3.2.4",
|
||||
"resolved": "https://registry.npmmirror.com/symbol-tree/-/symbol-tree-3.2.4.tgz",
|
||||
"integrity": "sha512-9QNk5KwDF+Bvz+PyObkmSYjI5ksVUYtjW7AU22r2NKcfLJcXp96hkDWU3+XndOsUb+AQ9QhfzfCT2O+CNWT5Tw==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/tinyglobby": {
|
||||
"version": "0.2.16",
|
||||
"resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.16.tgz",
|
||||
@@ -5448,52 +4941,6 @@
|
||||
"url": "https://github.com/sponsors/SuperchupuDev"
|
||||
}
|
||||
},
|
||||
"node_modules/tldts": {
|
||||
"version": "6.1.86",
|
||||
"resolved": "https://registry.npmmirror.com/tldts/-/tldts-6.1.86.tgz",
|
||||
"integrity": "sha512-WMi/OQ2axVTf/ykqCQgXiIct+mSQDFdH2fkwhPwgEwvJ1kSzZRiinb0zF2Xb8u4+OqPChmyI6MEu4EezNJz+FQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"tldts-core": "^6.1.86"
|
||||
},
|
||||
"bin": {
|
||||
"tldts": "bin/cli.js"
|
||||
}
|
||||
},
|
||||
"node_modules/tldts-core": {
|
||||
"version": "6.1.86",
|
||||
"resolved": "https://registry.npmmirror.com/tldts-core/-/tldts-core-6.1.86.tgz",
|
||||
"integrity": "sha512-Je6p7pkk+KMzMv2XXKmAE3McmolOQFdxkKw0R8EYNr7sELW46JqnNeTX8ybPiQgvg1ymCoF8LXs5fzFaZvJPTA==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/tough-cookie": {
|
||||
"version": "5.1.2",
|
||||
"resolved": "https://registry.npmmirror.com/tough-cookie/-/tough-cookie-5.1.2.tgz",
|
||||
"integrity": "sha512-FVDYdxtnj0G6Qm/DhNPSb8Ju59ULcup3tuJxkFb5K8Bv2pUXILbf0xZWU8PX8Ov19OXljbUyveOFwRMwkXzO+A==",
|
||||
"dev": true,
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"tldts": "^6.1.32"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=16"
|
||||
}
|
||||
},
|
||||
"node_modules/tr46": {
|
||||
"version": "5.1.1",
|
||||
"resolved": "https://registry.npmmirror.com/tr46/-/tr46-5.1.1.tgz",
|
||||
"integrity": "sha512-hdF5ZgjTqgAntKkklYw0R03MG2x/bSzTtkxmIRw/sTNV8YXsCJ1tfLAX23lhxhHJlEf3CRCOCGGWw3vI3GaSPw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"punycode": "^2.3.1"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/trim-lines": {
|
||||
"version": "3.0.1",
|
||||
"resolved": "https://registry.npmjs.org/trim-lines/-/trim-lines-3.0.1.tgz",
|
||||
@@ -5917,67 +5364,6 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/w3c-xmlserializer": {
|
||||
"version": "5.0.0",
|
||||
"resolved": "https://registry.npmmirror.com/w3c-xmlserializer/-/w3c-xmlserializer-5.0.0.tgz",
|
||||
"integrity": "sha512-o8qghlI8NZHU1lLPrpi2+Uq7abh4GGPpYANlalzWxyWteJOCsr/P+oPBA49TOLu5FTZO4d3F9MnWJfiMo4BkmA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"xml-name-validator": "^5.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/webidl-conversions": {
|
||||
"version": "7.0.0",
|
||||
"resolved": "https://registry.npmmirror.com/webidl-conversions/-/webidl-conversions-7.0.0.tgz",
|
||||
"integrity": "sha512-VwddBukDzu71offAQR975unBIGqfKZpM+8ZX6ySk8nYhVoo5CYaZyzt3YBvYtRtO+aoGlqxPg/B87NGVZ/fu6g==",
|
||||
"dev": true,
|
||||
"license": "BSD-2-Clause",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
}
|
||||
},
|
||||
"node_modules/whatwg-encoding": {
|
||||
"version": "3.1.1",
|
||||
"resolved": "https://registry.npmmirror.com/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz",
|
||||
"integrity": "sha512-6qN4hJdMwfYBtE3YBTTHhoeuUrDBPZmbQaxWAqSALV/MeEnR5z1xd8UKud2RAkFoPkmB+hli1TZSnyi84xz1vQ==",
|
||||
"deprecated": "Use @exodus/bytes instead for a more spec-conformant and faster implementation",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"iconv-lite": "0.6.3"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/whatwg-mimetype": {
|
||||
"version": "4.0.0",
|
||||
"resolved": "https://registry.npmmirror.com/whatwg-mimetype/-/whatwg-mimetype-4.0.0.tgz",
|
||||
"integrity": "sha512-QaKxh0eNIi2mE9p2vEdzfagOKHCcj1pJ56EEHGQOVxp8r9/iszLUUV7v89x9O1p/T+NlTM5W7jW6+cz4Fq1YVg==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/whatwg-url": {
|
||||
"version": "14.2.0",
|
||||
"resolved": "https://registry.npmmirror.com/whatwg-url/-/whatwg-url-14.2.0.tgz",
|
||||
"integrity": "sha512-De72GdQZzNTUBBChsXueQUnPKDkg/5A5zp7pFDuQAj5UFoENpiACU0wlCvzpAGnTkj++ihpKwKyYewn/XNUbKw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"tr46": "^5.1.0",
|
||||
"webidl-conversions": "^7.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/which": {
|
||||
"version": "2.0.2",
|
||||
"resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",
|
||||
@@ -6004,45 +5390,6 @@
|
||||
"node": ">=0.10.0"
|
||||
}
|
||||
},
|
||||
"node_modules/ws": {
|
||||
"version": "8.21.3",
|
||||
"resolved": "https://registry.npmmirror.com/ws/-/ws-8.21.3.tgz",
|
||||
"integrity": "sha512-201TZ/kPWxoPr/OKWjquZR1SWKXcvxdH+e1xrx89b3YbmzLMFCLfnaG1HFIgWzJOEWZ7MvpK++odZufgYR50Rw==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=10.0.0"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"bufferutil": "^4.0.1",
|
||||
"utf-8-validate": ">=5.0.2"
|
||||
},
|
||||
"peerDependenciesMeta": {
|
||||
"bufferutil": {
|
||||
"optional": true
|
||||
},
|
||||
"utf-8-validate": {
|
||||
"optional": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/xml-name-validator": {
|
||||
"version": "5.0.0",
|
||||
"resolved": "https://registry.npmmirror.com/xml-name-validator/-/xml-name-validator-5.0.0.tgz",
|
||||
"integrity": "sha512-EvGK8EJ3DhaHfbRlETOWAS5pO9MZITeauHKJyb8wyajUfQUenkIg2MvLDTZ4T/TgIcm3HU0TFBgWWboAZ30UHg==",
|
||||
"dev": true,
|
||||
"license": "Apache-2.0",
|
||||
"engines": {
|
||||
"node": ">=18"
|
||||
}
|
||||
},
|
||||
"node_modules/xmlchars": {
|
||||
"version": "2.2.0",
|
||||
"resolved": "https://registry.npmmirror.com/xmlchars/-/xmlchars-2.2.0.tgz",
|
||||
"integrity": "sha512-JZnDKK8B0RCDw84FNdDAIpZK+JuJw+s7Lz8nksI7SIuU3UXJJslUthsi+uWBUYOwPFwW7W7PRLRfUKpxjtjFCw==",
|
||||
"dev": true,
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/xss": {
|
||||
"version": "1.0.15",
|
||||
"resolved": "https://registry.npmjs.org/xss/-/xss-1.0.15.tgz",
|
||||
|
||||
@@ -9,8 +9,7 @@
|
||||
"lint": "eslint .",
|
||||
"preview": "vite preview",
|
||||
"test:graph-store": "node --test tests/graphStore.multi-edge.test.mjs",
|
||||
"test:graph-workspace": "node --import tsx --test tests/markdownContentViewer.test.ts tests/markdownEditorInteraction.test.tsx tests/markdownEditorState.test.ts tests/nodeMarkdownSync.test.ts tests/graphSceneState.display.test.ts tests/temporalLifecycle.test.ts tests/deterministicExplorerRendering.test.ts tests/explorerCapabilities.test.tsx tests/smallGraphLayout.test.ts tests/realtimeGraphAttributes.test.ts",
|
||||
"test:graph-workspace": "node --import tsx --test tests/markdownContentViewer.test.ts tests/graphSceneState.display.test.ts tests/temporalLifecycle.test.ts tests/deterministicExplorerRendering.test.ts tests/smallGraphLayout.test.ts tests/realtimeGraphAttributes.test.ts tests/ontologyEditorModel.test.ts",
|
||||
"test:graph-workspace": "node --import tsx --test tests/markdownContentViewer.test.ts tests/graphSceneState.display.test.ts tests/temporalLifecycle.test.ts tests/deterministicExplorerRendering.test.ts tests/smallGraphLayout.test.ts tests/realtimeGraphAttributes.test.ts",
|
||||
"test:deterministic-e2e": "node --import tsx --test tests/deterministicExplorerRendering.e2e.ts",
|
||||
"test:plugin-registry": "node --import tsx --test tests/pluginRegistry.temporal.test.mjs"
|
||||
},
|
||||
@@ -40,9 +39,7 @@
|
||||
"devDependencies": {
|
||||
"@babel/core": "^7.29.6",
|
||||
"@eslint/js": "^9.39.4",
|
||||
"@testing-library/react": "^16.3.3",
|
||||
"@types/babel__core": "^7.20.5",
|
||||
"@types/jsdom": "^21.1.7",
|
||||
"@types/node": "^24.12.0",
|
||||
"@types/react": "^19.2.14",
|
||||
"@types/react-dom": "^19.2.3",
|
||||
@@ -52,7 +49,6 @@
|
||||
"eslint-plugin-react-hooks": "^7.0.1",
|
||||
"eslint-plugin-react-refresh": "^0.5.2",
|
||||
"globals": "^17.4.0",
|
||||
"jsdom": "^26.1.0",
|
||||
"tsx": "^4.21.0",
|
||||
"typescript": "~5.9.3",
|
||||
"typescript-eslint": "^8.57.0",
|
||||
|
||||
+15
-58
@@ -17,13 +17,10 @@ import {
|
||||
type LucideIcon,
|
||||
} from 'lucide-react';
|
||||
import { ErrorBoundary } from './ErrorBoundary';
|
||||
import { ExploreWorkspaceTabs, type ExploreView } from './ExploreWorkspaceTabs';
|
||||
import { fetchAgentMemoryAvailability } from './explorerCapabilities';
|
||||
|
||||
const DecisionWorkspace = lazy(() => import('./workspaces/DecisionWorkspace/DecisionWorkspace').then((module) => ({ default: module.DecisionWorkspace })));
|
||||
const DiffMergeWorkspace = lazy(() => import('./workspaces/DiffMergeWorkspace/DiffMergeWorkspace').then((module) => ({ default: module.DiffMergeWorkspace })));
|
||||
const GraphWorkspace = lazy(() => import('./workspaces/GraphWorkspace/GraphWorkspace').then((module) => ({ default: module.GraphWorkspace })));
|
||||
const MemoryWorkspace = lazy(() => import('./workspaces/MemoryWorkspace').then((module) => ({ default: module.MemoryWorkspace })));
|
||||
const ImportExportWorkspace = lazy(() => import('./workspaces/ImportExportWorkspace/ImportExportWorkspace').then((module) => ({ default: module.ImportExportWorkspace })));
|
||||
const LineageDiagram = lazy(() => import('./workspaces/LineageWorkspace/LineageDiagram').then((module) => ({ default: module.LineageDiagram })));
|
||||
const ReasoningWorkspace = lazy(() => import('./workspaces/ReasoningWorkspace').then((module) => ({ default: module.ReasoningWorkspace })));
|
||||
@@ -36,6 +33,7 @@ const OntologySummaryTab = lazy(() => import('./workspaces/ManageWorkspace/Ontol
|
||||
const OntologyWorkspace = lazy(() => import('./workspaces/OntologyWorkspace').then((module) => ({ default: module.OntologyWorkspace })));
|
||||
|
||||
type WorkspaceId = 'welcome' | 'explore' | 'analyze' | 'decisions' | 'enrich' | 'manage' | 'ontology-hub';
|
||||
type ExploreView = 'graph' | 'vocabulary';
|
||||
type AnalyzeView = 'sparql' | 'reasoning';
|
||||
type EnrichView = 'import' | 'merge' | 'registry' | 'resolve';
|
||||
type ManageView = 'lineage' | 'kg-overview' | 'ontology';
|
||||
@@ -95,18 +93,6 @@ const navItems: NavItem[] = [
|
||||
{ id: 'ontology-hub', label: 'Ontology Hub', hint: 'Schema governance, registry, and vocabulary management', icon: GitMerge },
|
||||
];
|
||||
|
||||
function readInitialWorkspace(): WorkspaceId {
|
||||
try {
|
||||
const params = new URLSearchParams(window.location.search);
|
||||
if (params.has("ontologyTab") || params.has("ontologyEntity")) {
|
||||
return "ontology-hub";
|
||||
}
|
||||
} catch {
|
||||
// Default to the welcome screen when URL state is unavailable.
|
||||
}
|
||||
return "welcome";
|
||||
}
|
||||
|
||||
const shellStyles = `
|
||||
:root {
|
||||
--app-bg: #07111f;
|
||||
@@ -1787,43 +1773,12 @@ function WelcomeScreen({
|
||||
}
|
||||
|
||||
export default function App() {
|
||||
const [activeWorkspace, setActiveWorkspace] = useState<WorkspaceId>(readInitialWorkspace);
|
||||
const [activeWorkspace, setActiveWorkspace] = useState<WorkspaceId>('welcome');
|
||||
const [exploreView, setExploreView] = useState<ExploreView>('graph');
|
||||
const [analyzeView, setAnalyzeView] = useState<AnalyzeView>('reasoning');
|
||||
const [enrichView, setEnrichView] = useState<EnrichView>('import');
|
||||
const [manageView, setManageView] = useState<ManageView>('lineage');
|
||||
const [graphFocusRequest, setGraphFocusRequest] = useState<{ nodeId: string; token: number } | null>(null);
|
||||
const [exploreDraftDirty, setExploreDraftDirty] = useState(false);
|
||||
const [agentMemoryAvailable, setAgentMemoryAvailable] = useState(false);
|
||||
|
||||
useEffect(() => {
|
||||
let active = true;
|
||||
void fetchAgentMemoryAvailability().then((available) => {
|
||||
if (active) setAgentMemoryAvailable(available);
|
||||
});
|
||||
return () => {
|
||||
active = false;
|
||||
};
|
||||
}, []);
|
||||
|
||||
const confirmDiscardExploreDraft = () => (
|
||||
!exploreDraftDirty
|
||||
|| window.confirm("Discard the unapplied Markdown draft and leave this resource?")
|
||||
);
|
||||
|
||||
const switchExploreView = (nextView: ExploreView) => {
|
||||
if (nextView === exploreView) return;
|
||||
if (!confirmDiscardExploreDraft()) return;
|
||||
setExploreDraftDirty(false);
|
||||
setExploreView(nextView);
|
||||
};
|
||||
|
||||
const switchWorkspace = (nextWorkspace: WorkspaceId) => {
|
||||
if (nextWorkspace === activeWorkspace) return;
|
||||
if (activeWorkspace === "explore" && !confirmDiscardExploreDraft()) return;
|
||||
setExploreDraftDirty(false);
|
||||
setActiveWorkspace(nextWorkspace);
|
||||
};
|
||||
|
||||
|
||||
const renderWorkspace = () => {
|
||||
@@ -1856,15 +1811,18 @@ export default function App() {
|
||||
return (
|
||||
<WorkspaceShell
|
||||
title="Explore"
|
||||
subtitle={exploreView === 'graph' ? undefined : exploreView === 'memories' ? "Browse and edit canonical AgentMemory documents." : "Browse the graph and switch views without leaving the workspace."}
|
||||
kicker={exploreView === 'graph' ? 'Graph Studio' : exploreView === 'memories' ? 'Memory Browser' : 'Vocabulary Browser'}
|
||||
subtitle={exploreView === 'graph' ? undefined : "Browse the graph and switch views without leaving the workspace."}
|
||||
kicker={exploreView === 'graph' ? 'Graph Studio' : 'Vocabulary Browser'}
|
||||
compact
|
||||
tabs={
|
||||
<ExploreWorkspaceTabs
|
||||
activeView={exploreView}
|
||||
agentMemoryAvailable={agentMemoryAvailable}
|
||||
onSelect={switchExploreView}
|
||||
/>
|
||||
<>
|
||||
<button className="workspace-tab" data-active={exploreView === 'graph'} onClick={() => setExploreView('graph')}>
|
||||
Semantica Explorer
|
||||
</button>
|
||||
<button className="workspace-tab" data-active={exploreView === 'vocabulary'} onClick={() => setExploreView('vocabulary')}>
|
||||
Vocabulary Browser
|
||||
</button>
|
||||
</>
|
||||
}
|
||||
>
|
||||
<ErrorBoundary key={`explore-${exploreView}`}>
|
||||
@@ -1873,9 +1831,8 @@ export default function App() {
|
||||
<GraphWorkspace
|
||||
externalFocusNodeId={graphFocusRequest?.nodeId}
|
||||
externalFocusToken={graphFocusRequest?.token}
|
||||
onDirtyChange={setExploreDraftDirty}
|
||||
/>
|
||||
) : exploreView === 'memories' ? <MemoryWorkspace onDirtyChange={setExploreDraftDirty} /> : <VocabularyWorkspace />}
|
||||
) : <VocabularyWorkspace />}
|
||||
</Suspense>
|
||||
</ErrorBoundary>
|
||||
</WorkspaceShell>
|
||||
@@ -2020,13 +1977,13 @@ export default function App() {
|
||||
<style>{shellStyles}</style>
|
||||
<div className="app-shell">
|
||||
<aside className="app-rail">
|
||||
<button className="brand-pill" title="Semantica Knowledge Explorer" onClick={() => switchWorkspace('welcome')} style={{ cursor: 'pointer', border: '1px solid rgba(127,208,255,0.18)' }}>SKE</button>
|
||||
<button className="brand-pill" title="Semantica Knowledge Explorer" onClick={() => setActiveWorkspace('welcome')} style={{ cursor: 'pointer', border: '1px solid rgba(127,208,255,0.18)' }}>SKE</button>
|
||||
{navItems.map(({ id, label, hint, icon: Icon }) => (
|
||||
<button
|
||||
key={id}
|
||||
className="nav-button"
|
||||
data-active={activeWorkspace === id}
|
||||
onClick={() => switchWorkspace(id)}
|
||||
onClick={() => setActiveWorkspace(id)}
|
||||
title={hint}
|
||||
>
|
||||
<Icon size={20} />
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
export type ExploreView = 'graph' | 'memories' | 'vocabulary';
|
||||
|
||||
type ExploreWorkspaceTabsProps = {
|
||||
activeView: ExploreView;
|
||||
agentMemoryAvailable: boolean;
|
||||
onSelect: (view: ExploreView) => void;
|
||||
};
|
||||
|
||||
export function ExploreWorkspaceTabs({
|
||||
activeView,
|
||||
agentMemoryAvailable,
|
||||
onSelect,
|
||||
}: ExploreWorkspaceTabsProps) {
|
||||
return (
|
||||
<>
|
||||
<button className="workspace-tab" data-active={activeView === 'graph'} onClick={() => onSelect('graph')}>
|
||||
Semantica Explorer
|
||||
</button>
|
||||
{agentMemoryAvailable ? (
|
||||
<button className="workspace-tab" data-active={activeView === 'memories'} onClick={() => onSelect('memories')}>
|
||||
Memories
|
||||
</button>
|
||||
) : null}
|
||||
<button className="workspace-tab" data-active={activeView === 'vocabulary'} onClick={() => onSelect('vocabulary')}>
|
||||
Vocabulary Browser
|
||||
</button>
|
||||
</>
|
||||
);
|
||||
}
|
||||
@@ -1,24 +0,0 @@
|
||||
type Fetcher = (
|
||||
input: RequestInfo | URL,
|
||||
init?: RequestInit,
|
||||
) => Promise<Response>;
|
||||
|
||||
type ExplorerInfo = {
|
||||
capabilities?: {
|
||||
agent_memory?: boolean;
|
||||
};
|
||||
};
|
||||
|
||||
export async function fetchAgentMemoryAvailability(
|
||||
fetcher: Fetcher = fetch,
|
||||
): Promise<boolean> {
|
||||
try {
|
||||
const response = await fetcher('/api/info');
|
||||
if (!response.ok) return false;
|
||||
|
||||
const info = await response.json() as ExplorerInfo;
|
||||
return info.capabilities?.agent_memory === true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -15,7 +15,6 @@ export type RegistryEntryOp =
|
||||
| "export"
|
||||
| "merge"
|
||||
| "add-node"
|
||||
| "update-node"
|
||||
| "add-edge"
|
||||
| "delete"
|
||||
| "infer"
|
||||
|
||||
@@ -16,7 +16,6 @@ const OP_META: Record<
|
||||
export: { label: "EXPORT", color: "#8fa8c6", bg: "rgba(143,168,198,0.08)", border: "rgba(143,168,198,0.18)" },
|
||||
merge: { label: "MERGE", color: "#f2b66d", bg: "rgba(242,182,109,0.12)", border: "rgba(242,182,109,0.28)" },
|
||||
"add-node": { label: "ADD NODE", color: "#4cc38a", bg: "rgba(76,195,138,0.12)", border: "rgba(76,195,138,0.28)" },
|
||||
"update-node": { label: "UPDATE NODE", color: "#79c0ff", bg: "rgba(121,192,255,0.10)", border: "rgba(121,192,255,0.24)" },
|
||||
"add-edge": { label: "ADD EDGE", color: "#4cc38a", bg: "rgba(76,195,138,0.10)", border: "rgba(76,195,138,0.22)" },
|
||||
delete: { label: "DELETE", color: "#ff7b72", bg: "rgba(255,123,114,0.12)", border: "rgba(255,123,114,0.28)" },
|
||||
infer: { label: "INFER", color: "#d2a8ff", bg: "rgba(210,168,255,0.12)", border: "rgba(210,168,255,0.28)" },
|
||||
@@ -24,7 +23,7 @@ const OP_META: Record<
|
||||
};
|
||||
|
||||
const ALL_OPS: (RegistryEntryOp | "all")[] = [
|
||||
"all", "import", "export", "merge", "add-node", "update-node", "add-edge", "infer", "delete", "vocab-import",
|
||||
"all", "import", "export", "merge", "add-node", "add-edge", "infer", "delete", "vocab-import",
|
||||
];
|
||||
|
||||
function formatTimestamp(date: Date): string {
|
||||
|
||||
@@ -4,7 +4,6 @@ import { graph } from "../../store/graphStore";
|
||||
import { GRAPH_THEME, withAlpha } from "./graphTheme";
|
||||
import type { GraphSelectedNodeKind } from "./types";
|
||||
import { MarkdownContentViewer } from "./MarkdownContentViewer";
|
||||
import type { MarkdownApplyResult } from "./markdownResourceClient";
|
||||
|
||||
export type LinkPrediction = {
|
||||
target: string;
|
||||
@@ -45,8 +44,6 @@ export interface GraphInspectorPanelProps {
|
||||
pathResult: PathResponse | null;
|
||||
onDownloadProvenance: (format: "json" | "markdown") => void;
|
||||
onFocusNode?: (nodeId: string) => void;
|
||||
onMarkdownApplied?: (result: MarkdownApplyResult) => void;
|
||||
onMarkdownDirtyChange?: (dirty: boolean) => void;
|
||||
}
|
||||
|
||||
const PROVENANCE_KEYS = ["source", "source_url", "pmid", "pmids", "evidence", "provenance", "confidence"] as const;
|
||||
@@ -307,8 +304,6 @@ export function GraphInspectorPanel({
|
||||
pathResult,
|
||||
onDownloadProvenance,
|
||||
onFocusNode,
|
||||
onMarkdownApplied,
|
||||
onMarkdownDirtyChange,
|
||||
}: GraphInspectorPanelProps) {
|
||||
if (!nodeId) {
|
||||
return (
|
||||
@@ -419,18 +414,19 @@ export function GraphInspectorPanel({
|
||||
</div>
|
||||
) : null}
|
||||
|
||||
{/* Canonical nodes remain editable even when their current body is empty. */}
|
||||
<details className="node-panel-collapse" open>
|
||||
<summary className="node-panel-summary">Content</summary>
|
||||
<div className="node-panel-body" style={{ marginTop: 8 }}>
|
||||
<MarkdownContentViewer
|
||||
content={nodeContent}
|
||||
resource={{ kind: "context-node", id: effectiveNodeId }}
|
||||
onApplied={onMarkdownApplied}
|
||||
onDirtyChange={onMarkdownDirtyChange}
|
||||
/>
|
||||
</div>
|
||||
</details>
|
||||
{/* Content Section — only rendered when the node carries actual content.
|
||||
This matches the existing inspector convention: sections that have no
|
||||
data for the current node are either hidden (temporal bounds) or closed
|
||||
by default (Source Attribution, Properties). Always showing an open
|
||||
empty panel would add noise for every relationship/predicate node. */}
|
||||
{nodeContent && (
|
||||
<details className="node-panel-collapse" open>
|
||||
<summary className="node-panel-summary">Content</summary>
|
||||
<div className="node-panel-body" style={{ marginTop: 8 }}>
|
||||
<MarkdownContentViewer content={nodeContent} />
|
||||
</div>
|
||||
</details>
|
||||
)}
|
||||
|
||||
{/* Actions */}
|
||||
<section style={sectionStyle}>
|
||||
|
||||
@@ -44,12 +44,6 @@ import { createTemporalSnapshotGuards, type TemporalSnapshotResponse } from "./t
|
||||
import { SMALL_GRAPH_MAX_NODES } from "./smallGraphLayout";
|
||||
import { buildRealtimeEdgeAttributes } from "./realtimeGraphAttributes";
|
||||
import type { LinkPrediction, PathResponse } from "./GraphInspectorPanel";
|
||||
import type { MarkdownApplyResult } from "./markdownResourceClient";
|
||||
import {
|
||||
NodeMarkdownRefreshGuard,
|
||||
buildNodeMarkdownAttributeUpdate,
|
||||
readNodeMarkdownAttributeUpdate,
|
||||
} from "./nodeMarkdownSync";
|
||||
import type { GraphSceneHandle, GraphSceneRuntime } from "./scene";
|
||||
import type {
|
||||
GraphAnalyticsSnapshot,
|
||||
@@ -1247,10 +1241,9 @@ function collectPluginOverlays(
|
||||
interface GraphWorkspaceProps {
|
||||
externalFocusNodeId?: string;
|
||||
externalFocusToken?: number;
|
||||
onDirtyChange?: (dirty: boolean) => void;
|
||||
}
|
||||
|
||||
export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirtyChange }: GraphWorkspaceProps = {}) {
|
||||
export function GraphWorkspace({ externalFocusNodeId, externalFocusToken }: GraphWorkspaceProps = {}) {
|
||||
const [selectedNodeId, setSelectedNodeId] = useState("");
|
||||
const [focusedNodeId, setFocusedNodeId] = useState("");
|
||||
const [lastGroupedSelectedNodeId, setLastGroupedSelectedNodeId] = useState("");
|
||||
@@ -1258,12 +1251,6 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
const [isLayoutRunning, setIsLayoutRunning] = useState(false);
|
||||
const [graphReady, setGraphReady] = useState(false);
|
||||
const [graphVersion, setGraphVersion] = useState(0);
|
||||
const [markdownDraftDirty, setMarkdownDraftDirty] = useState(false);
|
||||
const markdownRefreshGuard = useMemo(() => new NodeMarkdownRefreshGuard(), []);
|
||||
const handleMarkdownDirtyChange = useCallback((dirty: boolean) => {
|
||||
setMarkdownDraftDirty(dirty);
|
||||
onDirtyChange?.(dirty);
|
||||
}, [onDirtyChange]);
|
||||
const [viewMode, setViewMode] = useState<GraphViewMode>("full");
|
||||
const [aggregationEnabled] = useState(true);
|
||||
const [collapsedNeighborhoodNodeIds, setCollapsedNeighborhoodNodeIds] = useState<string[]>([]);
|
||||
@@ -1641,17 +1628,8 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
: null,
|
||||
[viewMode, aggregationEnabled, collapsedNeighborhoodNodeIds, graphVersion],
|
||||
);
|
||||
const confirmDiscardMarkdownDraft = useCallback(() => {
|
||||
if (!markdownDraftDirty) return true;
|
||||
const discard = window.confirm(
|
||||
"Discard the unapplied Markdown draft and leave this node?",
|
||||
);
|
||||
return discard;
|
||||
}, [markdownDraftDirty]);
|
||||
|
||||
|
||||
const requestViewMode = useCallback((nextViewMode: GraphViewMode) => {
|
||||
if (nextViewMode !== viewMode && !confirmDiscardMarkdownDraft()) return;
|
||||
if (nextViewMode === "focused") {
|
||||
const resolution = resolveNodeIdForFocusedMode(selectedNodeId, pluginRuntimeRef.current?.displayGraph);
|
||||
if (!resolution.resolvedNodeId) {
|
||||
@@ -1704,7 +1682,6 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
));
|
||||
setViewMode("full");
|
||||
}, [
|
||||
confirmDiscardMarkdownDraft,
|
||||
aggregationEnabled,
|
||||
collapsedNeighborhoodNodeIds,
|
||||
focusedNodeId,
|
||||
@@ -1715,11 +1692,9 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
lastGroupedSelectedNodeId,
|
||||
resolveNodeIdForFocusedMode,
|
||||
selectedNodeId,
|
||||
viewMode,
|
||||
]);
|
||||
|
||||
const focusNode = useCallback((nodeId: string) => {
|
||||
if (nodeId !== selectedNodeId && !confirmDiscardMarkdownDraft()) return;
|
||||
if (!nodeId) {
|
||||
setSelectedNodeId("");
|
||||
setSelectedEdgeId("");
|
||||
@@ -1745,18 +1720,14 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
setFocusedNodeId(nextSelectedNodeId);
|
||||
setIsLayoutRunning(false);
|
||||
}
|
||||
}, [confirmDiscardMarkdownDraft, selectedNodeId, viewMode]); // Note: ego/heatmap/distanceMode effects re-run automatically when selectedNodeId changes
|
||||
}, [viewMode]); // Note: ego/heatmap/distanceMode effects re-run automatically when selectedNodeId changes
|
||||
|
||||
useEffect(() => {
|
||||
if (!externalFocusNodeId || externalFocusToken == null) return;
|
||||
if (lastExternalFocusTokenRef.current === externalFocusToken) return;
|
||||
if (!graphReady || !graph.hasNode(externalFocusNodeId)) return;
|
||||
if (
|
||||
externalFocusNodeId !== selectedNodeId
|
||||
&& !confirmDiscardMarkdownDraft()
|
||||
) return;
|
||||
lastExternalFocusTokenRef.current = externalFocusToken;
|
||||
|
||||
lastExternalFocusTokenRef.current = externalFocusToken;
|
||||
// Set state directly instead of going through focusNode(), which captures
|
||||
// a stale viewMode in its closure. setViewMode is called first so the node
|
||||
// is visible in the full graph before the scene pans to it.
|
||||
@@ -1766,13 +1737,7 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
window.setTimeout(() => {
|
||||
sceneRef.current?.focusNode(externalFocusNodeId);
|
||||
}, 0);
|
||||
}, [
|
||||
confirmDiscardMarkdownDraft,
|
||||
externalFocusNodeId,
|
||||
externalFocusToken,
|
||||
graphReady,
|
||||
selectedNodeId,
|
||||
]);
|
||||
}, [externalFocusNodeId, externalFocusToken, graphReady]);
|
||||
|
||||
const handleEdgeSelect = useCallback((edgeId: string) => {
|
||||
setSelectedEdgeId(edgeId);
|
||||
@@ -1878,37 +1843,6 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
document.body.removeChild(anchor);
|
||||
}, [inspectableNodeId]);
|
||||
|
||||
const handleMarkdownApplied = useCallback((result: MarkdownApplyResult) => {
|
||||
if (result.resource.kind !== "context-node") return;
|
||||
if (!graph.hasNode(result.resource.id)) return;
|
||||
const syncGeneration = markdownRefreshGuard.begin(result.resource.id);
|
||||
const attributes = graph.getNodeAttributes(result.resource.id) as NodeAttributes;
|
||||
graph.mergeNodeAttributes(
|
||||
result.resource.id,
|
||||
buildNodeMarkdownAttributeUpdate(
|
||||
result.resource.id,
|
||||
result.body,
|
||||
attributes.properties ?? {},
|
||||
),
|
||||
);
|
||||
setGraphVersion((current) => current + 1);
|
||||
sceneRef.current?.getRuntime()?.requestRender();
|
||||
|
||||
void readNodeMarkdownAttributeUpdate(result.resource.id)
|
||||
.then((savedAttributes) => {
|
||||
if (
|
||||
!markdownRefreshGuard.isCurrent(result.resource.id, syncGeneration)
|
||||
|| !graph.hasNode(result.resource.id)
|
||||
) return;
|
||||
graph.mergeNodeAttributes(result.resource.id, savedAttributes);
|
||||
setGraphVersion((current) => current + 1);
|
||||
sceneRef.current?.getRuntime()?.requestRender();
|
||||
})
|
||||
.catch((syncError) => {
|
||||
console.error("[GraphWorkspace] applied node refresh failed", syncError);
|
||||
});
|
||||
}, [markdownRefreshGuard]);
|
||||
|
||||
useEffect(() => {
|
||||
const protocol = window.location.protocol === "https:" ? "wss:" : "ws:";
|
||||
const socket = new WebSocket(`${protocol}//${window.location.host}/ws/graph-updates`);
|
||||
@@ -1939,25 +1873,6 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
setGraphVersion((current) => current + 1);
|
||||
sceneRef.current?.getRuntime()?.requestRender();
|
||||
}
|
||||
if (eventType === "UPDATE_NODE" && payload?.id && graph.hasNode(payload.id)) {
|
||||
markdownRefreshGuard.invalidate(payload.id);
|
||||
const properties = payload.properties ?? {};
|
||||
const current = graph.getNodeAttributes(payload.id) as NodeAttributes;
|
||||
const content = typeof properties.content === "string" ? properties.content : "";
|
||||
graph.mergeNodeAttributes(payload.id, {
|
||||
...buildNodeMarkdownAttributeUpdate(payload.id, content, properties),
|
||||
nodeType: payload.type ?? current.nodeType,
|
||||
valid_from: properties.valid_from ?? null,
|
||||
valid_until: properties.valid_until ?? null,
|
||||
});
|
||||
logEvent(
|
||||
"update-node",
|
||||
`Updated node ${payload.id} via realtime ws`,
|
||||
{ nodeId: payload.id, nodeType: payload.type },
|
||||
);
|
||||
setGraphVersion((version) => version + 1);
|
||||
sceneRef.current?.getRuntime()?.requestRender();
|
||||
}
|
||||
if (eventType === "ADD_EDGE") {
|
||||
const isSmallGraph = smallGraphModeRef.current;
|
||||
batchMergeEdges([
|
||||
@@ -1984,7 +1899,7 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
return () => {
|
||||
socket.close();
|
||||
};
|
||||
}, [markdownRefreshGuard]);
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
setCollapsedNeighborhoodNodeIds([]);
|
||||
@@ -2257,29 +2172,28 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
}, [collapsedNeighborhoodNodeIds, focusedNodeId, selectedNodeId, viewMode]);
|
||||
const structuralActivePath = structuralSelectedNodeId ? activePath : EMPTY_PATH;
|
||||
const structuralActivePathEdgeIds = structuralSelectedNodeId ? activePathEdgeIds : EMPTY_PATH;
|
||||
const displayResult = useMemo(() => {
|
||||
// The displayed graph is an aggregated clone. Rebuild it after domain
|
||||
// mutations so applied Markdown labels do not remain stale on the canvas.
|
||||
void graphVersion;
|
||||
return viewMode === "grouped"
|
||||
? (groupedDisplayCandidate ?? resolveDisplayGraph("", EMPTY_PATH, EMPTY_PATH, "grouped", {
|
||||
aggregationEnabled,
|
||||
collapsedNeighborhoodNodeIds,
|
||||
}))
|
||||
: resolveDisplayGraph(structuralSelectedNodeId, structuralActivePath, structuralActivePathEdgeIds, viewMode, {
|
||||
aggregationEnabled,
|
||||
collapsedNeighborhoodNodeIds,
|
||||
});
|
||||
}, [
|
||||
aggregationEnabled,
|
||||
collapsedNeighborhoodNodeIds,
|
||||
graphVersion,
|
||||
groupedDisplayCandidate,
|
||||
structuralActivePath,
|
||||
structuralActivePathEdgeIds,
|
||||
structuralSelectedNodeId,
|
||||
viewMode,
|
||||
]);
|
||||
const displayResult = useMemo(
|
||||
() => (
|
||||
viewMode === "grouped"
|
||||
? (groupedDisplayCandidate ?? resolveDisplayGraph("", EMPTY_PATH, EMPTY_PATH, "grouped", {
|
||||
aggregationEnabled,
|
||||
collapsedNeighborhoodNodeIds,
|
||||
}))
|
||||
: resolveDisplayGraph(structuralSelectedNodeId, structuralActivePath, structuralActivePathEdgeIds, viewMode, {
|
||||
aggregationEnabled,
|
||||
collapsedNeighborhoodNodeIds,
|
||||
})
|
||||
),
|
||||
[
|
||||
aggregationEnabled,
|
||||
collapsedNeighborhoodNodeIds,
|
||||
groupedDisplayCandidate,
|
||||
structuralActivePath,
|
||||
structuralActivePathEdgeIds,
|
||||
structuralSelectedNodeId,
|
||||
viewMode,
|
||||
],
|
||||
);
|
||||
const displayState = useMemo(
|
||||
() => (
|
||||
viewMode === "grouped"
|
||||
@@ -3381,8 +3295,6 @@ export function GraphWorkspace({ externalFocusNodeId, externalFocusToken, onDirt
|
||||
pathResult={pathResult}
|
||||
onDownloadProvenance={(format) => void handleDownloadProvenance(format)}
|
||||
onFocusNode={focusNode}
|
||||
onMarkdownApplied={handleMarkdownApplied}
|
||||
onMarkdownDirtyChange={handleMarkdownDirtyChange}
|
||||
/>
|
||||
</Suspense>
|
||||
</div>
|
||||
|
||||
@@ -1,243 +1,125 @@
|
||||
import {
|
||||
useEffect,
|
||||
useMemo,
|
||||
useRef,
|
||||
useState,
|
||||
type CSSProperties,
|
||||
} from "react";
|
||||
import { useState, useRef, useEffect, useMemo, type CSSProperties } from "react";
|
||||
import ReactMarkdown, { type Components } from "react-markdown";
|
||||
import remarkGfm from "remark-gfm";
|
||||
import {
|
||||
Check,
|
||||
Code2,
|
||||
Copy,
|
||||
Eye,
|
||||
ExternalLink,
|
||||
Image as ImageIcon,
|
||||
Loader2,
|
||||
Pencil,
|
||||
RefreshCw,
|
||||
X,
|
||||
} from "lucide-react";
|
||||
import { Check, Copy, Code2, Eye, ExternalLink, Image as ImageIcon } from "lucide-react";
|
||||
import { GRAPH_THEME } from "./graphTheme";
|
||||
import type { MarkdownApplyResult } from "./markdownResourceClient";
|
||||
import type { MarkdownResourceRef } from "./markdownEditorState";
|
||||
import { isSafeUrl } from "./markdownUrlSafety";
|
||||
import { useMarkdownEditor } from "./useMarkdownEditor";
|
||||
|
||||
export interface MarkdownContentViewerProps {
|
||||
content?: string | null;
|
||||
resource?: MarkdownResourceRef;
|
||||
onApplied?: (result: MarkdownApplyResult) => void;
|
||||
onDirtyChange?: (dirty: boolean) => void;
|
||||
className?: string;
|
||||
defaultMode?: "preview" | "source";
|
||||
}
|
||||
|
||||
export function MarkdownContentViewer({
|
||||
content,
|
||||
resource,
|
||||
onApplied,
|
||||
onDirtyChange,
|
||||
className,
|
||||
defaultMode = "preview",
|
||||
}: MarkdownContentViewerProps) {
|
||||
const [activeMode, setActiveMode] = useState<"preview" | "source">(defaultMode);
|
||||
const [copied, setCopied] = useState(false);
|
||||
const modeBeforeEditRef = useRef<"preview" | "source">(defaultMode);
|
||||
const resourceKey = resource ? `${resource.kind}:${resource.id}` : "";
|
||||
const [activeResourceKey, setActiveResourceKey] = useState(resourceKey);
|
||||
const editor = useMarkdownEditor({ resource, onApplied, onDirtyChange });
|
||||
const {
|
||||
session,
|
||||
error,
|
||||
dirty,
|
||||
editing,
|
||||
saving,
|
||||
loading,
|
||||
} = editor;
|
||||
|
||||
if (activeResourceKey !== resourceKey) {
|
||||
setActiveResourceKey(resourceKey);
|
||||
setCopied(false);
|
||||
setActiveMode(defaultMode);
|
||||
}
|
||||
|
||||
// Track the content value for which the copied indicator is valid.
|
||||
// When content changes (i.e. the user selects a different node), reset the
|
||||
// copied indicator inline during render rather than in a useEffect — this
|
||||
// avoids a cascading-render lint error and is the React-recommended pattern
|
||||
// for resetting derived visual state on prop changes.
|
||||
const [copiedForContent, setCopiedForContent] = useState<string | null | undefined>(content);
|
||||
if (copiedForContent !== content) {
|
||||
setCopiedForContent(content);
|
||||
if (copied) setCopied(false);
|
||||
if (copied) {
|
||||
// Clear the stale indicator synchronously so the new node's copy button
|
||||
// never shows "Copied" from the previous selection.
|
||||
setCopied(false);
|
||||
}
|
||||
}
|
||||
|
||||
const copyTimeoutRef = useRef<number | undefined>(undefined);
|
||||
const copyTimeoutRef = useRef<ReturnType<typeof setTimeout> | null>(null);
|
||||
|
||||
// Clean up any outstanding timeout on unmount.
|
||||
useEffect(() => {
|
||||
return () => {
|
||||
clearTimeout(copyTimeoutRef.current);
|
||||
if (copyTimeoutRef.current) {
|
||||
clearTimeout(copyTimeoutRef.current);
|
||||
}
|
||||
};
|
||||
}, []);
|
||||
|
||||
const rawContent = editor.editing
|
||||
? editor.session?.draft ?? ""
|
||||
: (typeof content === "string" ? content : "");
|
||||
const previewContent = useMemo(() => {
|
||||
if (!editor.editing) return rawContent;
|
||||
const lines = rawContent.split(/\r?\n/);
|
||||
if (lines[0] !== "---") return rawContent;
|
||||
const closingIndex = lines.findIndex((line, index) => index > 0 && line === "---");
|
||||
return closingIndex < 0 ? rawContent : lines.slice(closingIndex + 1).join("\n").replace(/^\n/, "");
|
||||
}, [editor.editing, rawContent]);
|
||||
const rawContent = typeof content === "string" ? content : "";
|
||||
const hasContent = rawContent.trim().length > 0;
|
||||
|
||||
// react-markdown runs the whole remark pipeline synchronously inside its own
|
||||
// render, so without this memo every unrelated re-render of this component --
|
||||
// clicking Copy, toggling Preview/Source -- re-parses the entire document.
|
||||
// Measured at ~364ms per re-render for a 1000-row GFM table (issue #1118).
|
||||
// Keyed on rawContent so a genuine node change still re-parses exactly once.
|
||||
const renderedMarkdown = useMemo(
|
||||
() => (
|
||||
<ReactMarkdown remarkPlugins={REMARK_PLUGINS} components={MARKDOWN_COMPONENTS}>
|
||||
{previewContent}
|
||||
{rawContent}
|
||||
</ReactMarkdown>
|
||||
),
|
||||
[previewContent],
|
||||
[rawContent],
|
||||
);
|
||||
|
||||
const handleCopy = async () => {
|
||||
if (!hasContent) return;
|
||||
try {
|
||||
await navigator.clipboard.writeText(rawContent);
|
||||
clearTimeout(copyTimeoutRef.current);
|
||||
if (copyTimeoutRef.current) {
|
||||
clearTimeout(copyTimeoutRef.current);
|
||||
}
|
||||
setCopied(true);
|
||||
copyTimeoutRef.current = window.setTimeout(() => setCopied(false), 1500);
|
||||
copyTimeoutRef.current = setTimeout(() => setCopied(false), 1500);
|
||||
} catch {
|
||||
// Clipboard write unavailable.
|
||||
}
|
||||
};
|
||||
|
||||
const handleEdit = async () => {
|
||||
modeBeforeEditRef.current = activeMode;
|
||||
setActiveMode("source");
|
||||
if (!await editor.beginEdit()) {
|
||||
setActiveMode(modeBeforeEditRef.current);
|
||||
}
|
||||
};
|
||||
|
||||
const handleCancel = () => {
|
||||
editor.discard();
|
||||
setActiveMode(modeBeforeEditRef.current);
|
||||
};
|
||||
|
||||
const handleApply = async () => {
|
||||
if (await editor.save()) {
|
||||
setActiveMode("preview");
|
||||
// Clipboard write unavailable
|
||||
}
|
||||
};
|
||||
|
||||
return (
|
||||
<div className={className} style={viewerContainerStyle}>
|
||||
<div style={viewerHeaderStyle}>
|
||||
<div style={{ display: "flex", gap: 4 }} role="tablist" aria-label="Markdown view">
|
||||
<div style={{ display: "flex", gap: 4 }} role="tablist">
|
||||
<button
|
||||
type="button"
|
||||
role="tab"
|
||||
aria-selected={activeMode === "preview"}
|
||||
aria-controls="markdown-viewer-panel"
|
||||
onClick={() => setActiveMode("preview")}
|
||||
style={{ ...tabBtnStyle, ...(activeMode === "preview" ? activeTabBtnStyle : {}) }}
|
||||
>
|
||||
<Eye size={12} style={{ marginRight: 5 }} aria-hidden="true" />
|
||||
<Eye size={12} style={{ marginRight: 5 }} />
|
||||
Preview
|
||||
</button>
|
||||
<button
|
||||
type="button"
|
||||
role="tab"
|
||||
aria-selected={activeMode === "source"}
|
||||
aria-controls="markdown-viewer-panel"
|
||||
onClick={() => setActiveMode("source")}
|
||||
style={{ ...tabBtnStyle, ...(activeMode === "source" ? activeTabBtnStyle : {}) }}
|
||||
>
|
||||
<Code2 size={12} style={{ marginRight: 5 }} aria-hidden="true" />
|
||||
<Code2 size={12} style={{ marginRight: 5 }} />
|
||||
Source
|
||||
</button>
|
||||
</div>
|
||||
|
||||
<div style={{ display: "flex", alignItems: "center", gap: 6 }}>
|
||||
{hasContent && (
|
||||
<button type="button" onClick={() => void handleCopy()} style={copyBtnStyle} title="Copy raw content">
|
||||
{copied ? (
|
||||
<>
|
||||
<Check size={12} color="#3fb950" style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
<span style={{ color: "#3fb950", fontSize: 11 }}>Copied</span>
|
||||
</>
|
||||
) : (
|
||||
<>
|
||||
<Copy size={12} style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
<span style={{ fontSize: 11 }}>Copy</span>
|
||||
</>
|
||||
)}
|
||||
</button>
|
||||
)}
|
||||
{resource && !editing && !loading ? (
|
||||
<button type="button" onClick={() => void handleEdit()} style={copyBtnStyle}>
|
||||
<Pencil size={12} style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
Edit
|
||||
</button>
|
||||
) : null}
|
||||
{loading ? (
|
||||
<button type="button" disabled style={{ ...copyBtnStyle, opacity: 0.65 }}>
|
||||
<Loader2 size={12} className="animate-spin" style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
Loading…
|
||||
</button>
|
||||
) : null}
|
||||
{editing ? (
|
||||
<>
|
||||
<button type="button" onClick={handleCancel} disabled={saving} style={copyBtnStyle}>
|
||||
<X size={12} style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
Cancel
|
||||
</button>
|
||||
<button
|
||||
type="button"
|
||||
onClick={() => void handleApply()}
|
||||
disabled={saving || !dirty}
|
||||
title={!dirty ? "Make a change before applying" : undefined}
|
||||
style={{ ...saveBtnStyle, opacity: saving || !dirty ? 0.55 : 1 }}
|
||||
>
|
||||
{saving ? (
|
||||
<Loader2 size={12} className="animate-spin" style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
) : (
|
||||
<Check size={12} style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
)}
|
||||
{saving ? "Applying…" : "Apply"}
|
||||
</button>
|
||||
</>
|
||||
) : null}
|
||||
</div>
|
||||
{hasContent && (
|
||||
<button type="button" onClick={() => void handleCopy()} style={copyBtnStyle} title="Copy raw content">
|
||||
{copied ? (
|
||||
<>
|
||||
<Check size={12} color="#3fb950" style={{ marginRight: 4 }} />
|
||||
<span style={{ color: "#3fb950", fontSize: 11 }}>Copied</span>
|
||||
</>
|
||||
) : (
|
||||
<>
|
||||
<Copy size={12} style={{ marginRight: 4 }} />
|
||||
<span style={{ fontSize: 11 }}>Copy</span>
|
||||
</>
|
||||
)}
|
||||
</button>
|
||||
)}
|
||||
</div>
|
||||
|
||||
{error ? (
|
||||
<div id="markdown-editor-error" role="alert" style={errorStyle}>
|
||||
<span>{error.message}</span>
|
||||
{error.kind === "conflict" ? (
|
||||
<button type="button" onClick={() => void editor.reloadLatest()} style={errorActionStyle}>
|
||||
<RefreshCw size={12} style={{ marginRight: 4 }} aria-hidden="true" />
|
||||
Reload latest
|
||||
</button>
|
||||
) : null}
|
||||
</div>
|
||||
) : null}
|
||||
|
||||
<div
|
||||
id="markdown-viewer-panel"
|
||||
role="tabpanel"
|
||||
aria-busy={saving || loading}
|
||||
style={viewerBodyStyle}
|
||||
>
|
||||
{activeMode === "source" && editing ? (
|
||||
<textarea
|
||||
aria-label="Markdown source"
|
||||
aria-describedby={error ? "markdown-editor-error" : undefined}
|
||||
aria-invalid={error?.kind === "validation" || undefined}
|
||||
value={session?.draft ?? ""}
|
||||
onChange={(event) => editor.changeDraft(event.target.value)}
|
||||
disabled={saving}
|
||||
spellCheck={false}
|
||||
style={editorStyle}
|
||||
/>
|
||||
) : !hasContent ? (
|
||||
<div style={viewerBodyStyle}>
|
||||
{!hasContent ? (
|
||||
<div style={emptyTextStyle}>No content available for this node.</div>
|
||||
) : activeMode === "source" ? (
|
||||
<pre style={sourcePreStyle}>
|
||||
@@ -356,8 +238,6 @@ const viewerHeaderStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
alignItems: "center",
|
||||
justifyContent: "space-between",
|
||||
gap: 8,
|
||||
flexWrap: "wrap",
|
||||
padding: "6px 10px",
|
||||
background: "rgba(0, 0, 0, 0.2)",
|
||||
borderBottom: `1px solid ${GRAPH_THEME.ui.surface.panelBorder}`,
|
||||
@@ -395,56 +275,12 @@ const copyBtnStyle: CSSProperties = {
|
||||
cursor: "pointer",
|
||||
};
|
||||
|
||||
const saveBtnStyle: CSSProperties = {
|
||||
...copyBtnStyle,
|
||||
background: GRAPH_THEME.ui.control.primaryBg,
|
||||
border: `1px solid ${GRAPH_THEME.ui.control.primaryBorder}`,
|
||||
color: GRAPH_THEME.ui.control.primaryText,
|
||||
fontWeight: 700,
|
||||
};
|
||||
|
||||
const errorStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
alignItems: "center",
|
||||
justifyContent: "space-between",
|
||||
gap: 8,
|
||||
padding: "8px 12px",
|
||||
color: "#ffb4ad",
|
||||
background: "rgba(248, 81, 73, 0.1)",
|
||||
borderBottom: "1px solid rgba(248, 81, 73, 0.25)",
|
||||
fontSize: 12,
|
||||
lineHeight: 1.5,
|
||||
};
|
||||
|
||||
const errorActionStyle: CSSProperties = {
|
||||
...copyBtnStyle,
|
||||
flexShrink: 0,
|
||||
color: "#ffb4ad",
|
||||
border: "1px solid rgba(248, 81, 73, 0.32)",
|
||||
};
|
||||
|
||||
const viewerBodyStyle: CSSProperties = {
|
||||
padding: 12,
|
||||
maxHeight: 380,
|
||||
overflowY: "auto",
|
||||
};
|
||||
|
||||
const editorStyle: CSSProperties = {
|
||||
display: "block",
|
||||
boxSizing: "border-box",
|
||||
width: "100%",
|
||||
minHeight: 280,
|
||||
resize: "vertical",
|
||||
padding: 10,
|
||||
borderRadius: 8,
|
||||
border: `1px solid ${GRAPH_THEME.ui.control.activeBorder}`,
|
||||
background: "rgba(0, 0, 0, 0.3)",
|
||||
color: GRAPH_THEME.ui.text.strong,
|
||||
fontFamily: "'JetBrains Mono', 'Fira Code', monospace",
|
||||
fontSize: 12,
|
||||
lineHeight: 1.6,
|
||||
};
|
||||
|
||||
const emptyTextStyle: CSSProperties = {
|
||||
color: GRAPH_THEME.ui.text.muted,
|
||||
fontSize: 12,
|
||||
|
||||
@@ -1,114 +0,0 @@
|
||||
export type MarkdownResourceRef =
|
||||
| { kind: "context-node"; id: string }
|
||||
| { kind: "agent-memory"; id: string };
|
||||
|
||||
export type EditorStatus =
|
||||
| "viewing"
|
||||
| "loading-document"
|
||||
| "editing"
|
||||
| "saving"
|
||||
| "validation-error"
|
||||
| "save-error"
|
||||
| "conflict";
|
||||
|
||||
export interface MarkdownEditorError {
|
||||
kind: "validation" | "conflict" | "save" | "network";
|
||||
message: string;
|
||||
field?: string;
|
||||
currentRevision?: string;
|
||||
}
|
||||
|
||||
export interface MarkdownEditSession {
|
||||
resource: MarkdownResourceRef;
|
||||
baseSource: string;
|
||||
baseRevision: string;
|
||||
draft: string;
|
||||
status: EditorStatus;
|
||||
error: MarkdownEditorError | null;
|
||||
}
|
||||
|
||||
export interface MarkdownSavedDocument {
|
||||
source: string;
|
||||
revision: string;
|
||||
}
|
||||
|
||||
export function createLoadingSession(resource: MarkdownResourceRef): MarkdownEditSession {
|
||||
return {
|
||||
resource,
|
||||
baseSource: "",
|
||||
baseRevision: "",
|
||||
draft: "",
|
||||
status: "loading-document",
|
||||
error: null,
|
||||
};
|
||||
}
|
||||
|
||||
export function createEditSession(
|
||||
resource: MarkdownResourceRef,
|
||||
document: MarkdownSavedDocument,
|
||||
): MarkdownEditSession {
|
||||
return {
|
||||
resource,
|
||||
baseSource: document.source,
|
||||
baseRevision: document.revision,
|
||||
draft: document.source,
|
||||
status: "editing",
|
||||
error: null,
|
||||
};
|
||||
}
|
||||
|
||||
export function updateDraft(
|
||||
session: MarkdownEditSession,
|
||||
draft: string,
|
||||
): MarkdownEditSession {
|
||||
return {
|
||||
...session,
|
||||
draft,
|
||||
status: "editing",
|
||||
error: null,
|
||||
};
|
||||
}
|
||||
|
||||
export function isDirty(session: MarkdownEditSession | null): boolean {
|
||||
return session !== null && session.draft !== session.baseSource;
|
||||
}
|
||||
|
||||
export function saveStarted(session: MarkdownEditSession): MarkdownEditSession {
|
||||
if (!isDirty(session)) return session;
|
||||
return { ...session, status: "saving", error: null };
|
||||
}
|
||||
|
||||
export function saveSucceeded(
|
||||
session: MarkdownEditSession,
|
||||
document: MarkdownSavedDocument,
|
||||
): MarkdownEditSession {
|
||||
return {
|
||||
...session,
|
||||
baseSource: document.source,
|
||||
baseRevision: document.revision,
|
||||
draft: document.source,
|
||||
status: "viewing",
|
||||
error: null,
|
||||
};
|
||||
}
|
||||
|
||||
export function saveFailed(
|
||||
session: MarkdownEditSession,
|
||||
error: MarkdownEditorError,
|
||||
): MarkdownEditSession {
|
||||
const status: EditorStatus =
|
||||
error.kind === "validation"
|
||||
? "validation-error"
|
||||
: error.kind === "conflict"
|
||||
? "conflict"
|
||||
: "save-error";
|
||||
return { ...session, status, error };
|
||||
}
|
||||
|
||||
export function cancelEdit(): null {
|
||||
return null;
|
||||
}
|
||||
|
||||
export function shouldConfirmDiscard(session: MarkdownEditSession | null): boolean {
|
||||
return isDirty(session) && session?.status !== "saving";
|
||||
}
|
||||
@@ -1,103 +0,0 @@
|
||||
import type {
|
||||
MarkdownEditorError,
|
||||
MarkdownResourceRef,
|
||||
} from "./markdownEditorState";
|
||||
|
||||
export interface MarkdownDocument {
|
||||
resource: MarkdownResourceRef;
|
||||
source: string;
|
||||
body: string;
|
||||
revision: string;
|
||||
editable: boolean;
|
||||
}
|
||||
|
||||
export interface MarkdownApplyResult extends MarkdownDocument {
|
||||
changed: boolean;
|
||||
}
|
||||
|
||||
type ErrorDetail = {
|
||||
code?: string;
|
||||
message?: string;
|
||||
field?: string;
|
||||
current_revision?: string;
|
||||
};
|
||||
|
||||
export class MarkdownClientError extends Error implements MarkdownEditorError {
|
||||
readonly kind: MarkdownEditorError["kind"];
|
||||
readonly field?: string;
|
||||
readonly currentRevision?: string;
|
||||
|
||||
constructor(error: MarkdownEditorError) {
|
||||
super(error.message);
|
||||
this.name = "MarkdownClientError";
|
||||
this.kind = error.kind;
|
||||
this.field = error.field;
|
||||
this.currentRevision = error.currentRevision;
|
||||
}
|
||||
}
|
||||
|
||||
function resourceUrl(ref: MarkdownResourceRef): string {
|
||||
return `/api/markdown/${ref.kind}/${encodeURIComponent(ref.id)}`;
|
||||
}
|
||||
|
||||
async function responseError(response: Response): Promise<MarkdownClientError> {
|
||||
let detail: ErrorDetail = {};
|
||||
try {
|
||||
const payload = (await response.json()) as { detail?: ErrorDetail };
|
||||
if (payload.detail && typeof payload.detail === "object") {
|
||||
detail = payload.detail;
|
||||
}
|
||||
} catch {
|
||||
// A non-JSON response is mapped from its status below.
|
||||
}
|
||||
|
||||
const kind: MarkdownEditorError["kind"] =
|
||||
response.status === 422
|
||||
? "validation"
|
||||
: response.status === 409
|
||||
? "conflict"
|
||||
: "save";
|
||||
return new MarkdownClientError({
|
||||
kind,
|
||||
message: detail.message || `Markdown request failed (${response.status}).`,
|
||||
field: detail.field,
|
||||
currentRevision: detail.current_revision,
|
||||
});
|
||||
}
|
||||
|
||||
async function request<T>(input: RequestInfo | URL, init?: RequestInit): Promise<T> {
|
||||
try {
|
||||
const response = await fetch(input, init);
|
||||
if (!response.ok) {
|
||||
throw await responseError(response);
|
||||
}
|
||||
return (await response.json()) as T;
|
||||
} catch (error) {
|
||||
if (error instanceof MarkdownClientError) throw error;
|
||||
throw new MarkdownClientError({
|
||||
kind: "network",
|
||||
message: "The Markdown service could not be reached. Your draft was kept.",
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
export function readMarkdownResource(
|
||||
ref: MarkdownResourceRef,
|
||||
): Promise<MarkdownDocument> {
|
||||
return request<MarkdownDocument>(resourceUrl(ref));
|
||||
}
|
||||
|
||||
export function applyMarkdownResource(
|
||||
ref: MarkdownResourceRef,
|
||||
markdown: string,
|
||||
expectedRevision: string,
|
||||
): Promise<MarkdownApplyResult> {
|
||||
return request<MarkdownApplyResult>(resourceUrl(ref), {
|
||||
method: "PUT",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({
|
||||
markdown,
|
||||
expected_revision: expectedRevision,
|
||||
}),
|
||||
});
|
||||
}
|
||||
@@ -1,81 +0,0 @@
|
||||
export interface NodeMarkdownAttributeUpdate {
|
||||
label: string;
|
||||
content: string;
|
||||
properties: Record<string, unknown>;
|
||||
}
|
||||
|
||||
export interface GraphNodeMarkdownSnapshot {
|
||||
id: string;
|
||||
type: string;
|
||||
content: string;
|
||||
properties: Record<string, unknown>;
|
||||
valid_from: string | null;
|
||||
valid_until: string | null;
|
||||
}
|
||||
|
||||
export interface SavedNodeMarkdownAttributeUpdate extends NodeMarkdownAttributeUpdate {
|
||||
nodeType: string;
|
||||
valid_from: string | null;
|
||||
valid_until: string | null;
|
||||
}
|
||||
|
||||
export class NodeMarkdownRefreshGuard {
|
||||
private readonly generations = new Map<string, number>();
|
||||
|
||||
begin(nodeId: string): number {
|
||||
const generation = (this.generations.get(nodeId) ?? 0) + 1;
|
||||
this.generations.set(nodeId, generation);
|
||||
return generation;
|
||||
}
|
||||
|
||||
invalidate(nodeId: string): void {
|
||||
this.begin(nodeId);
|
||||
}
|
||||
|
||||
isCurrent(nodeId: string, generation: number): boolean {
|
||||
return this.generations.get(nodeId) === generation;
|
||||
}
|
||||
}
|
||||
|
||||
export function buildNodeMarkdownAttributeUpdate(
|
||||
nodeId: string,
|
||||
content: string,
|
||||
properties: Record<string, unknown>,
|
||||
): NodeMarkdownAttributeUpdate {
|
||||
return {
|
||||
label: content || nodeId,
|
||||
content,
|
||||
properties: {
|
||||
...properties,
|
||||
content,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
export async function readNodeMarkdownAttributeUpdate(
|
||||
nodeId: string,
|
||||
fetcher: typeof fetch = fetch,
|
||||
): Promise<SavedNodeMarkdownAttributeUpdate> {
|
||||
const response = await fetcher(
|
||||
`/api/graph/node?node_id=${encodeURIComponent(nodeId)}`,
|
||||
);
|
||||
if (!response.ok) {
|
||||
throw new Error(`Graph node refresh failed (${response.status}).`);
|
||||
}
|
||||
|
||||
const node = await response.json() as GraphNodeMarkdownSnapshot;
|
||||
if (node.id !== nodeId) {
|
||||
throw new Error("Graph node refresh returned a different resource.");
|
||||
}
|
||||
|
||||
return {
|
||||
...buildNodeMarkdownAttributeUpdate(
|
||||
node.id,
|
||||
node.content,
|
||||
node.properties ?? {},
|
||||
),
|
||||
nodeType: node.type,
|
||||
valid_from: node.valid_from ?? null,
|
||||
valid_until: node.valid_until ?? null,
|
||||
};
|
||||
}
|
||||
@@ -1,177 +0,0 @@
|
||||
import {
|
||||
useCallback,
|
||||
useEffect,
|
||||
useLayoutEffect,
|
||||
useRef,
|
||||
useState,
|
||||
} from "react";
|
||||
import {
|
||||
MarkdownClientError,
|
||||
applyMarkdownResource,
|
||||
readMarkdownResource,
|
||||
type MarkdownApplyResult,
|
||||
} from "./markdownResourceClient";
|
||||
import {
|
||||
cancelEdit,
|
||||
createEditSession,
|
||||
createLoadingSession,
|
||||
isDirty,
|
||||
saveFailed,
|
||||
saveStarted,
|
||||
saveSucceeded,
|
||||
updateDraft,
|
||||
type MarkdownEditorError,
|
||||
type MarkdownEditSession,
|
||||
type MarkdownResourceRef,
|
||||
} from "./markdownEditorState";
|
||||
|
||||
interface MarkdownEditorOptions {
|
||||
resource?: MarkdownResourceRef;
|
||||
onApplied?: (result: MarkdownApplyResult) => void;
|
||||
onDirtyChange?: (dirty: boolean) => void;
|
||||
}
|
||||
|
||||
interface KeyedError {
|
||||
resourceKey: string;
|
||||
error: MarkdownEditorError;
|
||||
}
|
||||
|
||||
function keyOf(resource?: MarkdownResourceRef): string {
|
||||
return resource ? `${resource.kind}:${resource.id}` : "";
|
||||
}
|
||||
|
||||
function normalizeError(failure: unknown): MarkdownEditorError {
|
||||
if (failure instanceof MarkdownClientError) return failure;
|
||||
return {
|
||||
kind: "network",
|
||||
message: "The Markdown service could not be reached. Your draft was kept.",
|
||||
};
|
||||
}
|
||||
|
||||
export function useMarkdownEditor({
|
||||
resource,
|
||||
onApplied,
|
||||
onDirtyChange,
|
||||
}: MarkdownEditorOptions) {
|
||||
const resourceKey = keyOf(resource);
|
||||
const [session, setSession] = useState<MarkdownEditSession | null>(null);
|
||||
const [viewError, setViewError] = useState<KeyedError | null>(null);
|
||||
const [renderedResourceKey, setRenderedResourceKey] = useState(resourceKey);
|
||||
const loadGenerationRef = useRef(0);
|
||||
|
||||
if (renderedResourceKey !== resourceKey) {
|
||||
setRenderedResourceKey(resourceKey);
|
||||
setSession(null);
|
||||
setViewError(null);
|
||||
}
|
||||
|
||||
useLayoutEffect(() => {
|
||||
loadGenerationRef.current += 1;
|
||||
}, [resourceKey]);
|
||||
|
||||
const activeSession = session && keyOf(session.resource) === resourceKey
|
||||
? session
|
||||
: null;
|
||||
const dirty = isDirty(activeSession);
|
||||
const editing = activeSession !== null
|
||||
&& activeSession.status !== "viewing"
|
||||
&& activeSession.status !== "loading-document";
|
||||
const saving = activeSession?.status === "saving";
|
||||
const loading = activeSession?.status === "loading-document";
|
||||
const error = activeSession?.error
|
||||
?? (viewError?.resourceKey === resourceKey ? viewError.error : null);
|
||||
|
||||
useEffect(() => {
|
||||
onDirtyChange?.(dirty);
|
||||
return () => {
|
||||
if (dirty) onDirtyChange?.(false);
|
||||
};
|
||||
}, [dirty, onDirtyChange]);
|
||||
|
||||
useEffect(() => {
|
||||
if (!dirty) return;
|
||||
const protectDraft = (event: BeforeUnloadEvent) => {
|
||||
event.preventDefault();
|
||||
event.returnValue = "";
|
||||
};
|
||||
window.addEventListener("beforeunload", protectDraft);
|
||||
return () => window.removeEventListener("beforeunload", protectDraft);
|
||||
}, [dirty]);
|
||||
|
||||
const beginEdit = useCallback(async () => {
|
||||
if (!resource) return false;
|
||||
const loadGeneration = ++loadGenerationRef.current;
|
||||
setViewError(null);
|
||||
setSession(createLoadingSession(resource));
|
||||
try {
|
||||
const document = await readMarkdownResource(resource);
|
||||
if (loadGeneration !== loadGenerationRef.current) return false;
|
||||
setSession(createEditSession(resource, document));
|
||||
return true;
|
||||
} catch (failure) {
|
||||
if (loadGeneration !== loadGenerationRef.current) return false;
|
||||
setSession(null);
|
||||
setViewError({ resourceKey, error: normalizeError(failure) });
|
||||
return false;
|
||||
}
|
||||
}, [resource, resourceKey]);
|
||||
|
||||
const discard = useCallback(() => {
|
||||
if (!activeSession || saving) return;
|
||||
setSession(cancelEdit());
|
||||
setViewError(null);
|
||||
}, [activeSession, saving]);
|
||||
|
||||
const save = useCallback(async () => {
|
||||
if (!activeSession || saving || !dirty) return false;
|
||||
const resourceGeneration = loadGenerationRef.current;
|
||||
const pending = saveStarted(activeSession);
|
||||
setSession(pending);
|
||||
try {
|
||||
const result = await applyMarkdownResource(
|
||||
pending.resource,
|
||||
pending.draft,
|
||||
pending.baseRevision,
|
||||
);
|
||||
if (resourceGeneration !== loadGenerationRef.current) return false;
|
||||
setSession(saveSucceeded(pending, result));
|
||||
onApplied?.(result);
|
||||
return true;
|
||||
} catch (failure) {
|
||||
if (resourceGeneration !== loadGenerationRef.current) return false;
|
||||
setSession(saveFailed(pending, normalizeError(failure)));
|
||||
return false;
|
||||
}
|
||||
}, [activeSession, dirty, onApplied, saving]);
|
||||
|
||||
const reloadLatest = useCallback(async () => {
|
||||
if (!resource || saving) return;
|
||||
if (
|
||||
dirty
|
||||
&& !window.confirm("Discard this draft and reload the latest applied version?")
|
||||
) return;
|
||||
await beginEdit();
|
||||
}, [beginEdit, dirty, resource, saving]);
|
||||
|
||||
const changeDraft = useCallback((draft: string) => {
|
||||
setSession((current) => (
|
||||
current && keyOf(current.resource) === resourceKey
|
||||
? updateDraft(current, draft)
|
||||
: current
|
||||
));
|
||||
}, [resourceKey]);
|
||||
|
||||
return {
|
||||
session: activeSession,
|
||||
error,
|
||||
dirty,
|
||||
editing,
|
||||
saving,
|
||||
loading,
|
||||
beginEdit,
|
||||
discard,
|
||||
save,
|
||||
reloadLatest,
|
||||
changeDraft,
|
||||
};
|
||||
}
|
||||
@@ -1,464 +0,0 @@
|
||||
import { useCallback, useEffect, useRef, useState, type CSSProperties } from "react";
|
||||
import { Brain, RefreshCw } from "lucide-react";
|
||||
|
||||
import { MarkdownContentViewer } from "./GraphWorkspace/MarkdownContentViewer";
|
||||
import {
|
||||
readMarkdownResource,
|
||||
type MarkdownApplyResult,
|
||||
} from "./GraphWorkspace/markdownResourceClient";
|
||||
import { GRAPH_THEME } from "./GraphWorkspace/graphTheme";
|
||||
|
||||
interface MemorySummary {
|
||||
id: string;
|
||||
type: string;
|
||||
excerpt: string;
|
||||
updated_at: string | null;
|
||||
}
|
||||
|
||||
interface MemoryListResponse {
|
||||
items: MemorySummary[];
|
||||
total: number;
|
||||
skip: number;
|
||||
limit: number;
|
||||
}
|
||||
interface MemoryWorkspaceProps {
|
||||
onDirtyChange?: (dirty: boolean) => void;
|
||||
}
|
||||
|
||||
const MEMORY_PAGE_SIZE = 100;
|
||||
|
||||
|
||||
function responseMessage(payload: unknown, fallback: string): string {
|
||||
if (!payload || typeof payload !== "object" || !("detail" in payload)) {
|
||||
return fallback;
|
||||
}
|
||||
return typeof payload.detail === "string" ? payload.detail : fallback;
|
||||
}
|
||||
|
||||
|
||||
async function fetchMemoryList(skip = 0): Promise<MemoryListResponse> {
|
||||
const response = await fetch(`/api/memories?skip=${skip}&limit=${MEMORY_PAGE_SIZE}`);
|
||||
if (!response.ok) {
|
||||
const payload = await response.json().catch(() => null);
|
||||
throw new Error(responseMessage(payload, `Memory list failed (${response.status}).`));
|
||||
}
|
||||
return response.json() as Promise<MemoryListResponse>;
|
||||
}
|
||||
|
||||
async function fetchLoadedMemoryPages(endOffset: number): Promise<{
|
||||
items: MemorySummary[];
|
||||
total: number;
|
||||
nextOffset: number;
|
||||
}> {
|
||||
const items: MemorySummary[] = [];
|
||||
let total = 0;
|
||||
let nextOffset = 0;
|
||||
const targetOffset = Math.max(endOffset, MEMORY_PAGE_SIZE);
|
||||
|
||||
while (nextOffset < targetOffset) {
|
||||
const payload = await fetchMemoryList(nextOffset);
|
||||
items.push(...payload.items);
|
||||
total = payload.total;
|
||||
nextOffset = payload.skip + payload.items.length;
|
||||
if (payload.items.length === 0 || nextOffset >= total) break;
|
||||
}
|
||||
|
||||
return { items, total, nextOffset };
|
||||
}
|
||||
|
||||
export function MemoryWorkspace({ onDirtyChange }: MemoryWorkspaceProps = {}) {
|
||||
const [items, setItems] = useState<MemorySummary[]>([]);
|
||||
const [total, setTotal] = useState(0);
|
||||
const [nextOffset, setNextOffset] = useState(0);
|
||||
const [selectedId, setSelectedId] = useState("");
|
||||
const [selectedBody, setSelectedBody] = useState("");
|
||||
const [loading, setLoading] = useState(true);
|
||||
const [loadingMore, setLoadingMore] = useState(false);
|
||||
const [error, setError] = useState("");
|
||||
const [dirty, setDirty] = useState(false);
|
||||
const [reloadToken, setReloadToken] = useState(0);
|
||||
const listGenerationRef = useRef(0);
|
||||
const selectionGenerationRef = useRef(0);
|
||||
const handleDirtyChange = useCallback((nextDirty: boolean) => {
|
||||
setDirty(nextDirty);
|
||||
onDirtyChange?.(nextDirty);
|
||||
}, [onDirtyChange]);
|
||||
|
||||
|
||||
useEffect(() => {
|
||||
let cancelled = false;
|
||||
const listGeneration = ++listGenerationRef.current;
|
||||
const selectionGeneration = ++selectionGenerationRef.current;
|
||||
const isCurrent = () => (
|
||||
!cancelled
|
||||
&& listGeneration === listGenerationRef.current
|
||||
&& selectionGeneration === selectionGenerationRef.current
|
||||
);
|
||||
const load = async () => {
|
||||
setLoading(true);
|
||||
setLoadingMore(false);
|
||||
setError("");
|
||||
try {
|
||||
const payload = await fetchMemoryList();
|
||||
if (!isCurrent()) return;
|
||||
setItems(payload.items);
|
||||
setTotal(payload.total);
|
||||
setNextOffset(payload.skip + payload.items.length);
|
||||
const first = payload.items[0];
|
||||
if (!first) {
|
||||
setSelectedId("");
|
||||
setSelectedBody("");
|
||||
return;
|
||||
}
|
||||
const document = await readMarkdownResource({
|
||||
kind: "agent-memory",
|
||||
id: first.id,
|
||||
});
|
||||
if (!isCurrent()) return;
|
||||
setSelectedId(first.id);
|
||||
setSelectedBody(document.body);
|
||||
} catch (failure) {
|
||||
if (isCurrent()) {
|
||||
setError(failure instanceof Error ? failure.message : "Memories could not be loaded.");
|
||||
}
|
||||
} finally {
|
||||
if (isCurrent()) setLoading(false);
|
||||
}
|
||||
};
|
||||
void load();
|
||||
return () => {
|
||||
cancelled = true;
|
||||
listGenerationRef.current += 1;
|
||||
selectionGenerationRef.current += 1;
|
||||
};
|
||||
}, [reloadToken]);
|
||||
|
||||
const selectMemory = async (memoryId: string) => {
|
||||
if (memoryId === selectedId) return;
|
||||
if (dirty && !window.confirm("Discard the unapplied Markdown draft and open another memory?")) return;
|
||||
const selectionGeneration = ++selectionGenerationRef.current;
|
||||
// Do NOT call handleDirtyChange(false) here: the editor's own onDirtyChange
|
||||
// callback fires automatically when MarkdownContentViewer re-renders with
|
||||
// the new resource prop and its session is cleared.
|
||||
setLoading(true);
|
||||
setError("");
|
||||
try {
|
||||
const document = await readMarkdownResource({
|
||||
kind: "agent-memory",
|
||||
id: memoryId,
|
||||
});
|
||||
if (selectionGeneration !== selectionGenerationRef.current) return;
|
||||
setSelectedId(memoryId);
|
||||
setSelectedBody(document.body);
|
||||
} catch (failure) {
|
||||
if (selectionGeneration === selectionGenerationRef.current) {
|
||||
setError(failure instanceof Error ? failure.message : "The memory could not be loaded.");
|
||||
}
|
||||
} finally {
|
||||
if (selectionGeneration === selectionGenerationRef.current) {
|
||||
setLoading(false);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const loadMoreMemories = useCallback(async () => {
|
||||
if (loadingMore || nextOffset >= total) return;
|
||||
const listGeneration = ++listGenerationRef.current;
|
||||
setLoadingMore(true);
|
||||
setError("");
|
||||
try {
|
||||
const payload = await fetchMemoryList(nextOffset);
|
||||
if (listGeneration !== listGenerationRef.current) return;
|
||||
setItems((current) => {
|
||||
const knownIds = new Set(current.map((item) => item.id));
|
||||
return [
|
||||
...current,
|
||||
...payload.items.filter((item) => !knownIds.has(item.id)),
|
||||
];
|
||||
});
|
||||
setTotal(payload.total);
|
||||
setNextOffset(payload.skip + payload.items.length);
|
||||
} catch (failure) {
|
||||
if (listGeneration === listGenerationRef.current) {
|
||||
setError(failure instanceof Error ? failure.message : "More memories could not be loaded.");
|
||||
}
|
||||
} finally {
|
||||
if (listGeneration === listGenerationRef.current) {
|
||||
setLoadingMore(false);
|
||||
}
|
||||
}
|
||||
}, [loadingMore, nextOffset, total]);
|
||||
|
||||
const refreshMemorySummaries = useCallback(async () => {
|
||||
const listGeneration = ++listGenerationRef.current;
|
||||
try {
|
||||
const payload = await fetchLoadedMemoryPages(nextOffset);
|
||||
if (listGeneration !== listGenerationRef.current) return;
|
||||
setItems(payload.items);
|
||||
setTotal(payload.total);
|
||||
setNextOffset(payload.nextOffset);
|
||||
} catch {
|
||||
if (listGeneration === listGenerationRef.current) {
|
||||
setError("Memory was applied, but its summary could not be refreshed.");
|
||||
}
|
||||
} finally {
|
||||
if (listGeneration === listGenerationRef.current) {
|
||||
setLoadingMore(false);
|
||||
}
|
||||
}
|
||||
}, [nextOffset]);
|
||||
|
||||
const applyMemory = useCallback((result: MarkdownApplyResult) => {
|
||||
setSelectedBody(result.body);
|
||||
handleDirtyChange(false);
|
||||
setItems((current) => current.map((item) => (
|
||||
item.id === result.resource.id
|
||||
? { ...item, excerpt: result.body.replace(/\s+/g, " ").slice(0, 160) }
|
||||
: item
|
||||
)));
|
||||
void refreshMemorySummaries();
|
||||
}, [handleDirtyChange, refreshMemorySummaries]);
|
||||
|
||||
return (
|
||||
<div style={workspaceStyle}>
|
||||
<aside style={listPanelStyle} aria-label="Agent memories">
|
||||
<div style={listHeaderStyle}>
|
||||
<div>
|
||||
<div style={listTitleStyle}>AgentMemory</div>
|
||||
<div style={listCountStyle}>{items.length} of {total} loaded</div>
|
||||
</div>
|
||||
<button
|
||||
type="button"
|
||||
aria-label="Refresh memories"
|
||||
onClick={() => setReloadToken((value) => value + 1)}
|
||||
disabled={loading || loadingMore || dirty}
|
||||
title={dirty ? "Apply or cancel the current draft before refreshing" : "Refresh memories"}
|
||||
style={{ ...iconButtonStyle, opacity: loading || loadingMore || dirty ? 0.55 : 1 }}
|
||||
>
|
||||
<RefreshCw size={14} aria-hidden="true" />
|
||||
</button>
|
||||
</div>
|
||||
<div style={memoryListStyle}>
|
||||
{items.map((item) => (
|
||||
<button
|
||||
type="button"
|
||||
key={item.id}
|
||||
onClick={() => void selectMemory(item.id)}
|
||||
aria-current={item.id === selectedId ? "true" : undefined}
|
||||
style={{
|
||||
...memoryButtonStyle,
|
||||
...(item.id === selectedId ? selectedMemoryButtonStyle : {}),
|
||||
}}
|
||||
>
|
||||
<span style={memoryTypeStyle}>{item.type}</span>
|
||||
<span style={memoryIdStyle}>{item.id}</span>
|
||||
<span style={memoryExcerptStyle}>{item.excerpt || "Empty memory"}</span>
|
||||
</button>
|
||||
))}
|
||||
{nextOffset < total ? (
|
||||
<button
|
||||
type="button"
|
||||
aria-label="Load more memories"
|
||||
onClick={() => void loadMoreMemories()}
|
||||
disabled={loading || loadingMore}
|
||||
style={{ ...retryButtonStyle, opacity: loading || loadingMore ? 0.55 : 1 }}
|
||||
>
|
||||
{loadingMore ? "Loading…" : "Load more"}
|
||||
</button>
|
||||
) : null}
|
||||
{!loading && items.length === 0 ? (
|
||||
<div style={emptyStyle}>
|
||||
<Brain size={22} aria-hidden="true" />
|
||||
<span>No AgentMemory items are available.</span>
|
||||
<button type="button" onClick={() => setReloadToken((value) => value + 1)} style={retryButtonStyle}>
|
||||
Refresh
|
||||
</button>
|
||||
</div>
|
||||
) : null}
|
||||
</div>
|
||||
</aside>
|
||||
|
||||
<main style={editorPanelStyle}>
|
||||
{error ? <div role="alert" style={alertStyle}>{error}</div> : null}
|
||||
{loading ? (
|
||||
<div role="status" style={emptyStyle}>Loading memories…</div>
|
||||
) : selectedId ? (
|
||||
<>
|
||||
<div style={selectionHeaderStyle}>
|
||||
<span style={selectionLabelStyle}>Selected memory</span>
|
||||
<strong style={selectionIdStyle}>{selectedId}</strong>
|
||||
</div>
|
||||
<MarkdownContentViewer
|
||||
content={selectedBody}
|
||||
resource={{ kind: "agent-memory", id: selectedId }}
|
||||
onApplied={applyMemory}
|
||||
onDirtyChange={handleDirtyChange}
|
||||
/>
|
||||
</>
|
||||
) : null}
|
||||
</main>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
const workspaceStyle: CSSProperties = {
|
||||
display: "grid",
|
||||
gridTemplateColumns: "minmax(220px, 300px) minmax(0, 1fr)",
|
||||
height: "100%",
|
||||
minHeight: 0,
|
||||
background: GRAPH_THEME.ui.surface.stage,
|
||||
};
|
||||
|
||||
const listPanelStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
flexDirection: "column",
|
||||
minHeight: 0,
|
||||
borderRight: `1px solid ${GRAPH_THEME.ui.surface.panelBorder}`,
|
||||
background: GRAPH_THEME.ui.surface.panel,
|
||||
};
|
||||
|
||||
const listHeaderStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
alignItems: "center",
|
||||
justifyContent: "space-between",
|
||||
gap: 12,
|
||||
padding: 16,
|
||||
borderBottom: `1px solid ${GRAPH_THEME.ui.surface.panelBorder}`,
|
||||
};
|
||||
|
||||
const listTitleStyle: CSSProperties = {
|
||||
color: GRAPH_THEME.ui.text.strong,
|
||||
fontSize: 14,
|
||||
fontWeight: 700,
|
||||
};
|
||||
|
||||
const listCountStyle: CSSProperties = {
|
||||
color: GRAPH_THEME.ui.text.muted,
|
||||
fontSize: 11,
|
||||
marginTop: 3,
|
||||
};
|
||||
|
||||
const iconButtonStyle: CSSProperties = {
|
||||
display: "inline-grid",
|
||||
placeItems: "center",
|
||||
width: 30,
|
||||
height: 30,
|
||||
borderRadius: 8,
|
||||
border: `1px solid ${GRAPH_THEME.ui.surface.panelBorder}`,
|
||||
background: "rgba(255, 255, 255, 0.04)",
|
||||
color: GRAPH_THEME.ui.text.body,
|
||||
cursor: "pointer",
|
||||
};
|
||||
|
||||
const memoryListStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
flexDirection: "column",
|
||||
gap: 6,
|
||||
minHeight: 0,
|
||||
padding: 10,
|
||||
overflowY: "auto",
|
||||
};
|
||||
|
||||
const memoryButtonStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
flexDirection: "column",
|
||||
alignItems: "flex-start",
|
||||
gap: 5,
|
||||
padding: 10,
|
||||
borderRadius: 9,
|
||||
border: "1px solid transparent",
|
||||
background: "transparent",
|
||||
color: GRAPH_THEME.ui.text.body,
|
||||
textAlign: "left",
|
||||
cursor: "pointer",
|
||||
};
|
||||
|
||||
const selectedMemoryButtonStyle: CSSProperties = {
|
||||
border: `1px solid ${GRAPH_THEME.ui.control.activeBorder}`,
|
||||
background: GRAPH_THEME.ui.timeline.playheadSoft,
|
||||
};
|
||||
|
||||
const memoryTypeStyle: CSSProperties = {
|
||||
color: GRAPH_THEME.ui.timeline.playhead,
|
||||
fontSize: 10,
|
||||
fontWeight: 700,
|
||||
textTransform: "uppercase",
|
||||
};
|
||||
|
||||
const memoryIdStyle: CSSProperties = {
|
||||
maxWidth: "100%",
|
||||
overflow: "hidden",
|
||||
color: GRAPH_THEME.ui.text.strong,
|
||||
fontFamily: "monospace",
|
||||
fontSize: 12,
|
||||
textOverflow: "ellipsis",
|
||||
whiteSpace: "nowrap",
|
||||
};
|
||||
|
||||
const memoryExcerptStyle: CSSProperties = {
|
||||
display: "-webkit-box",
|
||||
overflow: "hidden",
|
||||
color: GRAPH_THEME.ui.text.muted,
|
||||
fontSize: 11,
|
||||
lineHeight: 1.45,
|
||||
WebkitBoxOrient: "vertical",
|
||||
WebkitLineClamp: 2,
|
||||
};
|
||||
|
||||
const editorPanelStyle: CSSProperties = {
|
||||
minWidth: 0,
|
||||
minHeight: 0,
|
||||
padding: 20,
|
||||
overflowY: "auto",
|
||||
};
|
||||
|
||||
const selectionHeaderStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
flexDirection: "column",
|
||||
gap: 4,
|
||||
marginBottom: 12,
|
||||
};
|
||||
|
||||
const selectionLabelStyle: CSSProperties = {
|
||||
color: GRAPH_THEME.ui.text.muted,
|
||||
fontSize: 11,
|
||||
};
|
||||
|
||||
const selectionIdStyle: CSSProperties = {
|
||||
color: GRAPH_THEME.ui.text.strong,
|
||||
fontFamily: "monospace",
|
||||
fontSize: 14,
|
||||
wordBreak: "break-all",
|
||||
};
|
||||
|
||||
const emptyStyle: CSSProperties = {
|
||||
display: "flex",
|
||||
flexDirection: "column",
|
||||
alignItems: "center",
|
||||
justifyContent: "center",
|
||||
gap: 10,
|
||||
minHeight: 160,
|
||||
padding: 20,
|
||||
color: GRAPH_THEME.ui.text.muted,
|
||||
fontSize: 12,
|
||||
textAlign: "center",
|
||||
};
|
||||
|
||||
const retryButtonStyle: CSSProperties = {
|
||||
padding: "6px 10px",
|
||||
borderRadius: 7,
|
||||
border: `1px solid ${GRAPH_THEME.ui.control.activeBorder}`,
|
||||
background: GRAPH_THEME.ui.timeline.playheadSoft,
|
||||
color: GRAPH_THEME.ui.timeline.playhead,
|
||||
cursor: "pointer",
|
||||
};
|
||||
|
||||
const alertStyle: CSSProperties = {
|
||||
marginBottom: 12,
|
||||
padding: "10px 12px",
|
||||
borderRadius: 8,
|
||||
border: "1px solid rgba(248, 81, 73, 0.28)",
|
||||
background: "rgba(248, 81, 73, 0.1)",
|
||||
color: "#ffb4ad",
|
||||
fontSize: 12,
|
||||
};
|
||||
@@ -8,10 +8,8 @@ import {
|
||||
useNodesState,
|
||||
useEdgesState,
|
||||
MarkerType,
|
||||
Handle,
|
||||
Position,
|
||||
} from "@xyflow/react";
|
||||
import type { Connection, Edge, Node, ReactFlowInstance } from "@xyflow/react";
|
||||
import type { Connection, Edge, Node } from "@xyflow/react";
|
||||
import "@xyflow/react/dist/style.css";
|
||||
import {
|
||||
Plus,
|
||||
@@ -24,20 +22,10 @@ import {
|
||||
Pencil,
|
||||
Trash2,
|
||||
} from "lucide-react";
|
||||
import { loadOntologyEntityOwner, loadOntologyGraph } from "./api";
|
||||
import type { OntologyGraphEdge, OntologyGraphNode } from "./api";
|
||||
import {
|
||||
classifyNodeType,
|
||||
inferOntologyUri,
|
||||
isEditableEntityType,
|
||||
ONTOLOGY_MINIMAP_THEME,
|
||||
} from "./ontologyEditorModel";
|
||||
import type { EditorEntityType, RegistryEntry } from "./ontologyEditorModel";
|
||||
|
||||
type OntologyNodeData = {
|
||||
label?: string;
|
||||
type?: string;
|
||||
entityType?: EditorEntityType;
|
||||
};
|
||||
|
||||
type OntologyNode = Node<OntologyNodeData>;
|
||||
@@ -46,57 +34,12 @@ type OntologyEdge = Edge<Record<string, unknown>>;
|
||||
const nodeTypes = {
|
||||
classNode: ({ data }: { data: OntologyNodeData }) => (
|
||||
<div style={classNodeStyle}>
|
||||
<Handle type="target" position={Position.Left} style={handleStyle} />
|
||||
<div style={classNodeHeader}>{data.label}</div>
|
||||
<div style={classNodeSub}>{data.type}</div>
|
||||
<Handle type="source" position={Position.Right} style={handleStyle} />
|
||||
</div>
|
||||
),
|
||||
};
|
||||
|
||||
const handleStyle: React.CSSProperties = {
|
||||
width: 8,
|
||||
height: 8,
|
||||
border: "1px solid rgba(235, 243, 255, 0.8)",
|
||||
background: "#4aa3ff",
|
||||
};
|
||||
|
||||
const ontologyFlowThemeCss = `
|
||||
.ontology-editor-flow .react-flow__controls {
|
||||
overflow: hidden;
|
||||
border: 1px solid rgba(127, 208, 255, 0.2);
|
||||
border-radius: 9px;
|
||||
background: rgba(6, 13, 26, 0.96);
|
||||
box-shadow: 0 8px 24px rgba(0, 0, 0, 0.38);
|
||||
}
|
||||
|
||||
.ontology-editor-flow .react-flow__controls-button {
|
||||
width: 30px;
|
||||
height: 30px;
|
||||
background: transparent;
|
||||
border-bottom-color: rgba(127, 208, 255, 0.14);
|
||||
color: #8fa8c6;
|
||||
transition: color 140ms ease, background 140ms ease;
|
||||
}
|
||||
|
||||
.ontology-editor-flow .react-flow__controls-button:hover {
|
||||
background: rgba(74, 163, 255, 0.14);
|
||||
color: #ebf3ff;
|
||||
}
|
||||
|
||||
.ontology-editor-flow .react-flow__controls-button:focus-visible {
|
||||
position: relative;
|
||||
z-index: 1;
|
||||
outline: 2px solid #7fd0ff;
|
||||
outline-offset: -2px;
|
||||
}
|
||||
|
||||
.ontology-editor-flow .react-flow__controls-button:disabled {
|
||||
background: rgba(3, 9, 18, 0.32);
|
||||
color: #40566f;
|
||||
}
|
||||
`;
|
||||
|
||||
const classNodeStyle: React.CSSProperties = {
|
||||
padding: "12px 16px",
|
||||
borderRadius: "8px",
|
||||
@@ -136,95 +79,17 @@ interface DraftDiff {
|
||||
annotation_changes: Record<string, Record<string, any>>;
|
||||
}
|
||||
|
||||
function requestedEntityUri(): string {
|
||||
try {
|
||||
return new URLSearchParams(window.location.search).get("ontologyEntity") || "";
|
||||
} catch {
|
||||
return "";
|
||||
}
|
||||
}
|
||||
|
||||
function nodeLabel(node: OntologyGraphNode): string {
|
||||
const explicit = String(node.content || node.properties?.["rdfs:label"] || "").trim();
|
||||
if (explicit && explicit !== node.id) {
|
||||
return explicit;
|
||||
}
|
||||
const trimmed = node.id.replace(/[/#]+$/, "");
|
||||
return trimmed.split("#").pop() || trimmed.split("/").pop() || node.id;
|
||||
}
|
||||
|
||||
function classifyEditorNode(node: OntologyGraphNode): OntologyNodeData["entityType"] {
|
||||
return classifyNodeType(node.type);
|
||||
}
|
||||
|
||||
function layoutEditorNodes(inputNodes: OntologyNode[]): OntologyNode[] {
|
||||
const properties = inputNodes.filter((node) => node.data.entityType === "property");
|
||||
const targets = inputNodes.filter((node) => (
|
||||
node.data.entityType === "class" || node.data.entityType === "external"
|
||||
));
|
||||
const context = inputNodes.filter((node) => (
|
||||
node.data.entityType !== "property"
|
||||
&& node.data.entityType !== "class"
|
||||
&& node.data.entityType !== "external"
|
||||
));
|
||||
const height = Math.max(360, Math.max(properties.length, targets.length) * 180);
|
||||
const positions = new Map<string, { x: number; y: number }>();
|
||||
|
||||
properties.forEach((node, index) => {
|
||||
positions.set(node.id, { x: 0, y: ((index + 1) * height) / (properties.length + 1) });
|
||||
});
|
||||
targets.forEach((node, index) => {
|
||||
positions.set(node.id, { x: 600, y: ((index + 1) * height) / (targets.length + 1) });
|
||||
});
|
||||
context.forEach((node, index) => {
|
||||
positions.set(node.id, { x: 300 + index * 220, y: height + 120 });
|
||||
});
|
||||
|
||||
return inputNodes.map((node) => ({
|
||||
...node,
|
||||
position: positions.get(node.id) || node.position,
|
||||
}));
|
||||
}
|
||||
|
||||
function buildEditorElements(apiNodes: OntologyGraphNode[], apiEdges: OntologyGraphEdge[]) {
|
||||
const sortedNodes = [...apiNodes].sort((left, right) => {
|
||||
const typeDelta = left.type.localeCompare(right.type);
|
||||
return typeDelta || left.id.localeCompare(right.id);
|
||||
});
|
||||
const nodes = layoutEditorNodes(sortedNodes.map((node) => ({
|
||||
id: node.id,
|
||||
type: "classNode",
|
||||
position: { x: 0, y: 0 },
|
||||
data: {
|
||||
label: nodeLabel(node),
|
||||
type: node.type,
|
||||
entityType: classifyEditorNode(node),
|
||||
},
|
||||
})));
|
||||
const edges: OntologyEdge[] = apiEdges.map((edge, index) => ({
|
||||
id: edge.id || `${edge.source}:${edge.type}:${edge.target}:${index}`,
|
||||
source: edge.source,
|
||||
target: edge.target,
|
||||
label: edge.type,
|
||||
type: "default",
|
||||
markerEnd: { type: MarkerType.ArrowClosed },
|
||||
style: { stroke: "rgba(127, 208, 255, 0.72)", strokeWidth: 1.5 },
|
||||
labelStyle: { fill: "#c8dcf5", fontSize: 11, fontWeight: 600 },
|
||||
labelBgStyle: { fill: "#07111f", fillOpacity: 0.9 },
|
||||
}));
|
||||
return { nodes, edges };
|
||||
interface RegistryEntry {
|
||||
uri: string;
|
||||
name: string;
|
||||
}
|
||||
|
||||
export function OntologyEditor() {
|
||||
const [nodes, setNodes, onNodesChange] = useNodesState<OntologyNode>([]);
|
||||
const [edges, setEdges, onEdgesChange] = useEdgesState<OntologyEdge>([]);
|
||||
const [selectedElement, setSelectedElement] = useState<OntologyNode | OntologyEdge | null>(null);
|
||||
const hasDetailPanel = selectedElement !== null;
|
||||
const [registry, setRegistry] = useState<RegistryEntry[]>([]);
|
||||
const [ontologyUri, setOntologyUri] = useState<string>("");
|
||||
const [flowInstance, setFlowInstance] = useState<ReactFlowInstance<OntologyNode, OntologyEdge> | null>(null);
|
||||
const [isLoadingGraph, setIsLoadingGraph] = useState(false);
|
||||
const [graphError, setGraphError] = useState("");
|
||||
const [draftDiff, setDraftDiff] = useState<DraftDiff>({
|
||||
added_classes: [],
|
||||
removed_classes: [],
|
||||
@@ -243,18 +108,12 @@ export function OntologyEditor() {
|
||||
|
||||
useEffect(() => {
|
||||
let cancelled = false;
|
||||
const requested = requestedEntityUri();
|
||||
Promise.all([
|
||||
fetch("/api/ontology/registry").then((response) => (response.ok ? response.json() : [])),
|
||||
requested
|
||||
? loadOntologyEntityOwner(requested).catch(() => undefined)
|
||||
: Promise.resolve(undefined),
|
||||
])
|
||||
.then(([entries, explicitOwner]: [RegistryEntry[], string | undefined]) => {
|
||||
fetch("/api/ontology/registry")
|
||||
.then((response) => (response.ok ? response.json() : []))
|
||||
.then((entries: RegistryEntry[]) => {
|
||||
if (cancelled) return;
|
||||
setRegistry(entries);
|
||||
const inferredOntology = inferOntologyUri(entries, requested, explicitOwner);
|
||||
setOntologyUri((current) => current || inferredOntology || entries[0]?.uri || "");
|
||||
setOntologyUri((current) => current || entries[0]?.uri || "");
|
||||
})
|
||||
.catch((error) => {
|
||||
console.error("Failed to load ontology registry:", error);
|
||||
@@ -264,47 +123,6 @@ export function OntologyEditor() {
|
||||
};
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
if (!ontologyUri) {
|
||||
setNodes([]);
|
||||
setEdges([]);
|
||||
setSelectedElement(null);
|
||||
return;
|
||||
}
|
||||
|
||||
const controller = new AbortController();
|
||||
setIsLoadingGraph(true);
|
||||
setGraphError("");
|
||||
loadOntologyGraph(ontologyUri, controller.signal)
|
||||
.then((payload) => {
|
||||
const elements = buildEditorElements(payload.nodes, payload.edges);
|
||||
setNodes(elements.nodes);
|
||||
setEdges(elements.edges);
|
||||
const requested = requestedEntityUri();
|
||||
setSelectedElement(elements.nodes.find((node) => node.id === requested) || null);
|
||||
})
|
||||
.catch((error) => {
|
||||
if (controller.signal.aborted) return;
|
||||
setNodes([]);
|
||||
setEdges([]);
|
||||
setSelectedElement(null);
|
||||
setGraphError(error instanceof Error ? error.message : "Failed to load ontology graph");
|
||||
})
|
||||
.finally(() => {
|
||||
if (!controller.signal.aborted) setIsLoadingGraph(false);
|
||||
});
|
||||
|
||||
return () => controller.abort();
|
||||
}, [ontologyUri, setEdges, setNodes]);
|
||||
|
||||
useEffect(() => {
|
||||
if (!flowInstance || nodes.length === 0) return;
|
||||
const frame = window.requestAnimationFrame(() => {
|
||||
void flowInstance.fitView({ padding: 0.22, duration: 320, maxZoom: 1.25 });
|
||||
});
|
||||
return () => window.cancelAnimationFrame(frame);
|
||||
}, [flowInstance, hasDetailPanel, nodes.length, ontologyUri]);
|
||||
|
||||
const onConnect = useCallback(
|
||||
(params: Connection) => setEdges((eds) => addEdge({ ...params, markerEnd: { type: MarkerType.ArrowClosed } }, eds)),
|
||||
[setEdges]
|
||||
@@ -316,7 +134,7 @@ export function OntologyEditor() {
|
||||
id: newId,
|
||||
type: "classNode",
|
||||
position: { x: Math.random() * 400, y: Math.random() * 300 },
|
||||
data: { label: "NewClass", type: "owl:Class", entityType: "class" },
|
||||
data: { label: "NewClass", type: "owl:Class" },
|
||||
};
|
||||
setNodes((nds) => [...nds, newNode]);
|
||||
setDraftDiff((prev) => ({
|
||||
@@ -352,7 +170,7 @@ export function OntologyEditor() {
|
||||
id: newId,
|
||||
type: "classNode",
|
||||
position: { x: Math.random() * 400, y: Math.random() * 300 },
|
||||
data: { label: "NewIndividual", type: "owl:NamedIndividual", entityType: "external" },
|
||||
data: { label: "NewIndividual", type: "owl:NamedIndividual" },
|
||||
};
|
||||
setNodes((nds) => [...nds, newNode]);
|
||||
}, [setNodes]);
|
||||
@@ -372,21 +190,13 @@ export function OntologyEditor() {
|
||||
}, []);
|
||||
|
||||
const autoLayout = useCallback(() => {
|
||||
setNodes(layoutEditorNodes(nodes));
|
||||
const layoutNodes = nodes.map((node, index) => ({
|
||||
...node,
|
||||
position: { x: (index % 4) * 200, y: Math.floor(index / 4) * 150 },
|
||||
}));
|
||||
setNodes(layoutNodes);
|
||||
}, [nodes, setNodes]);
|
||||
|
||||
const selectNode = useCallback((node: OntologyNode) => {
|
||||
setSelectedElement(node);
|
||||
try {
|
||||
const params = new URLSearchParams(window.location.search);
|
||||
params.set("ontologyTab", "editor");
|
||||
params.set("ontologyEntity", node.id);
|
||||
window.history.replaceState(null, "", `?${params.toString()}`);
|
||||
} catch {
|
||||
// URL state is optional; the editor selection still works without it.
|
||||
}
|
||||
}, []);
|
||||
|
||||
const saveDraft = useCallback(async () => {
|
||||
if (!ontologyUri) {
|
||||
alert("Please select an ontology first");
|
||||
@@ -437,11 +247,12 @@ export function OntologyEditor() {
|
||||
...prev,
|
||||
removed_properties: [...prev.removed_properties, target.id],
|
||||
}));
|
||||
} else if (isEditableEntityType(target.data.entityType)) {
|
||||
} else {
|
||||
setNodes((nds) => nds.filter((n) => n.id !== target.id));
|
||||
setDraftDiff((prev) => target.data.entityType === "property"
|
||||
? { ...prev, removed_properties: [...prev.removed_properties, target.id] }
|
||||
: { ...prev, removed_classes: [...prev.removed_classes, target.id] });
|
||||
setDraftDiff((prev) => ({
|
||||
...prev,
|
||||
removed_classes: [...prev.removed_classes, target.id],
|
||||
}));
|
||||
}
|
||||
setSelectedElement(null);
|
||||
}
|
||||
@@ -450,21 +261,16 @@ export function OntologyEditor() {
|
||||
|
||||
const renameSelected = useCallback(() => {
|
||||
const target = showContext?.element ?? selectedElement;
|
||||
if (target && !("source" in target) && isEditableEntityType(target.data.entityType)) {
|
||||
if (target && !("source" in target)) {
|
||||
const newLabel = prompt("Enter new name:", String(target.data.label ?? ""));
|
||||
if (newLabel) {
|
||||
setNodes((nds) =>
|
||||
nds.map((n) => (n.id === target.id ? { ...n, data: { ...n.data, label: newLabel } } : n))
|
||||
);
|
||||
setDraftDiff((prev) => target.data.entityType === "property"
|
||||
? {
|
||||
...prev,
|
||||
modified_properties: { ...prev.modified_properties, [target.id]: { label: newLabel } },
|
||||
}
|
||||
: {
|
||||
...prev,
|
||||
modified_classes: { ...prev.modified_classes, [target.id]: { label: newLabel } },
|
||||
});
|
||||
setDraftDiff((prev) => ({
|
||||
...prev,
|
||||
modified_classes: { ...prev.modified_classes, [target.id]: { label: newLabel } },
|
||||
}));
|
||||
}
|
||||
}
|
||||
setShowContext(null);
|
||||
@@ -533,10 +339,11 @@ export function OntologyEditor() {
|
||||
};
|
||||
|
||||
const detailPanelStyle: React.CSSProperties = {
|
||||
flex: "0 0 320px",
|
||||
position: "absolute",
|
||||
right: 0,
|
||||
top: 0,
|
||||
bottom: 0,
|
||||
width: "320px",
|
||||
minWidth: "320px",
|
||||
boxSizing: "border-box",
|
||||
background: "rgba(9, 19, 34, 0.95)",
|
||||
borderLeft: "1px solid rgba(140, 192, 255, 0.12)",
|
||||
padding: "20px",
|
||||
@@ -546,24 +353,11 @@ export function OntologyEditor() {
|
||||
|
||||
return (
|
||||
<div style={{ display: "flex", flexDirection: "column", height: "100%", background: "#07111f" }}>
|
||||
<style>{ontologyFlowThemeCss}</style>
|
||||
<div style={toolbarStyle}>
|
||||
<select
|
||||
aria-label="Active ontology"
|
||||
value={ontologyUri}
|
||||
onChange={(event) => {
|
||||
setOntologyUri(event.target.value);
|
||||
setSelectedElement(null);
|
||||
try {
|
||||
// Drop the previous ontology's entity from the URL, or a reload
|
||||
// would resolve the stale ID and jump back to that ontology.
|
||||
const params = new URLSearchParams(window.location.search);
|
||||
params.delete("ontologyEntity");
|
||||
window.history.replaceState(null, "", `?${params.toString()}`);
|
||||
} catch {
|
||||
// URL state is optional; switching ontologies still works.
|
||||
}
|
||||
}}
|
||||
onChange={(event) => setOntologyUri(event.target.value)}
|
||||
style={selectStyle}
|
||||
>
|
||||
<option value="">Select ontology...</option>
|
||||
@@ -604,75 +398,43 @@ export function OntologyEditor() {
|
||||
</button>
|
||||
</div>
|
||||
|
||||
<div style={{ display: "flex", flex: 1, minHeight: 0, minWidth: 0 }}>
|
||||
<div style={{ flex: 1, minHeight: 0, minWidth: 0, position: "relative" }}>
|
||||
<ReactFlow
|
||||
className="ontology-editor-flow"
|
||||
nodes={nodes}
|
||||
edges={edges}
|
||||
onNodesChange={onNodesChange}
|
||||
onEdgesChange={onEdgesChange}
|
||||
onConnect={onConnect}
|
||||
onInit={setFlowInstance}
|
||||
onNodeClick={(_, node) => selectNode(node)}
|
||||
onEdgeClick={(_, edge) => setSelectedElement(edge)}
|
||||
onNodeContextMenu={handleNodeContextMenu}
|
||||
onEdgeContextMenu={handleEdgeContextMenu}
|
||||
nodeTypes={nodeTypes}
|
||||
fitView
|
||||
style={{ background: "#07111f" }}
|
||||
>
|
||||
<Background color="#1a2d3d" gap={20} />
|
||||
<Controls />
|
||||
<MiniMap {...ONTOLOGY_MINIMAP_THEME} />
|
||||
</ReactFlow>
|
||||
<div style={{ flex: 1, position: "relative" }}>
|
||||
<ReactFlow
|
||||
nodes={nodes}
|
||||
edges={edges}
|
||||
onNodesChange={onNodesChange}
|
||||
onEdgesChange={onEdgesChange}
|
||||
onConnect={onConnect}
|
||||
onNodeClick={(_, node) => setSelectedElement(node)}
|
||||
onEdgeClick={(_, edge) => setSelectedElement(edge)}
|
||||
onNodeContextMenu={handleNodeContextMenu}
|
||||
onEdgeContextMenu={handleEdgeContextMenu}
|
||||
nodeTypes={nodeTypes}
|
||||
fitView
|
||||
style={{ background: "#07111f" }}
|
||||
>
|
||||
<Background color="#1a2d3d" gap={20} />
|
||||
<Controls />
|
||||
<MiniMap nodeColor="#4aa3ff" maskColor="rgba(0,0,0,0.6)" />
|
||||
</ReactFlow>
|
||||
|
||||
{isLoadingGraph && (
|
||||
<div style={canvasMessageStyle}>Loading ontology structure…</div>
|
||||
)}
|
||||
{!isLoadingGraph && graphError && (
|
||||
<div style={{ ...canvasMessageStyle, color: "#ff9a8d" }}>{graphError}</div>
|
||||
)}
|
||||
{!isLoadingGraph && !graphError && ontologyUri && nodes.length === 0 && (
|
||||
<div style={canvasMessageStyle}>This ontology has no editable classes or properties.</div>
|
||||
)}
|
||||
|
||||
{showContext && (
|
||||
<div style={{ ...contextMenuStyle, left: showContext.x, top: showContext.y }}>
|
||||
{"source" in showContext.element || isEditableEntityType(showContext.element.data.entityType) ? (
|
||||
<>
|
||||
{!("source" in showContext.element) && (
|
||||
<div style={contextItemStyle} onClick={renameSelected}>
|
||||
<Pencil size={14} />
|
||||
Rename
|
||||
</div>
|
||||
)}
|
||||
<div style={contextItemStyle} onClick={deleteSelected}>
|
||||
<Trash2 size={14} />
|
||||
Delete
|
||||
</div>
|
||||
</>
|
||||
) : (
|
||||
<div style={{ ...contextItemStyle, cursor: "default", color: "#8fa8c6" }}>
|
||||
This term is read-only
|
||||
</div>
|
||||
)}
|
||||
{showContext && (
|
||||
<div style={{ ...contextMenuStyle, left: showContext.x, top: showContext.y }}>
|
||||
<div style={contextItemStyle} onClick={renameSelected}>
|
||||
<Pencil size={14} />
|
||||
Rename
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
<div style={contextItemStyle} onClick={deleteSelected}>
|
||||
<Trash2 size={14} />
|
||||
Delete
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{selectedElement && (
|
||||
<div style={detailPanelStyle}>
|
||||
<h3 style={{ margin: "0 0 16px", color: "#ebf3ff", fontSize: "16px" }}>
|
||||
{"source" in selectedElement
|
||||
? "Relationship Details"
|
||||
: selectedElement.data.entityType === "property"
|
||||
? "Property Details"
|
||||
: selectedElement.data.entityType === "ontology"
|
||||
? "Ontology Details"
|
||||
: selectedElement.data.entityType === "external"
|
||||
? "External Term Details"
|
||||
: "Class Details"}
|
||||
{"source" in selectedElement ? "Property Details" : "Class Details"}
|
||||
</h3>
|
||||
<div style={{ marginBottom: "12px" }}>
|
||||
<label style={{ display: "block", color: "#8fa8c6", fontSize: "12px", marginBottom: "4px" }}>
|
||||
@@ -691,9 +453,7 @@ export function OntologyEditor() {
|
||||
<input
|
||||
type="text"
|
||||
value={String(selectedElement.data.label ?? "")}
|
||||
readOnly={!isEditableEntityType(selectedElement.data.entityType)}
|
||||
onChange={(e) => {
|
||||
if (!isEditableEntityType(selectedElement.data.entityType)) return;
|
||||
setNodes((nds) =>
|
||||
nds.map((n) =>
|
||||
n.id === selectedElement.id
|
||||
@@ -703,19 +463,10 @@ export function OntologyEditor() {
|
||||
);
|
||||
setDraftDiff((prev) => ({
|
||||
...prev,
|
||||
...(selectedElement.data.entityType === "property"
|
||||
? {
|
||||
modified_properties: {
|
||||
...prev.modified_properties,
|
||||
[selectedElement.id]: { label: e.target.value },
|
||||
},
|
||||
}
|
||||
: {
|
||||
modified_classes: {
|
||||
...prev.modified_classes,
|
||||
[selectedElement.id]: { label: e.target.value },
|
||||
},
|
||||
}),
|
||||
modified_classes: {
|
||||
...prev.modified_classes,
|
||||
[selectedElement.id]: { label: e.target.value },
|
||||
},
|
||||
}));
|
||||
}}
|
||||
style={{
|
||||
@@ -745,17 +496,3 @@ export function OntologyEditor() {
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
const canvasMessageStyle: React.CSSProperties = {
|
||||
position: "absolute",
|
||||
left: "50%",
|
||||
top: "50%",
|
||||
transform: "translate(-50%, -50%)",
|
||||
padding: "10px 14px",
|
||||
borderRadius: "8px",
|
||||
border: "1px solid rgba(127, 208, 255, 0.18)",
|
||||
background: "rgba(3, 9, 18, 0.9)",
|
||||
color: "#8fa8c6",
|
||||
fontSize: "13px",
|
||||
pointerEvents: "none",
|
||||
};
|
||||
|
||||
@@ -9,32 +9,6 @@ import type {
|
||||
ShaclValidationResponse,
|
||||
} from "./types";
|
||||
|
||||
export type OntologyGraphNode = {
|
||||
id: string;
|
||||
type: string;
|
||||
content?: string;
|
||||
properties?: Record<string, unknown>;
|
||||
};
|
||||
|
||||
export type OntologyGraphEdge = {
|
||||
id?: string;
|
||||
source: string;
|
||||
target: string;
|
||||
type: string;
|
||||
weight?: number;
|
||||
properties?: Record<string, unknown>;
|
||||
};
|
||||
|
||||
export type OntologyGraphResponse = {
|
||||
uri: string;
|
||||
nodes: OntologyGraphNode[];
|
||||
edges: OntologyGraphEdge[];
|
||||
};
|
||||
|
||||
export type OntologyEntityOwner = {
|
||||
source_ontology?: string;
|
||||
};
|
||||
|
||||
async function parseResponse<T>(response: Response): Promise<T> {
|
||||
if (!response.ok) {
|
||||
let detail = `Request failed with status ${response.status}`;
|
||||
@@ -57,18 +31,6 @@ export async function loadOntologyRegistry(): Promise<OntologyEntry[]> {
|
||||
return parseResponse<OntologyEntry[]>(await fetch("/api/ontology/registry"));
|
||||
}
|
||||
|
||||
export async function loadOntologyGraph(uri: string, signal?: AbortSignal): Promise<OntologyGraphResponse> {
|
||||
return parseResponse<OntologyGraphResponse>(
|
||||
await fetch(`/api/ontology/graph?uri=${encodeURIComponent(uri)}`, { signal }),
|
||||
);
|
||||
}
|
||||
|
||||
export async function loadOntologyEntityOwner(uri: string): Promise<string | undefined> {
|
||||
const response = await fetch(`/api/ontology/entity/${encodeURIComponent(uri)}`);
|
||||
if (!response.ok) return undefined;
|
||||
return (await response.json() as OntologyEntityOwner).source_ontology;
|
||||
}
|
||||
|
||||
export async function loadAlignments(uri?: string): Promise<OntologyAlignment[]> {
|
||||
const query = uri ? `?uri=${encodeURIComponent(uri)}` : "";
|
||||
return parseResponse<OntologyAlignment[]>(await fetch(`/api/ontology/alignments${query}`));
|
||||
|
||||
@@ -38,7 +38,6 @@ function readTabParam(): OntologyHubTab {
|
||||
const params = new URLSearchParams(window.location.search);
|
||||
const raw = params.get(TAB_PARAM);
|
||||
if (raw && TABS.some((t) => t.id === raw)) return raw as OntologyHubTab;
|
||||
if (params.get("ontologyEntity")) return "editor";
|
||||
} catch {
|
||||
// ignore
|
||||
}
|
||||
@@ -117,3 +116,4 @@ export function OntologyWorkspace({ onJumpToGraphNode }: OntologyWorkspaceProps)
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -1,70 +0,0 @@
|
||||
export type EditorEntityType = "ontology" | "class" | "property" | "external";
|
||||
|
||||
export type RegistryEntry = {
|
||||
uri: string;
|
||||
name: string;
|
||||
};
|
||||
|
||||
export const ONTOLOGY_MINIMAP_THEME = {
|
||||
bgColor: "#0b1625",
|
||||
maskColor: "rgba(7, 17, 31, 0.72)",
|
||||
maskStrokeColor: "#5faeff",
|
||||
maskStrokeWidth: 2,
|
||||
nodeColor: "#2d7fd3",
|
||||
nodeStrokeColor: "#9acbff",
|
||||
nodeStrokeWidth: 1,
|
||||
style: {
|
||||
border: "1px solid #29435c",
|
||||
borderRadius: 6,
|
||||
boxShadow: "0 4px 16px rgba(0, 0, 0, 0.32)",
|
||||
},
|
||||
} as const;
|
||||
|
||||
// The backend emits node types in compact (owl:Class) or full IRI
|
||||
// (http://www.w3.org/2002/07/owl#Class) form; classification must accept both.
|
||||
const FULL_IRI_PREFIXES: Array<[string, string]> = [
|
||||
["http://www.w3.org/2002/07/owl#", "owl:"],
|
||||
["http://www.w3.org/2000/01/rdf-schema#", "rdfs:"],
|
||||
["http://www.w3.org/2004/02/skos/core#", "skos:"],
|
||||
];
|
||||
|
||||
export function compactNodeType(type: string): string {
|
||||
for (const [iri, prefix] of FULL_IRI_PREFIXES) {
|
||||
if (type.startsWith(iri)) {
|
||||
return `${prefix}${type.slice(iri.length)}`;
|
||||
}
|
||||
}
|
||||
return type;
|
||||
}
|
||||
|
||||
export function classifyNodeType(rawType: string): EditorEntityType {
|
||||
const type = compactNodeType(rawType);
|
||||
if (type === "owl:Ontology") return "ontology";
|
||||
if (type === "owl:Class" || type === "rdfs:Class") return "class";
|
||||
if (type.includes("Property")) return "property";
|
||||
return "external";
|
||||
}
|
||||
|
||||
function ownsByNamespace(entityUri: string, ontologyUri: string): boolean {
|
||||
const stem = ontologyUri.replace(/[/#]+$/, "");
|
||||
return entityUri === ontologyUri
|
||||
|| entityUri.startsWith(`${stem}#`)
|
||||
|| entityUri.startsWith(`${stem}/`);
|
||||
}
|
||||
|
||||
export function inferOntologyUri(
|
||||
entries: RegistryEntry[],
|
||||
entityUri: string,
|
||||
explicitOwner?: string,
|
||||
): string | undefined {
|
||||
if (explicitOwner && entries.some((entry) => entry.uri === explicitOwner)) {
|
||||
return explicitOwner;
|
||||
}
|
||||
return [...entries]
|
||||
.filter((entry) => ownsByNamespace(entityUri, entry.uri))
|
||||
.sort((left, right) => right.uri.length - left.uri.length)[0]?.uri;
|
||||
}
|
||||
|
||||
export function isEditableEntityType(entityType?: EditorEntityType): boolean {
|
||||
return entityType === "class" || entityType === "property";
|
||||
}
|
||||
@@ -42,9 +42,6 @@ async function startVite(): Promise<void> {
|
||||
}
|
||||
|
||||
async function installApiFixture(page: Page): Promise<void> {
|
||||
await page.route("**/api/info", async (route) => {
|
||||
await route.fulfill({ json: { capabilities: { agent_memory: false } } });
|
||||
});
|
||||
await page.route("**/api/graph/**", async (route) => {
|
||||
const pathname = new URL(route.request().url()).pathname;
|
||||
if (pathname === "/api/graph/stats") {
|
||||
|
||||
@@ -1,74 +0,0 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import { JSDOM } from "jsdom";
|
||||
import React from "react";
|
||||
|
||||
import { fetchAgentMemoryAvailability } from "../src/explorerCapabilities.ts";
|
||||
|
||||
(globalThis as typeof globalThis & { React: typeof React }).React = React;
|
||||
const dom = new JSDOM("<!doctype html><html><body></body></html>", {
|
||||
url: "http://localhost",
|
||||
});
|
||||
Object.assign(globalThis, {
|
||||
window: dom.window,
|
||||
document: dom.window.document,
|
||||
HTMLElement: dom.window.HTMLElement,
|
||||
Node: dom.window.Node,
|
||||
});
|
||||
Object.defineProperty(globalThis, "navigator", {
|
||||
configurable: true,
|
||||
value: dom.window.navigator,
|
||||
});
|
||||
|
||||
const { cleanup, render } = await import("@testing-library/react");
|
||||
const { ExploreWorkspaceTabs } = await import("../src/ExploreWorkspaceTabs.tsx");
|
||||
|
||||
test.afterEach(cleanup);
|
||||
|
||||
test("reports AgentMemory when the Explorer host provides it", async () => {
|
||||
const available = await fetchAgentMemoryAvailability(async () => (
|
||||
new Response(
|
||||
JSON.stringify({ capabilities: { agent_memory: true } }),
|
||||
{ status: 200, headers: { "content-type": "application/json" } },
|
||||
)
|
||||
));
|
||||
|
||||
assert.equal(available, true);
|
||||
});
|
||||
|
||||
test("keeps AgentMemory hidden when the capability is absent or unavailable", async () => {
|
||||
const absent = await fetchAgentMemoryAvailability(async () => (
|
||||
new Response(JSON.stringify({ status: "active" }), { status: 200 })
|
||||
));
|
||||
const unavailable = await fetchAgentMemoryAvailability(async () => {
|
||||
throw new Error("network unavailable");
|
||||
});
|
||||
|
||||
assert.equal(absent, false);
|
||||
assert.equal(unavailable, false);
|
||||
});
|
||||
|
||||
test("shows the Memories tab only when the host provides AgentMemory", () => {
|
||||
const availableView = render(
|
||||
<ExploreWorkspaceTabs
|
||||
activeView="graph"
|
||||
agentMemoryAvailable
|
||||
onSelect={() => undefined}
|
||||
/>,
|
||||
);
|
||||
assert.ok(availableView.getByRole("button", { name: "Memories" }));
|
||||
cleanup();
|
||||
|
||||
const unavailableView = render(
|
||||
<ExploreWorkspaceTabs
|
||||
activeView="graph"
|
||||
agentMemoryAvailable={false}
|
||||
onSelect={() => undefined}
|
||||
/>,
|
||||
);
|
||||
assert.equal(
|
||||
unavailableView.queryByRole("button", { name: "Memories" }),
|
||||
null,
|
||||
);
|
||||
});
|
||||
@@ -3,7 +3,7 @@ import assert from "node:assert/strict";
|
||||
import React from "react";
|
||||
import { renderToString } from "react-dom/server";
|
||||
|
||||
(globalThis as typeof globalThis & { React: typeof React }).React = React;
|
||||
(globalThis as any).React = React;
|
||||
|
||||
import { MarkdownContentViewer } from "../src/workspaces/GraphWorkspace/MarkdownContentViewer.tsx";
|
||||
import { isSafeUrl } from "../src/workspaces/GraphWorkspace/markdownUrlSafety.ts";
|
||||
@@ -60,29 +60,6 @@ test("renders Preview mode with formatted Markdown elements and tabs", () => {
|
||||
assert.equal(html.includes("Item B"), true);
|
||||
});
|
||||
|
||||
test("stays read-only without a resource and exposes Edit for canonical resources", () => {
|
||||
const readOnly = renderToString(React.createElement(MarkdownContentViewer, {
|
||||
content: "Read-only body",
|
||||
}));
|
||||
const editable = renderToString(React.createElement(MarkdownContentViewer, {
|
||||
content: "Editable body",
|
||||
resource: { kind: "context-node", id: "node-1" },
|
||||
}));
|
||||
|
||||
assert.equal(readOnly.includes(">Edit</button>"), false);
|
||||
assert.equal(editable.includes(">Edit</button>"), true);
|
||||
});
|
||||
|
||||
test("empty canonical resources still expose Edit", () => {
|
||||
const html = renderToString(React.createElement(MarkdownContentViewer, {
|
||||
content: "",
|
||||
resource: { kind: "context-node", id: "empty-node" },
|
||||
}));
|
||||
|
||||
assert.equal(html.includes("No content available for this node."), true);
|
||||
assert.equal(html.includes(">Edit</button>"), true);
|
||||
});
|
||||
|
||||
test("renders Source mode with exact unmodified text inside pre/code", () => {
|
||||
const markdown = `# Title 🚀\n\n * Indented item\n\n\`\`\`python\ndef test():\n return "α + β"\n\`\`\``;
|
||||
const html = renderToString(React.createElement(MarkdownContentViewer, { content: markdown, defaultMode: "source" }));
|
||||
|
||||
@@ -1,639 +0,0 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import { JSDOM } from "jsdom";
|
||||
import React from "react";
|
||||
|
||||
(globalThis as typeof globalThis & { React: typeof React }).React = React;
|
||||
const dom = new JSDOM("<!doctype html><html><body></body></html>", {
|
||||
url: "http://localhost",
|
||||
});
|
||||
Object.assign(globalThis, {
|
||||
window: dom.window,
|
||||
document: dom.window.document,
|
||||
HTMLElement: dom.window.HTMLElement,
|
||||
Node: dom.window.Node,
|
||||
});
|
||||
Object.defineProperty(globalThis, "navigator", {
|
||||
configurable: true,
|
||||
value: dom.window.navigator,
|
||||
});
|
||||
dom.window.confirm = () => true;
|
||||
|
||||
// Testing Library and the components must load after the jsdom globals above.
|
||||
const { act, cleanup, fireEvent, render, waitFor } = await import(
|
||||
"@testing-library/react"
|
||||
);
|
||||
const { MarkdownContentViewer } = await import(
|
||||
"../src/workspaces/GraphWorkspace/MarkdownContentViewer.tsx"
|
||||
);
|
||||
const { MemoryWorkspace } = await import(
|
||||
"../src/workspaces/MemoryWorkspace.tsx"
|
||||
);
|
||||
|
||||
test.afterEach(() => {
|
||||
cleanup();
|
||||
dom.window.confirm = () => true;
|
||||
});
|
||||
|
||||
const resource = { kind: "context-node" as const, id: "node-1" };
|
||||
const originalSource = "---\nid: node-1\ntype: Note\n---\n\nOriginal";
|
||||
|
||||
function jsonResponse(body: unknown, status = 200): Response {
|
||||
return new Response(JSON.stringify(body), {
|
||||
status,
|
||||
headers: { "Content-Type": "application/json" },
|
||||
});
|
||||
}
|
||||
|
||||
test("Edit and Apply send canonical Markdown and publish the applied result", async () => {
|
||||
const requests: Array<{ url: string; init?: RequestInit }> = [];
|
||||
let appliedBody = "";
|
||||
globalThis.fetch = async (input, init) => {
|
||||
requests.push({ url: String(input), init });
|
||||
if (init?.method === "PUT") {
|
||||
return jsonResponse({
|
||||
resource,
|
||||
source: originalSource.replace("Original", "Updated"),
|
||||
body: "Updated",
|
||||
revision: "sha256:updated",
|
||||
editable: true,
|
||||
changed: true,
|
||||
});
|
||||
}
|
||||
return jsonResponse({
|
||||
resource,
|
||||
source: originalSource,
|
||||
body: "Original",
|
||||
revision: "sha256:original",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(
|
||||
<MarkdownContentViewer
|
||||
content="Original"
|
||||
resource={resource}
|
||||
onApplied={(result) => { appliedBody = result.body; }}
|
||||
/>,
|
||||
);
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
fireEvent.input(textarea, {
|
||||
target: { value: originalSource.replace("Original", "Updated") },
|
||||
});
|
||||
fireEvent.click(view.getByRole("button", { name: "Apply" }));
|
||||
|
||||
await waitFor(() => assert.equal(appliedBody, "Updated"));
|
||||
assert.deepEqual(requests.map(({ init }) => init?.method ?? "GET"), ["GET", "PUT"]);
|
||||
assert.equal(
|
||||
JSON.parse(String(requests[1].init?.body)).expected_revision,
|
||||
"sha256:original",
|
||||
);
|
||||
assert.equal(
|
||||
view.getByRole("tab", { name: "Preview" }).getAttribute("aria-selected"),
|
||||
"true",
|
||||
);
|
||||
});
|
||||
|
||||
test("Cancel restores the previous view and never sends a PUT", async () => {
|
||||
const methods: string[] = [];
|
||||
globalThis.fetch = async (_input, init) => {
|
||||
methods.push(init?.method ?? "GET");
|
||||
return jsonResponse({
|
||||
resource,
|
||||
source: originalSource,
|
||||
body: "Original",
|
||||
revision: "sha256:original",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(<MarkdownContentViewer content="Original" resource={resource} />);
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
fireEvent.input(textarea, {
|
||||
target: { value: originalSource.replace("Original", "Draft") },
|
||||
});
|
||||
fireEvent.click(view.getByRole("button", { name: "Cancel" }));
|
||||
|
||||
assert.deepEqual(methods, ["GET"]);
|
||||
assert.equal(view.queryByRole("textbox", { name: "Markdown source" }), null);
|
||||
assert.equal(
|
||||
view.getByRole("tab", { name: "Preview" }).getAttribute("aria-selected"),
|
||||
"true",
|
||||
);
|
||||
});
|
||||
|
||||
test("validation failures keep the draft visible for correction", async () => {
|
||||
globalThis.fetch = async (_input, init) => {
|
||||
if (init?.method === "PUT") {
|
||||
return jsonResponse({
|
||||
detail: {
|
||||
code: "invalid_markdown_frontmatter",
|
||||
message: "Markdown frontmatter contains invalid YAML.",
|
||||
},
|
||||
}, 422);
|
||||
}
|
||||
return jsonResponse({
|
||||
resource,
|
||||
source: originalSource,
|
||||
body: "Original",
|
||||
revision: "sha256:original",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(<MarkdownContentViewer content="Original" resource={resource} />);
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
const invalidDraft = "---\nid: [\n---\n\nDraft";
|
||||
fireEvent.input(textarea, { target: { value: invalidDraft } });
|
||||
fireEvent.click(view.getByRole("button", { name: "Apply" }));
|
||||
|
||||
const alert = await view.findByRole("alert");
|
||||
assert.match(alert.textContent ?? "", /invalid YAML/);
|
||||
assert.equal(
|
||||
(view.getByRole("textbox", { name: "Markdown source" }) as HTMLTextAreaElement)
|
||||
.value,
|
||||
invalidDraft,
|
||||
);
|
||||
});
|
||||
|
||||
|
||||
test("resource changes discard the previous editor session", async () => {
|
||||
globalThis.fetch = async (input) => {
|
||||
const id = String(input).endsWith("node-2") ? "node-2" : "node-1";
|
||||
return jsonResponse({
|
||||
resource: { kind: "context-node", id },
|
||||
source: `---\nid: ${id}\ntype: Note\n---\n\n${id}`,
|
||||
body: id,
|
||||
revision: `sha256:${id}`,
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(
|
||||
<MarkdownContentViewer content="node-1" resource={resource} />,
|
||||
);
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
fireEvent.input(textarea, {
|
||||
target: { value: `${(textarea as HTMLTextAreaElement).value}\nDraft` },
|
||||
});
|
||||
|
||||
view.rerender(
|
||||
<MarkdownContentViewer
|
||||
content="node-2"
|
||||
resource={{ kind: "context-node", id: "node-2" }}
|
||||
/>,
|
||||
);
|
||||
await waitFor(() => assert.equal(
|
||||
view.queryByRole("textbox", { name: "Markdown source" }),
|
||||
null,
|
||||
));
|
||||
|
||||
view.rerender(
|
||||
<MarkdownContentViewer content="node-1" resource={resource} />,
|
||||
);
|
||||
await waitFor(() => assert.equal(
|
||||
view.queryByRole("textbox", { name: "Markdown source" }),
|
||||
null,
|
||||
));
|
||||
assert.ok(view.getByRole("button", { name: "Edit" }));
|
||||
});
|
||||
|
||||
|
||||
test("unmounting a dirty editor clears the parent dirty guard", async () => {
|
||||
const dirtyStates: boolean[] = [];
|
||||
globalThis.fetch = async () => jsonResponse({
|
||||
resource,
|
||||
source: originalSource,
|
||||
body: "Original",
|
||||
revision: "sha256:original",
|
||||
editable: true,
|
||||
});
|
||||
|
||||
const view = render(
|
||||
<MarkdownContentViewer
|
||||
content="Original"
|
||||
resource={resource}
|
||||
onDirtyChange={(dirty) => dirtyStates.push(dirty)}
|
||||
/>,
|
||||
);
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
fireEvent.input(textarea, {
|
||||
target: { value: originalSource.replace("Original", "Draft") },
|
||||
});
|
||||
await waitFor(() => assert.equal(dirtyStates.at(-1), true));
|
||||
|
||||
view.unmount();
|
||||
|
||||
assert.equal(dirtyStates.at(-1), false);
|
||||
});
|
||||
|
||||
test("MemoryWorkspace protects a dirty memory draft when selection changes", async () => {
|
||||
const requestedUrls: string[] = [];
|
||||
globalThis.fetch = async (input) => {
|
||||
const url = String(input);
|
||||
requestedUrls.push(url);
|
||||
if (url.startsWith("/api/memories")) {
|
||||
return jsonResponse({
|
||||
items: [
|
||||
{ id: "mem-1", type: "note", excerpt: "First", updated_at: null },
|
||||
{ id: "mem-2", type: "note", excerpt: "Second", updated_at: null },
|
||||
],
|
||||
total: 2,
|
||||
skip: 0,
|
||||
limit: 100,
|
||||
});
|
||||
}
|
||||
const id = url.endsWith("mem-2") ? "mem-2" : "mem-1";
|
||||
return jsonResponse({
|
||||
resource: { kind: "agent-memory", id },
|
||||
source: `---\nid: ${id}\ntype: note\n---\n\n${id}`,
|
||||
body: id,
|
||||
revision: `sha256:${id}`,
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(<MemoryWorkspace />);
|
||||
await view.findByText("Selected memory");
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
fireEvent.input(textarea, {
|
||||
target: { value: `${(textarea as HTMLTextAreaElement).value}\nDraft` },
|
||||
});
|
||||
|
||||
dom.window.confirm = () => false;
|
||||
fireEvent.click(view.getByRole("button", { name: /mem-2/ }));
|
||||
|
||||
assert.equal(requestedUrls.some((url) => url.endsWith("mem-2")), false);
|
||||
assert.equal(view.getByText("mem-1", { selector: "strong" }).textContent, "mem-1");
|
||||
});
|
||||
|
||||
|
||||
test("MemoryWorkspace loads memories beyond the first server page", async () => {
|
||||
const requestedUrls: string[] = [];
|
||||
const firstPage = Array.from({ length: 100 }, (_, index) => ({
|
||||
id: `mem-${index + 1}`,
|
||||
type: "note",
|
||||
excerpt: `Memory ${index + 1}`,
|
||||
updated_at: null,
|
||||
}));
|
||||
globalThis.fetch = async (input) => {
|
||||
const url = String(input);
|
||||
requestedUrls.push(url);
|
||||
if (url === "/api/memories?skip=0&limit=100") {
|
||||
return jsonResponse({
|
||||
items: firstPage,
|
||||
total: 101,
|
||||
skip: 0,
|
||||
limit: 100,
|
||||
});
|
||||
}
|
||||
if (url === "/api/memories?skip=100&limit=100") {
|
||||
return jsonResponse({
|
||||
items: [{
|
||||
id: "mem-101",
|
||||
type: "note",
|
||||
excerpt: "Memory 101",
|
||||
updated_at: null,
|
||||
}],
|
||||
total: 101,
|
||||
skip: 100,
|
||||
limit: 100,
|
||||
});
|
||||
}
|
||||
return jsonResponse({
|
||||
resource: { kind: "agent-memory", id: "mem-1" },
|
||||
source: "---\nid: mem-1\ntype: note\n---\n\nmem-1",
|
||||
body: "mem-1",
|
||||
revision: "sha256:mem-1",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(<MemoryWorkspace />);
|
||||
await view.findByText("Selected memory");
|
||||
fireEvent.click(view.getByRole("button", { name: "Load more memories" }));
|
||||
|
||||
await view.findByRole("button", { name: /mem-101/ });
|
||||
assert.ok(requestedUrls.includes("/api/memories?skip=100&limit=100"));
|
||||
assert.equal(view.getByText("101 of 101 loaded").textContent, "101 of 101 loaded");
|
||||
});
|
||||
|
||||
|
||||
test("MemoryWorkspace ignores stale selection responses", async () => {
|
||||
let resolveMem2: ((response: Response) => void) | undefined;
|
||||
let resolveMem3: ((response: Response) => void) | undefined;
|
||||
const mem2Response = new Promise<Response>((resolve) => {
|
||||
resolveMem2 = resolve;
|
||||
});
|
||||
const mem3Response = new Promise<Response>((resolve) => {
|
||||
resolveMem3 = resolve;
|
||||
});
|
||||
|
||||
globalThis.fetch = async (input) => {
|
||||
const url = String(input);
|
||||
if (url.startsWith("/api/memories")) {
|
||||
return jsonResponse({
|
||||
items: [
|
||||
{ id: "mem-1", type: "note", excerpt: "First", updated_at: null },
|
||||
{ id: "mem-2", type: "note", excerpt: "Second", updated_at: null },
|
||||
{ id: "mem-3", type: "note", excerpt: "Third", updated_at: null },
|
||||
],
|
||||
total: 3,
|
||||
skip: 0,
|
||||
limit: 100,
|
||||
});
|
||||
}
|
||||
if (url.endsWith("mem-2")) return mem2Response;
|
||||
if (url.endsWith("mem-3")) return mem3Response;
|
||||
return jsonResponse({
|
||||
resource: { kind: "agent-memory", id: "mem-1" },
|
||||
source: "---\nid: mem-1\ntype: note\n---\n\nmem-1",
|
||||
body: "mem-1",
|
||||
revision: "sha256:mem-1",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(<MemoryWorkspace />);
|
||||
await view.findByText("Selected memory");
|
||||
fireEvent.click(view.getByRole("button", { name: /mem-2/ }));
|
||||
fireEvent.click(view.getByRole("button", { name: /mem-3/ }));
|
||||
|
||||
await act(async () => {
|
||||
resolveMem3?.(jsonResponse({
|
||||
resource: { kind: "agent-memory", id: "mem-3" },
|
||||
source: "---\nid: mem-3\ntype: note\n---\n\nmem-3",
|
||||
body: "mem-3",
|
||||
revision: "sha256:mem-3",
|
||||
editable: true,
|
||||
}));
|
||||
await mem3Response;
|
||||
});
|
||||
await waitFor(() => assert.equal(
|
||||
view.getByText("mem-3", { selector: "strong" }).textContent,
|
||||
"mem-3",
|
||||
));
|
||||
|
||||
await act(async () => {
|
||||
resolveMem2?.(jsonResponse({
|
||||
resource: { kind: "agent-memory", id: "mem-2" },
|
||||
source: "---\nid: mem-2\ntype: note\n---\n\nmem-2",
|
||||
body: "mem-2",
|
||||
revision: "sha256:mem-2",
|
||||
editable: true,
|
||||
}));
|
||||
await mem2Response;
|
||||
});
|
||||
|
||||
assert.equal(
|
||||
view.getByText("mem-3", { selector: "strong" }).textContent,
|
||||
"mem-3",
|
||||
);
|
||||
});
|
||||
|
||||
|
||||
test("MemoryWorkspace refreshes frontmatter summaries after apply", async () => {
|
||||
let listRequests = 0;
|
||||
globalThis.fetch = async (input, init) => {
|
||||
const url = String(input);
|
||||
if (url.startsWith("/api/memories")) {
|
||||
listRequests += 1;
|
||||
const saved = listRequests > 1;
|
||||
return jsonResponse({
|
||||
items: [{
|
||||
id: "mem-1",
|
||||
type: saved ? "decision" : "note",
|
||||
excerpt: saved ? "Updated memory" : "Original memory",
|
||||
updated_at: saved ? "2026-09-01T12:00:00+00:00" : null,
|
||||
}],
|
||||
total: 1,
|
||||
skip: 0,
|
||||
limit: 100,
|
||||
});
|
||||
}
|
||||
if (init?.method === "PUT") {
|
||||
return jsonResponse({
|
||||
resource: { kind: "agent-memory", id: "mem-1" },
|
||||
source: "---\nid: mem-1\ntype: decision\n---\n\nUpdated memory",
|
||||
body: "Updated memory",
|
||||
revision: "sha256:updated",
|
||||
editable: true,
|
||||
changed: true,
|
||||
});
|
||||
}
|
||||
return jsonResponse({
|
||||
resource: { kind: "agent-memory", id: "mem-1" },
|
||||
source: "---\nid: mem-1\ntype: note\n---\n\nOriginal memory",
|
||||
body: "Original memory",
|
||||
revision: "sha256:original",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(<MemoryWorkspace />);
|
||||
await view.findByText("Selected memory");
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
fireEvent.input(textarea, {
|
||||
target: {
|
||||
value: (textarea as HTMLTextAreaElement).value
|
||||
.replace("type: note", "type: decision")
|
||||
.replace("Original memory", "Updated memory"),
|
||||
},
|
||||
});
|
||||
fireEvent.click(view.getByRole("button", { name: "Apply" }));
|
||||
|
||||
await view.findByText("decision");
|
||||
assert.equal(listRequests, 2);
|
||||
assert.equal(view.getAllByText("Updated memory").length, 2);
|
||||
});
|
||||
|
||||
test("HTTP 409 conflict preserves draft and shows conflict error with reload option", async () => {
|
||||
// After a 409, the user's draft must be kept and a recovery path available.
|
||||
const requests: Array<{ method: string; body?: unknown }> = [];
|
||||
let fetchCount = 0;
|
||||
|
||||
globalThis.fetch = async (input, init) => {
|
||||
fetchCount += 1;
|
||||
const method = init?.method ?? "GET";
|
||||
let parsedBody: unknown = undefined;
|
||||
if (init?.body) {
|
||||
try { parsedBody = JSON.parse(String(init.body)); } catch { /* ignore */ }
|
||||
}
|
||||
requests.push({ method, body: parsedBody });
|
||||
|
||||
if (method === "PUT") {
|
||||
// First PUT returns 409 with current_revision
|
||||
return jsonResponse({
|
||||
detail: {
|
||||
code: "markdown_revision_conflict",
|
||||
message: "This item changed after editing began. Reload the latest version before applying.",
|
||||
current_revision: "sha256:newer",
|
||||
},
|
||||
}, 409);
|
||||
}
|
||||
// All GETs return the canonical document
|
||||
return jsonResponse({
|
||||
resource,
|
||||
source: originalSource,
|
||||
body: "Original",
|
||||
revision: "sha256:original",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
const view = render(<MarkdownContentViewer content="Original" resource={resource} />);
|
||||
|
||||
// Enter edit mode
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
const draftValue = originalSource.replace("Original", "My draft");
|
||||
fireEvent.input(textarea, { target: { value: draftValue } });
|
||||
|
||||
// Apply → receives 409
|
||||
fireEvent.click(view.getByRole("button", { name: "Apply" }));
|
||||
|
||||
// Conflict error must appear
|
||||
const alert = await view.findByRole("alert");
|
||||
assert.match(
|
||||
alert.textContent ?? "",
|
||||
/changed after editing|Reload/i,
|
||||
"conflict error message must be shown",
|
||||
);
|
||||
|
||||
// Draft must be preserved in the textarea
|
||||
const textareaAfterConflict = view.getByRole("textbox", { name: "Markdown source" }) as HTMLTextAreaElement;
|
||||
assert.equal(textareaAfterConflict.value, draftValue, "draft must be preserved after 409");
|
||||
|
||||
// A reload / recovery action must be available
|
||||
const reloadButton = view.queryByRole("button", { name: /reload latest/i });
|
||||
assert.ok(reloadButton !== null, "a 'Reload latest' recovery button must be shown");
|
||||
|
||||
// Click reload — should re-fetch the latest canonical document
|
||||
await act(async () => {
|
||||
fireEvent.click(reloadButton!);
|
||||
});
|
||||
|
||||
// After reload the editor is re-initialized with the server's canonical source
|
||||
await waitFor(() => {
|
||||
const refreshedTextarea = view.queryByRole("textbox", { name: "Markdown source" });
|
||||
assert.ok(refreshedTextarea !== null, "editor must still be open after reload");
|
||||
assert.equal(
|
||||
(refreshedTextarea as HTMLTextAreaElement).value,
|
||||
originalSource,
|
||||
"editor must show the server canonical source after reload",
|
||||
);
|
||||
});
|
||||
|
||||
// Reload must have triggered exactly one more GET
|
||||
const getCount = requests.filter((r) => r.method === "GET").length;
|
||||
assert.ok(getCount >= 2, "reload must issue a new GET to fetch the latest canonical document");
|
||||
});
|
||||
|
||||
|
||||
test("successful retry after 422 uses the original revision and persists changes", async () => {
|
||||
// After a 422 (validation failure), the baseRevision must remain valid so that
|
||||
// correcting the draft and re-applying succeeds without re-fetching the document.
|
||||
let putCallCount = 0;
|
||||
|
||||
globalThis.fetch = async (_input, init) => {
|
||||
const method = init?.method ?? "GET";
|
||||
if (method === "PUT") {
|
||||
putCallCount += 1;
|
||||
if (putCallCount === 1) {
|
||||
// First PUT: validation failure — resource is unchanged
|
||||
return jsonResponse({
|
||||
detail: {
|
||||
code: "invalid_markdown_frontmatter",
|
||||
message: "Markdown frontmatter contains invalid YAML.",
|
||||
},
|
||||
}, 422);
|
||||
}
|
||||
// Second PUT: success with the corrected Markdown
|
||||
const body = JSON.parse(String(init?.body ?? "{}")) as { markdown: string };
|
||||
const correctedBody = body.markdown.includes("Corrected") ? "Corrected body" : "body";
|
||||
return jsonResponse({
|
||||
resource,
|
||||
source: originalSource.replace("Original", "Corrected"),
|
||||
body: correctedBody,
|
||||
revision: "sha256:after-retry",
|
||||
editable: true,
|
||||
changed: true,
|
||||
});
|
||||
}
|
||||
return jsonResponse({
|
||||
resource,
|
||||
source: originalSource,
|
||||
body: "Original",
|
||||
revision: "sha256:original",
|
||||
editable: true,
|
||||
});
|
||||
};
|
||||
|
||||
let appliedRevision = "";
|
||||
const view = render(
|
||||
<MarkdownContentViewer
|
||||
content="Original"
|
||||
resource={resource}
|
||||
onApplied={(result) => { appliedRevision = result.revision; }}
|
||||
/>,
|
||||
);
|
||||
|
||||
// Enter edit mode
|
||||
fireEvent.click(view.getByRole("button", { name: "Edit" }));
|
||||
const textarea = await view.findByRole("textbox", { name: "Markdown source" });
|
||||
|
||||
// First attempt: create an invalid draft
|
||||
const invalidDraft = "---\nid: [\n---\n\nInvalid body";
|
||||
fireEvent.input(textarea, { target: { value: invalidDraft } });
|
||||
fireEvent.click(view.getByRole("button", { name: "Apply" }));
|
||||
|
||||
// 422 error appears, draft is preserved
|
||||
const alert = await view.findByRole("alert");
|
||||
assert.match(alert.textContent ?? "", /invalid YAML/i);
|
||||
assert.equal(
|
||||
(view.getByRole("textbox", { name: "Markdown source" }) as HTMLTextAreaElement).value,
|
||||
invalidDraft,
|
||||
"invalid draft must be preserved after 422",
|
||||
);
|
||||
|
||||
// Correct the draft
|
||||
const correctedDraft = originalSource.replace("Original", "Corrected");
|
||||
fireEvent.input(view.getByRole("textbox", { name: "Markdown source" }), {
|
||||
target: { value: correctedDraft },
|
||||
});
|
||||
|
||||
// Apply is re-enabled (still dirty)
|
||||
const applyButton = view.getByRole("button", { name: "Apply" });
|
||||
assert.equal(
|
||||
(applyButton as HTMLButtonElement).disabled,
|
||||
false,
|
||||
"Apply must be re-enabled after correcting the draft",
|
||||
);
|
||||
|
||||
// Second attempt: apply corrected draft
|
||||
fireEvent.click(applyButton);
|
||||
|
||||
// Must succeed — server returns new revision
|
||||
await waitFor(() => assert.equal(appliedRevision, "sha256:after-retry"));
|
||||
|
||||
// Editor returns to preview mode after successful save
|
||||
assert.equal(
|
||||
view.getByRole("tab", { name: "Preview" }).getAttribute("aria-selected"),
|
||||
"true",
|
||||
"editor must return to preview after successful retry",
|
||||
);
|
||||
|
||||
// Error is cleared
|
||||
assert.equal(view.queryByRole("alert"), null, "error banner must be cleared after success");
|
||||
|
||||
// Both PUT attempts were made — retry used original revision (no extra GET between attempts)
|
||||
assert.equal(putCallCount, 2, "exactly two PUT requests must be made (failed + successful retry)");
|
||||
});
|
||||
@@ -1,132 +0,0 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import {
|
||||
cancelEdit,
|
||||
createEditSession,
|
||||
createLoadingSession,
|
||||
isDirty,
|
||||
saveFailed,
|
||||
saveStarted,
|
||||
saveSucceeded,
|
||||
shouldConfirmDiscard,
|
||||
updateDraft,
|
||||
} from "../src/workspaces/GraphWorkspace/markdownEditorState.ts";
|
||||
|
||||
const resource = { kind: "context-node" as const, id: "node-1" };
|
||||
|
||||
|
||||
test("enters loading and editing with the canonical source", () => {
|
||||
const loading = createLoadingSession(resource);
|
||||
const editing = createEditSession(resource, {
|
||||
source: "---\nid: node-1\n---\n\nBody",
|
||||
revision: "sha256:one",
|
||||
});
|
||||
|
||||
assert.equal(loading.status, "loading-document");
|
||||
assert.equal(editing.status, "editing");
|
||||
assert.equal(editing.draft, editing.baseSource);
|
||||
assert.equal(isDirty(editing), false);
|
||||
});
|
||||
|
||||
|
||||
test("draft changes derive dirty state and clear prior errors", () => {
|
||||
const session = createEditSession(resource, {
|
||||
source: "base",
|
||||
revision: "sha256:one",
|
||||
});
|
||||
const failed = saveFailed(session, {
|
||||
kind: "validation",
|
||||
message: "Invalid",
|
||||
});
|
||||
const edited = updateDraft(failed, "draft");
|
||||
|
||||
assert.equal(edited.status, "editing");
|
||||
assert.equal(edited.error, null);
|
||||
assert.equal(isDirty(edited), true);
|
||||
assert.equal(shouldConfirmDiscard(edited), true);
|
||||
});
|
||||
|
||||
|
||||
test("cancel discards the edit session without saving", () => {
|
||||
const session = updateDraft(
|
||||
createEditSession(resource, { source: "base", revision: "sha256:one" }),
|
||||
"draft",
|
||||
);
|
||||
|
||||
assert.equal(isDirty(session), true);
|
||||
assert.equal(cancelEdit(), null);
|
||||
});
|
||||
|
||||
|
||||
test("no-op save never enters saving state", () => {
|
||||
const session = createEditSession(resource, {
|
||||
source: "base",
|
||||
revision: "sha256:one",
|
||||
});
|
||||
|
||||
assert.equal(saveStarted(session), session);
|
||||
assert.equal(isDirty(session), false);
|
||||
});
|
||||
|
||||
|
||||
test("save success replaces the base source and revision", () => {
|
||||
const session = saveStarted(
|
||||
updateDraft(
|
||||
createEditSession(resource, { source: "base", revision: "sha256:one" }),
|
||||
"draft",
|
||||
),
|
||||
);
|
||||
const saved = saveSucceeded(session, {
|
||||
source: "canonical saved",
|
||||
revision: "sha256:two",
|
||||
});
|
||||
|
||||
assert.equal(saved.status, "viewing");
|
||||
assert.equal(saved.baseSource, "canonical saved");
|
||||
assert.equal(saved.draft, "canonical saved");
|
||||
assert.equal(saved.baseRevision, "sha256:two");
|
||||
assert.equal(isDirty(saved), false);
|
||||
});
|
||||
|
||||
|
||||
test("validation, conflict, and save failures retain the draft for retry", () => {
|
||||
const draft = updateDraft(
|
||||
createEditSession(resource, { source: "base", revision: "sha256:one" }),
|
||||
"draft",
|
||||
);
|
||||
|
||||
const validation = saveFailed(draft, {
|
||||
kind: "validation",
|
||||
message: "Invalid",
|
||||
});
|
||||
const conflict = saveFailed(draft, {
|
||||
kind: "conflict",
|
||||
message: "Stale",
|
||||
currentRevision: "sha256:two",
|
||||
});
|
||||
const network = saveFailed(draft, {
|
||||
kind: "network",
|
||||
message: "Offline",
|
||||
});
|
||||
|
||||
assert.equal(validation.status, "validation-error");
|
||||
assert.equal(conflict.status, "conflict");
|
||||
assert.equal(network.status, "save-error");
|
||||
assert.equal(validation.draft, "draft");
|
||||
assert.equal(conflict.draft, "draft");
|
||||
assert.equal(network.draft, "draft");
|
||||
assert.equal(saveStarted(network).status, "saving");
|
||||
});
|
||||
|
||||
|
||||
test("saving sessions do not allow a competing discard confirmation", () => {
|
||||
const saving = saveStarted(
|
||||
updateDraft(
|
||||
createEditSession(resource, { source: "base", revision: "sha256:one" }),
|
||||
"draft",
|
||||
),
|
||||
);
|
||||
|
||||
assert.equal(shouldConfirmDiscard(saving), false);
|
||||
});
|
||||
@@ -1,91 +0,0 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import {
|
||||
NodeMarkdownRefreshGuard,
|
||||
buildNodeMarkdownAttributeUpdate,
|
||||
readNodeMarkdownAttributeUpdate,
|
||||
} from "../src/workspaces/GraphWorkspace/nodeMarkdownSync.ts";
|
||||
|
||||
|
||||
test("saved Markdown updates graph content and its visible label", () => {
|
||||
const update = buildNodeMarkdownAttributeUpdate(
|
||||
"issue-1327",
|
||||
"# Issue 1328888\n\nUpdated body",
|
||||
{ status: "implemented" },
|
||||
);
|
||||
|
||||
assert.equal(update.content, "# Issue 1328888\n\nUpdated body");
|
||||
assert.equal(update.label, "# Issue 1328888\n\nUpdated body");
|
||||
assert.deepEqual(update.properties, {
|
||||
status: "implemented",
|
||||
content: "# Issue 1328888\n\nUpdated body",
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
test("empty Markdown falls back to the stable node id label", () => {
|
||||
const update = buildNodeMarkdownAttributeUpdate("issue-1327", "", {});
|
||||
|
||||
assert.equal(update.label, "issue-1327");
|
||||
assert.equal(update.content, "");
|
||||
});
|
||||
|
||||
|
||||
test("saved frontmatter is refreshed from the canonical graph node", async () => {
|
||||
const update = await readNodeMarkdownAttributeUpdate(
|
||||
"node/1",
|
||||
async (input) => {
|
||||
assert.equal(String(input), "/api/graph/node?node_id=node%2F1");
|
||||
return new Response(JSON.stringify({
|
||||
id: "node/1",
|
||||
type: "Decision",
|
||||
content: "Updated body",
|
||||
properties: {
|
||||
content: "Updated body",
|
||||
status: "accepted",
|
||||
valid_from: "2026-09-01T00:00:00Z",
|
||||
},
|
||||
valid_from: "2026-09-01T00:00:00Z",
|
||||
valid_until: null,
|
||||
}), {
|
||||
status: 200,
|
||||
headers: { "Content-Type": "application/json" },
|
||||
});
|
||||
},
|
||||
);
|
||||
assert.deepEqual(update, {
|
||||
label: "Updated body",
|
||||
content: "Updated body",
|
||||
properties: {
|
||||
content: "Updated body",
|
||||
status: "accepted",
|
||||
valid_from: "2026-09-01T00:00:00Z",
|
||||
},
|
||||
nodeType: "Decision",
|
||||
valid_from: "2026-09-01T00:00:00Z",
|
||||
valid_until: null,
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
test("realtime updates invalidate an older local-save refresh", () => {
|
||||
const guard = new NodeMarkdownRefreshGuard();
|
||||
const localSaveRefresh = guard.begin("node-1");
|
||||
|
||||
guard.invalidate("node-1");
|
||||
|
||||
assert.equal(guard.isCurrent("node-1", localSaveRefresh), false);
|
||||
});
|
||||
|
||||
|
||||
test("refresh invalidation is scoped to one node", () => {
|
||||
const guard = new NodeMarkdownRefreshGuard();
|
||||
const firstNodeRefresh = guard.begin("node-1");
|
||||
const secondNodeRefresh = guard.begin("node-2");
|
||||
|
||||
guard.invalidate("node-1");
|
||||
|
||||
assert.equal(guard.isCurrent("node-1", firstNodeRefresh), false);
|
||||
assert.equal(guard.isCurrent("node-2", secondNodeRefresh), true);
|
||||
});
|
||||
@@ -1,66 +0,0 @@
|
||||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import {
|
||||
classifyNodeType,
|
||||
compactNodeType,
|
||||
inferOntologyUri,
|
||||
isEditableEntityType,
|
||||
ONTOLOGY_MINIMAP_THEME,
|
||||
} from "../src/workspaces/OntologyWorkspace/ontologyEditorModel";
|
||||
|
||||
const registry = [
|
||||
{ uri: "https://example.test/foo", name: "Foo" },
|
||||
{ uri: "https://example.test/foo/nested", name: "Nested" },
|
||||
];
|
||||
|
||||
test("ontology inference requires a URI delimiter and prefers the closest namespace", () => {
|
||||
assert.equal(inferOntologyUri(registry, "https://example.test/foobar/Class"), undefined);
|
||||
assert.equal(
|
||||
inferOntologyUri(registry, "https://example.test/foo/nested#Class"),
|
||||
"https://example.test/foo/nested",
|
||||
);
|
||||
});
|
||||
|
||||
test("explicit scheme ownership wins when an entity uses another namespace", () => {
|
||||
assert.equal(
|
||||
inferOntologyUri(registry, "https://vocabulary.test/Class", "https://example.test/foo"),
|
||||
"https://example.test/foo",
|
||||
);
|
||||
});
|
||||
|
||||
test("only draft-supported class and property nodes are editable", () => {
|
||||
assert.equal(isEditableEntityType("class"), true);
|
||||
assert.equal(isEditableEntityType("property"), true);
|
||||
assert.equal(isEditableEntityType("ontology"), false);
|
||||
assert.equal(isEditableEntityType("external"), false);
|
||||
});
|
||||
|
||||
test("the ontology minimap has an explicit dark, high-contrast theme", () => {
|
||||
assert.equal(ONTOLOGY_MINIMAP_THEME.bgColor, "#0b1625");
|
||||
assert.equal(ONTOLOGY_MINIMAP_THEME.maskStrokeColor, "#5faeff");
|
||||
assert.equal(ONTOLOGY_MINIMAP_THEME.nodeStrokeColor, "#9acbff");
|
||||
assert.match(ONTOLOGY_MINIMAP_THEME.style.border, /#29435c/);
|
||||
});
|
||||
|
||||
test("node types classify identically in compact and full IRI form", () => {
|
||||
const cases: Array<[string, string, string]> = [
|
||||
["owl:Ontology", "http://www.w3.org/2002/07/owl#Ontology", "ontology"],
|
||||
["owl:Class", "http://www.w3.org/2002/07/owl#Class", "class"],
|
||||
["rdfs:Class", "http://www.w3.org/2000/01/rdf-schema#Class", "class"],
|
||||
["owl:ObjectProperty", "http://www.w3.org/2002/07/owl#ObjectProperty", "property"],
|
||||
["owl:DatatypeProperty", "http://www.w3.org/2002/07/owl#DatatypeProperty", "property"],
|
||||
["owl:AnnotationProperty", "http://www.w3.org/2002/07/owl#AnnotationProperty", "property"],
|
||||
];
|
||||
for (const [compact, fullIri, expected] of cases) {
|
||||
assert.equal(classifyNodeType(compact), expected, compact);
|
||||
assert.equal(classifyNodeType(fullIri), expected, fullIri);
|
||||
}
|
||||
assert.equal(classifyNodeType("owl:NamedIndividual"), "external");
|
||||
assert.equal(classifyNodeType("http://www.w3.org/2004/02/skos/core#Concept"), "external");
|
||||
});
|
||||
|
||||
test("compactNodeType leaves unknown namespaces untouched", () => {
|
||||
assert.equal(compactNodeType("https://example.org/custom#Thing"), "https://example.org/custom#Thing");
|
||||
assert.equal(compactNodeType("owl:Class"), "owl:Class");
|
||||
});
|
||||
@@ -1,270 +0,0 @@
|
||||
# Semantica Google ADK Integration
|
||||
|
||||
Google ADK integration for [Semantica](https://github.com/semantica-agi/semantica).
|
||||
|
||||
This integration provides:
|
||||
|
||||
- Google ADK `FunctionTool` wrappers for Semantica's knowledge graph
|
||||
- Decision recording and querying tools
|
||||
- A graph-backed Google ADK `BaseSessionService`
|
||||
- Shared `ContextGraph` state across ADK agents and sub-agents
|
||||
|
||||
Google ADK is an optional dependency.
|
||||
|
||||
## Installation
|
||||
|
||||
Install Semantica with the Google ADK integration:
|
||||
|
||||
```bash
|
||||
pip install semantica[google-adk]
|
||||
```
|
||||
|
||||
Or install Google ADK separately:
|
||||
|
||||
```bash
|
||||
pip install google-adk
|
||||
```
|
||||
|
||||
## Knowledge Graph Tools
|
||||
|
||||
Create a shared `ContextGraph` and expose it through ADK tools:
|
||||
|
||||
```python
|
||||
from google.adk.agents import Agent
|
||||
|
||||
from semantica.context import ContextGraph
|
||||
from integrations.google_adk import semantica_kg_tools
|
||||
|
||||
|
||||
graph = ContextGraph()
|
||||
|
||||
agent = Agent(
|
||||
name="researcher",
|
||||
model="gemini-2.0-flash",
|
||||
tools=semantica_kg_tools(graph),
|
||||
)
|
||||
```
|
||||
|
||||
The tool factory provides:
|
||||
|
||||
- `extract_entities`
|
||||
- `extract_relations`
|
||||
- `add_to_shared_graph`
|
||||
- `query_shared_graph`
|
||||
|
||||
The graph passed to `semantica_kg_tools()` is shared by all returned tools.
|
||||
|
||||
## Decision Tools
|
||||
|
||||
Decision intelligence can use the same graph:
|
||||
|
||||
```python
|
||||
from integrations.google_adk import semantica_decision_tools
|
||||
|
||||
decision_tools = semantica_decision_tools(graph)
|
||||
|
||||
agent = Agent(
|
||||
name="decision_agent",
|
||||
model="gemini-2.0-flash",
|
||||
tools=decision_tools,
|
||||
)
|
||||
```
|
||||
|
||||
The returned tools provide:
|
||||
|
||||
- `record_shared_decision`
|
||||
- `query_shared_decisions`
|
||||
|
||||
This allows decisions made by one agent to be queried later by another agent using the same `ContextGraph`.
|
||||
|
||||
## Combining Knowledge and Decision Tools
|
||||
|
||||
Both tool groups can be supplied to the same ADK agent:
|
||||
|
||||
```python
|
||||
from google.adk.agents import Agent
|
||||
|
||||
from semantica.context import ContextGraph
|
||||
from integrations.google_adk import (
|
||||
semantica_kg_tools,
|
||||
semantica_decision_tools,
|
||||
)
|
||||
|
||||
|
||||
graph = ContextGraph()
|
||||
|
||||
tools = (
|
||||
semantica_kg_tools(graph)
|
||||
+ semantica_decision_tools(graph)
|
||||
)
|
||||
|
||||
agent = Agent(
|
||||
name="researcher",
|
||||
model="gemini-2.0-flash",
|
||||
tools=tools,
|
||||
)
|
||||
```
|
||||
|
||||
This gives the agent access to both the shared knowledge graph and decision history.
|
||||
|
||||
## Graph-Backed Session Service
|
||||
|
||||
`SemanticaSessionService` implements Google ADK's session service interface while storing session information in a Semantica `ContextGraph`.
|
||||
|
||||
```python
|
||||
from semantica.context import ContextGraph
|
||||
from integrations.google_adk import SemanticaSessionService
|
||||
|
||||
|
||||
graph = ContextGraph()
|
||||
|
||||
session_service = SemanticaSessionService(graph)
|
||||
```
|
||||
|
||||
The same graph can be shared with the KG and decision tools:
|
||||
|
||||
```python
|
||||
from google.adk.agents import Agent
|
||||
|
||||
from semantica.context import ContextGraph
|
||||
from integrations.google_adk import (
|
||||
SemanticaSessionService,
|
||||
semantica_kg_tools,
|
||||
semantica_decision_tools,
|
||||
)
|
||||
|
||||
|
||||
graph = ContextGraph()
|
||||
|
||||
session_service = SemanticaSessionService(graph)
|
||||
|
||||
tools = (
|
||||
semantica_kg_tools(graph)
|
||||
+ semantica_decision_tools(graph)
|
||||
)
|
||||
|
||||
agent = Agent(
|
||||
name="researcher",
|
||||
model="gemini-2.0-flash",
|
||||
tools=tools,
|
||||
)
|
||||
```
|
||||
|
||||
Session information and tool-generated knowledge can therefore share the same graph-backed context store.
|
||||
|
||||
## Optional Dependency
|
||||
|
||||
Importing the integration does not require Google ADK to be installed:
|
||||
|
||||
```python
|
||||
from integrations.google_adk import ADK_AVAILABLE
|
||||
|
||||
print(ADK_AVAILABLE)
|
||||
```
|
||||
|
||||
If Google ADK is unavailable, attempting to construct ADK-specific tools or the session service raises an informative `ImportError`.
|
||||
|
||||
## Shared ContextGraph
|
||||
|
||||
A major purpose of this integration is allowing multiple ADK agents or sub-agents to share one Semantica graph:
|
||||
|
||||
```text
|
||||
ContextGraph
|
||||
|
|
||||
+--------------+--------------+
|
||||
| | |
|
||||
Researcher Planner Reviewer
|
||||
Agent Agent Agent
|
||||
| | |
|
||||
+--------------+--------------+
|
||||
|
|
||||
Shared knowledge
|
||||
+ decisions
|
||||
+ session state
|
||||
```
|
||||
|
||||
This makes information extracted during an earlier stage of an agent workflow available to later stages without requiring the information to be extracted again.
|
||||
|
||||
## Example Workflow
|
||||
|
||||
```python
|
||||
from google.adk.agents import SequentialAgent, Agent
|
||||
|
||||
from semantica.context import ContextGraph
|
||||
from integrations.google_adk import (
|
||||
semantica_kg_tools,
|
||||
semantica_decision_tools,
|
||||
)
|
||||
|
||||
|
||||
graph = ContextGraph()
|
||||
|
||||
researcher = Agent(
|
||||
name="researcher",
|
||||
model="gemini-2.0-flash",
|
||||
tools=semantica_kg_tools(graph),
|
||||
)
|
||||
|
||||
planner = Agent(
|
||||
name="planner",
|
||||
model="gemini-2.0-flash",
|
||||
tools=(
|
||||
semantica_kg_tools(graph)
|
||||
+ semantica_decision_tools(graph)
|
||||
),
|
||||
)
|
||||
|
||||
workflow = SequentialAgent(
|
||||
name="research_workflow",
|
||||
sub_agents=[
|
||||
researcher,
|
||||
planner,
|
||||
],
|
||||
)
|
||||
```
|
||||
|
||||
The researcher can add entities and relationships to the graph. The planner can then query the same graph and record decisions against it.
|
||||
|
||||
## API
|
||||
|
||||
### `semantica_kg_tools(graph=None)`
|
||||
|
||||
Returns Google ADK `FunctionTool` instances for Semantica knowledge graph operations.
|
||||
|
||||
### `semantica_decision_tools(graph=None)`
|
||||
|
||||
Returns Google ADK `FunctionTool` instances for recording and querying decisions.
|
||||
|
||||
### `SemanticaSessionService(graph=None)`
|
||||
|
||||
Creates a Google ADK-compatible session service backed by a Semantica `ContextGraph`.
|
||||
|
||||
### `ADK_AVAILABLE`
|
||||
|
||||
Boolean indicating whether Google ADK is installed.
|
||||
|
||||
### `__version__`
|
||||
|
||||
Version of the Semantica Google ADK integration.
|
||||
|
||||
## Development
|
||||
|
||||
Run the Google ADK integration tests with:
|
||||
|
||||
```bash
|
||||
pytest tests/integrations/google_adk -v
|
||||
```
|
||||
|
||||
Tests that require Google ADK should use:
|
||||
|
||||
```python
|
||||
import pytest
|
||||
|
||||
pytest.importorskip("google.adk")
|
||||
```
|
||||
|
||||
This keeps the integration optional for environments that do not install Google ADK.
|
||||
|
||||
## License
|
||||
|
||||
This integration follows the license of the Semantica project.
|
||||
@@ -1,50 +0,0 @@
|
||||
"""
|
||||
Google ADK integration for Semantica.
|
||||
|
||||
Google ADK is an optional dependency. The integration can be imported
|
||||
without google-adk installed, but ADK-specific functionality requires it.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
try:
|
||||
import google.adk # noqa: F401
|
||||
|
||||
ADK_AVAILABLE = True
|
||||
except ImportError:
|
||||
ADK_AVAILABLE = False
|
||||
|
||||
|
||||
from .kg_tools import (
|
||||
extract_entities,
|
||||
extract_relations,
|
||||
add_to_graph,
|
||||
query_graph,
|
||||
semantica_kg_tools,
|
||||
)
|
||||
|
||||
from .decision_tools import (
|
||||
record_decision,
|
||||
query_decisions,
|
||||
semantica_decision_tools,
|
||||
)
|
||||
|
||||
from .session_service import SemanticaSessionService
|
||||
|
||||
|
||||
__version__ = "0.1.0"
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ADK_AVAILABLE",
|
||||
"__version__",
|
||||
"extract_entities",
|
||||
"extract_relations",
|
||||
"add_to_graph",
|
||||
"query_graph",
|
||||
"semantica_kg_tools",
|
||||
"record_decision",
|
||||
"query_decisions",
|
||||
"semantica_decision_tools",
|
||||
"SemanticaSessionService",
|
||||
]
|
||||
@@ -1,45 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import threading
|
||||
from typing import Any, Dict
|
||||
|
||||
# Shared between kg_tools.py and decision_tools.py so that a ContextGraph
|
||||
# passed to both semantica_kg_tools() and semantica_decision_tools() (the
|
||||
# combined-tools use case documented in the README) is locked and defaulted
|
||||
# consistently across both tool sets rather than each module keeping its
|
||||
# own independent registry.
|
||||
|
||||
_graph_locks_guard = threading.Lock()
|
||||
_graph_locks: Dict[int, threading.RLock] = {}
|
||||
|
||||
|
||||
def graph_lock(graph: Any) -> threading.RLock:
|
||||
"""Return the mutation lock associated with a ContextGraph instance."""
|
||||
key = id(graph)
|
||||
|
||||
with _graph_locks_guard:
|
||||
lock = _graph_locks.get(key)
|
||||
|
||||
if lock is None:
|
||||
lock = threading.RLock()
|
||||
_graph_locks[key] = lock
|
||||
|
||||
return lock
|
||||
|
||||
|
||||
_default_graph: Any = None
|
||||
_default_graph_lock = threading.Lock()
|
||||
|
||||
|
||||
def get_default_graph() -> Any:
|
||||
"""Create or return the cached process-local default ContextGraph."""
|
||||
global _default_graph
|
||||
|
||||
if _default_graph is None:
|
||||
with _default_graph_lock:
|
||||
if _default_graph is None:
|
||||
from semantica.context import ContextGraph
|
||||
|
||||
_default_graph = ContextGraph()
|
||||
|
||||
return _default_graph
|
||||
@@ -1,305 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime
|
||||
from typing import Any, List, Optional
|
||||
import uuid
|
||||
|
||||
from ._shared import graph_lock as _graph_lock
|
||||
from ._shared import get_default_graph as _get_default_graph
|
||||
|
||||
|
||||
try:
|
||||
from google.adk.tools import FunctionTool
|
||||
|
||||
ADK_AVAILABLE = True
|
||||
except ImportError:
|
||||
FunctionTool = None
|
||||
ADK_AVAILABLE = False
|
||||
|
||||
|
||||
def _get_decision_models() -> Any:
|
||||
"""Import Semantica decision models lazily."""
|
||||
from semantica.context.decision_models import Decision
|
||||
|
||||
return Decision
|
||||
|
||||
|
||||
def _get_decision_recorder(graph: Any) -> Any:
|
||||
"""Create a DecisionRecorder backed by the supplied graph."""
|
||||
from semantica.context import DecisionRecorder
|
||||
|
||||
return DecisionRecorder(graph_store=graph)
|
||||
|
||||
|
||||
def _decision_to_dict(decision: Any) -> dict:
|
||||
"""Convert a Semantica Decision model into a serializable dictionary."""
|
||||
if hasattr(decision, "model_dump"):
|
||||
return decision.model_dump()
|
||||
|
||||
if hasattr(decision, "dict"):
|
||||
return decision.dict()
|
||||
|
||||
if isinstance(decision, dict):
|
||||
return decision
|
||||
|
||||
return {
|
||||
key: value
|
||||
for key, value in vars(decision).items()
|
||||
if not key.startswith("_")
|
||||
}
|
||||
|
||||
|
||||
def record_decision(
|
||||
category: str,
|
||||
scenario: str,
|
||||
reasoning: str,
|
||||
outcome: str,
|
||||
confidence: float = 1.0,
|
||||
decision_maker: str = "agent",
|
||||
entities: Optional[List[str]] = None,
|
||||
source_documents: Optional[List[str]] = None,
|
||||
) -> dict:
|
||||
"""
|
||||
Record a decision using Semantica's DecisionRecorder.
|
||||
|
||||
Args:
|
||||
category: Decision category such as "research", "planning", or
|
||||
"approval".
|
||||
scenario: Situation in which the decision was made.
|
||||
reasoning: Explanation for the decision.
|
||||
outcome: Result or selected action.
|
||||
confidence: Confidence score between 0 and 1.
|
||||
decision_maker: Agent, user, or system responsible for the decision.
|
||||
entities: Optional entity IDs related to the decision.
|
||||
source_documents: Optional source document IDs supporting the decision.
|
||||
|
||||
Returns:
|
||||
Dictionary containing the recorded decision ID and decision metadata.
|
||||
"""
|
||||
return _record_decision(
|
||||
category=category,
|
||||
scenario=scenario,
|
||||
reasoning=reasoning,
|
||||
outcome=outcome,
|
||||
confidence=confidence,
|
||||
decision_maker=decision_maker,
|
||||
entities=entities or [],
|
||||
source_documents=source_documents or [],
|
||||
graph=_get_default_graph(),
|
||||
)
|
||||
|
||||
|
||||
def _record_decision(
|
||||
category: str,
|
||||
scenario: str,
|
||||
reasoning: str,
|
||||
outcome: str,
|
||||
confidence: float,
|
||||
decision_maker: str,
|
||||
entities: List[str],
|
||||
source_documents: List[str],
|
||||
graph: Any,
|
||||
) -> dict:
|
||||
"""Internal implementation of decision recording."""
|
||||
try:
|
||||
confidence = max(0.0, min(1.0, float(confidence)))
|
||||
|
||||
Decision = _get_decision_models()
|
||||
|
||||
decision = Decision(
|
||||
decision_id=str(uuid.uuid4()),
|
||||
category=category,
|
||||
scenario=scenario,
|
||||
reasoning=reasoning,
|
||||
outcome=outcome,
|
||||
confidence=confidence,
|
||||
decision_maker=decision_maker,
|
||||
timestamp=datetime.now(),
|
||||
)
|
||||
|
||||
recorder = _get_decision_recorder(graph)
|
||||
|
||||
with _graph_lock(graph):
|
||||
decision_id = recorder.record_decision(
|
||||
decision=decision,
|
||||
entities=entities,
|
||||
source_documents=source_documents,
|
||||
)
|
||||
|
||||
return {
|
||||
"decision_id": decision_id,
|
||||
"category": category,
|
||||
"scenario": scenario,
|
||||
"outcome": outcome,
|
||||
"confidence": confidence,
|
||||
"decision_maker": decision_maker,
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
return {
|
||||
"decision_id": "",
|
||||
"error": str(exc),
|
||||
}
|
||||
|
||||
|
||||
def query_decisions(query: str) -> dict:
|
||||
"""
|
||||
Query previously recorded decisions by keyword.
|
||||
"""
|
||||
return _query_decisions(query, _get_default_graph())
|
||||
|
||||
def _query_decisions(query: str, graph: Any) -> dict:
|
||||
"""Internal decision query implementation."""
|
||||
if not isinstance(query, str):
|
||||
return {
|
||||
"query": query,
|
||||
"decisions": [],
|
||||
"count": 0,
|
||||
"error": "query must be a string",
|
||||
}
|
||||
|
||||
query = query.strip()
|
||||
|
||||
if not query:
|
||||
return {
|
||||
"query": query,
|
||||
"decisions": [],
|
||||
"count": 0,
|
||||
}
|
||||
|
||||
try:
|
||||
query_lower = query.lower()
|
||||
decisions = []
|
||||
seen = set()
|
||||
|
||||
for node in graph.find_nodes() or []:
|
||||
if not isinstance(node, dict):
|
||||
continue
|
||||
|
||||
node_type = node.get("type")
|
||||
|
||||
if str(node_type).lower() != "decision":
|
||||
continue
|
||||
|
||||
node_id = str(node.get("id") or "")
|
||||
|
||||
if not node_id or node_id in seen:
|
||||
continue
|
||||
|
||||
metadata = node.get("metadata") or {}
|
||||
|
||||
category = metadata.get("category", "")
|
||||
scenario = metadata.get("scenario", "")
|
||||
reasoning = metadata.get("reasoning", "")
|
||||
outcome = metadata.get("outcome", "")
|
||||
decision_maker = metadata.get("decision_maker", "")
|
||||
|
||||
searchable = " ".join(
|
||||
str(value or "")
|
||||
for value in (
|
||||
node_id,
|
||||
category,
|
||||
scenario,
|
||||
reasoning,
|
||||
outcome,
|
||||
decision_maker,
|
||||
)
|
||||
).lower()
|
||||
|
||||
if query_lower not in searchable:
|
||||
continue
|
||||
|
||||
seen.add(node_id)
|
||||
|
||||
decisions.append(
|
||||
{
|
||||
"decision_id": node_id,
|
||||
"category": str(category or ""),
|
||||
"scenario": str(scenario or ""),
|
||||
"reasoning": str(reasoning or "")[:1000],
|
||||
"outcome": str(outcome or ""),
|
||||
"decision_maker": str(
|
||||
decision_maker or ""
|
||||
),
|
||||
}
|
||||
)
|
||||
|
||||
return {
|
||||
"query": query,
|
||||
"decisions": decisions,
|
||||
"count": len(decisions),
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
return {
|
||||
"query": query,
|
||||
"decisions": [],
|
||||
"count": 0,
|
||||
"error": str(exc),
|
||||
}
|
||||
|
||||
def semantica_decision_tools(
|
||||
graph: Optional[Any] = None,
|
||||
) -> List[Any]:
|
||||
"""
|
||||
Return Google ADK FunctionTools bound to a shared ContextGraph.
|
||||
|
||||
Args:
|
||||
graph:
|
||||
Optional ContextGraph shared by the ADK agent and other
|
||||
Semantica tools.
|
||||
|
||||
Returns:
|
||||
ADK FunctionTools for recording and querying decisions.
|
||||
|
||||
Raises:
|
||||
ImportError:
|
||||
If google-adk is not installed.
|
||||
"""
|
||||
if not ADK_AVAILABLE or FunctionTool is None:
|
||||
raise ImportError(
|
||||
"Google ADK is required for semantica_decision_tools(). "
|
||||
"Install it with: pip install semantica[google-adk]"
|
||||
)
|
||||
|
||||
shared_graph = graph if graph is not None else _get_default_graph()
|
||||
|
||||
def record_shared_decision(
|
||||
category: str,
|
||||
scenario: str,
|
||||
reasoning: str,
|
||||
outcome: str,
|
||||
confidence: float = 1.0,
|
||||
decision_maker: str = "agent",
|
||||
entities: Optional[List[str]] = None,
|
||||
source_documents: Optional[List[str]] = None,
|
||||
) -> dict:
|
||||
"""Record a decision in the shared Semantica knowledge graph."""
|
||||
return _record_decision(
|
||||
category=category,
|
||||
scenario=scenario,
|
||||
reasoning=reasoning,
|
||||
outcome=outcome,
|
||||
confidence=confidence,
|
||||
decision_maker=decision_maker,
|
||||
entities=entities or [],
|
||||
source_documents=source_documents or [],
|
||||
graph=shared_graph,
|
||||
)
|
||||
|
||||
def query_shared_decisions(query: str) -> dict:
|
||||
"""Query decisions stored in the shared Semantica knowledge graph."""
|
||||
return _query_decisions(query, shared_graph)
|
||||
|
||||
return [
|
||||
FunctionTool(record_shared_decision),
|
||||
FunctionTool(query_shared_decisions),
|
||||
]
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ADK_AVAILABLE",
|
||||
"record_decision",
|
||||
"query_decisions",
|
||||
"semantica_decision_tools",
|
||||
]
|
||||
@@ -1,659 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from ._shared import graph_lock as _graph_lock
|
||||
from ._shared import get_default_graph as _get_default_graph
|
||||
|
||||
try:
|
||||
from google.adk.tools import FunctionTool
|
||||
|
||||
ADK_AVAILABLE = True
|
||||
except ImportError:
|
||||
FunctionTool = None # type: ignore
|
||||
ADK_AVAILABLE = False
|
||||
|
||||
|
||||
def _get_ner_extractor() -> Any:
|
||||
"""Create Semantica default NER extractor."""
|
||||
from semantica.semantic_extract import NERExtractor
|
||||
|
||||
return NERExtractor()
|
||||
|
||||
|
||||
def _get_relation_extractor() -> Any:
|
||||
"""Create Semantica default relation extractor."""
|
||||
from semantica.semantic_extract import RelationExtractor
|
||||
|
||||
return RelationExtractor()
|
||||
|
||||
|
||||
def _first_string(obj: Any, attributes: tuple[str, ...]) -> str:
|
||||
"""Return the first non-empty string from an object or dictionary."""
|
||||
if obj is None:
|
||||
return ""
|
||||
|
||||
if isinstance(obj, dict):
|
||||
for attribute in attributes:
|
||||
value = obj.get(attribute)
|
||||
|
||||
if isinstance(value, str) and value.strip():
|
||||
return value.strip()
|
||||
|
||||
return ""
|
||||
|
||||
for attribute in attributes:
|
||||
value = getattr(obj, attribute, None)
|
||||
|
||||
if isinstance(value, str) and value.strip():
|
||||
return value.strip()
|
||||
|
||||
return ""
|
||||
|
||||
|
||||
def _entity_name(entity: Any) -> str:
|
||||
"""Return a best-effort name for an extracted entity."""
|
||||
return _first_string(
|
||||
entity,
|
||||
(
|
||||
"name",
|
||||
"text",
|
||||
"label",
|
||||
"node_id",
|
||||
"id",
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def _entity_type(entity: Any) -> str:
|
||||
"""Return a best-effort type for an extracted entity."""
|
||||
return (
|
||||
_first_string(
|
||||
entity,
|
||||
(
|
||||
"type",
|
||||
"label",
|
||||
),
|
||||
)
|
||||
or "Entity"
|
||||
)
|
||||
|
||||
|
||||
def _entity_confidence(entity: Any) -> float:
|
||||
"""Normalize an entity confidence value."""
|
||||
try:
|
||||
confidence = (
|
||||
entity.get("confidence")
|
||||
if isinstance(entity, dict)
|
||||
else getattr(entity, "confidence", None)
|
||||
)
|
||||
|
||||
if confidence is None:
|
||||
return 1.0
|
||||
|
||||
return round(float(confidence), 4)
|
||||
|
||||
except (TypeError, ValueError):
|
||||
return 1.0
|
||||
|
||||
|
||||
def _relation_source(relation: Any) -> str:
|
||||
"""Return the source entity of an extracted relation."""
|
||||
source = _first_string(
|
||||
relation,
|
||||
(
|
||||
"source",
|
||||
"source_id",
|
||||
),
|
||||
)
|
||||
|
||||
if source:
|
||||
return source
|
||||
|
||||
if isinstance(relation, dict):
|
||||
return _entity_name(relation.get("subject"))
|
||||
|
||||
return _entity_name(getattr(relation, "subject", None))
|
||||
|
||||
|
||||
def _relation_target(relation: Any) -> str:
|
||||
"""Return the target entity of an extracted relation."""
|
||||
target = _first_string(
|
||||
relation,
|
||||
(
|
||||
"target",
|
||||
"target_id",
|
||||
),
|
||||
)
|
||||
|
||||
if target:
|
||||
return target
|
||||
|
||||
if isinstance(relation, dict):
|
||||
return _entity_name(relation.get("object"))
|
||||
|
||||
return _entity_name(getattr(relation, "object", None))
|
||||
|
||||
|
||||
def _relation_type(relation: Any) -> str:
|
||||
"""Return the relation predicate/type."""
|
||||
return (
|
||||
_first_string(
|
||||
relation,
|
||||
(
|
||||
"type",
|
||||
"relation",
|
||||
"predicate",
|
||||
),
|
||||
)
|
||||
or "related_to"
|
||||
)
|
||||
|
||||
|
||||
def _json_safe(value: Any) -> Any:
|
||||
"""
|
||||
Convert common Semantica objects into values suitable for ADK tool output.
|
||||
|
||||
ADK tools should return values that can be serialized into the tool
|
||||
response sent back to the model.
|
||||
"""
|
||||
if value is None or isinstance(value, (str, int, float, bool)):
|
||||
return value
|
||||
|
||||
if isinstance(value, dict):
|
||||
return {
|
||||
str(key): _json_safe(item)
|
||||
for key, item in value.items()
|
||||
}
|
||||
|
||||
if isinstance(value, (list, tuple, set)):
|
||||
return [_json_safe(item) for item in value]
|
||||
|
||||
if hasattr(value, "to_dict"):
|
||||
try:
|
||||
return _json_safe(value.to_dict())
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if hasattr(value, "model_dump"):
|
||||
try:
|
||||
return _json_safe(value.model_dump())
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return str(value)
|
||||
|
||||
|
||||
def extract_entities(text: str) -> dict:
|
||||
"""Extract named entities from text using Semantica's NER pipeline."""
|
||||
if not isinstance(text, str):
|
||||
return {
|
||||
"entities": [],
|
||||
"count": 0,
|
||||
"error": "text must be a string",
|
||||
}
|
||||
|
||||
try:
|
||||
extractor = _get_ner_extractor()
|
||||
raw_entities = extractor.extract_entities(text) or []
|
||||
|
||||
entities: List[Dict[str, Any]] = []
|
||||
|
||||
for entity in raw_entities:
|
||||
name = _entity_name(entity)
|
||||
|
||||
if not name:
|
||||
continue
|
||||
|
||||
entities.append(
|
||||
{
|
||||
"name": name,
|
||||
"type": _entity_type(entity),
|
||||
"confidence": _entity_confidence(entity),
|
||||
}
|
||||
)
|
||||
|
||||
return {
|
||||
"entities": entities,
|
||||
"count": len(entities),
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
return {
|
||||
"entities": [],
|
||||
"count": 0,
|
||||
"error": str(exc),
|
||||
}
|
||||
|
||||
|
||||
def extract_relations(text: str) -> dict:
|
||||
"""Extract relationships between entities from text using Semantica."""
|
||||
if not isinstance(text, str):
|
||||
return {
|
||||
"relations": [],
|
||||
"count": 0,
|
||||
"error": "text must be a string",
|
||||
}
|
||||
|
||||
try:
|
||||
ner_extractor = _get_ner_extractor()
|
||||
entities = ner_extractor.extract_entities(text)
|
||||
|
||||
relation_extractor = _get_relation_extractor()
|
||||
raw_relations = relation_extractor.extract_relations(text, entities=entities) or []
|
||||
|
||||
relations: List[Dict[str, Any]] = []
|
||||
|
||||
for relation in raw_relations:
|
||||
source = _relation_source(relation)
|
||||
target = _relation_target(relation)
|
||||
|
||||
if not source or not target:
|
||||
continue
|
||||
|
||||
relations.append(
|
||||
{
|
||||
"source": source,
|
||||
"relation": _relation_type(relation),
|
||||
"target": target,
|
||||
"confidence": _entity_confidence(relation),
|
||||
}
|
||||
)
|
||||
|
||||
return {
|
||||
"relations": relations,
|
||||
"count": len(relations),
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
return {
|
||||
"relations": [],
|
||||
"count": 0,
|
||||
"error": str(exc),
|
||||
}
|
||||
|
||||
|
||||
def add_to_graph(text: str) -> dict:
|
||||
"""
|
||||
Extract entities and relationships from text and add them to a ContextGraph.
|
||||
|
||||
This standalone function uses a process-local default graph. For a shared
|
||||
graph across ADK agents, use ``semantica_kg_tools(graph=shared_graph)``.
|
||||
"""
|
||||
return _add_to_graph(text, _get_default_graph())
|
||||
|
||||
|
||||
def query_graph(query: str) -> dict:
|
||||
"""
|
||||
Query the shared Semantica knowledge graph by keyword.
|
||||
|
||||
This standalone function uses a process-local default graph. For a shared
|
||||
graph, use ``semantica_kg_tools(graph=shared_graph)``.
|
||||
"""
|
||||
return _query_graph(query, _get_default_graph())
|
||||
|
||||
|
||||
def _add_to_graph(text: str, graph: Any) -> dict:
|
||||
"""Internal graph mutation implementation."""
|
||||
if not isinstance(text, str):
|
||||
return {
|
||||
"nodes_added": 0,
|
||||
"edges_added": 0,
|
||||
"error": "text must be a string",
|
||||
}
|
||||
|
||||
try:
|
||||
ner_extractor = _get_ner_extractor()
|
||||
relation_extractor = _get_relation_extractor()
|
||||
|
||||
nodes_added = 0
|
||||
edges_added = 0
|
||||
|
||||
with _graph_lock(graph):
|
||||
existing_nodes = set()
|
||||
|
||||
for node in graph.find_nodes() or []:
|
||||
if isinstance(node, dict):
|
||||
node_id = node.get("id") or node.get("node_id")
|
||||
else:
|
||||
node_id = getattr(
|
||||
node,
|
||||
"id",
|
||||
getattr(node, "node_id", None),
|
||||
)
|
||||
|
||||
if node_id:
|
||||
existing_nodes.add(str(node_id))
|
||||
|
||||
existing_edges = set()
|
||||
|
||||
for edge in graph.find_edges() or []:
|
||||
if isinstance(edge, dict):
|
||||
source = edge.get("source") or edge.get("source_id")
|
||||
target = edge.get("target") or edge.get("target_id")
|
||||
edge_type = edge.get("type") or edge.get("edge_type")
|
||||
else:
|
||||
source = getattr(
|
||||
edge,
|
||||
"source_id",
|
||||
getattr(edge, "source", None),
|
||||
)
|
||||
target = getattr(
|
||||
edge,
|
||||
"target_id",
|
||||
getattr(edge, "target", None),
|
||||
)
|
||||
edge_type = getattr(
|
||||
edge,
|
||||
"edge_type",
|
||||
getattr(edge, "type", None),
|
||||
)
|
||||
|
||||
if source and target:
|
||||
existing_edges.add(
|
||||
(
|
||||
str(source),
|
||||
str(edge_type or "related_to"),
|
||||
str(target),
|
||||
)
|
||||
)
|
||||
|
||||
raw_entities = ner_extractor.extract_entities(text) or []
|
||||
|
||||
entities: List[Any] = []
|
||||
seen_entities = set()
|
||||
|
||||
for entity in raw_entities:
|
||||
name = _entity_name(entity)
|
||||
entity_type = _entity_type(entity)
|
||||
|
||||
if not name or name in seen_entities:
|
||||
continue
|
||||
|
||||
seen_entities.add(name)
|
||||
entities.append(entity)
|
||||
|
||||
if name in existing_nodes:
|
||||
continue
|
||||
|
||||
try:
|
||||
added = graph.add_node(
|
||||
node_id=name,
|
||||
node_type=entity_type,
|
||||
)
|
||||
|
||||
if added:
|
||||
nodes_added += 1
|
||||
existing_nodes.add(name)
|
||||
|
||||
except Exception:
|
||||
# Do not fail the entire tool because one node could not
|
||||
# be inserted.
|
||||
continue
|
||||
|
||||
raw_relations = relation_extractor.extract_relations(
|
||||
text,
|
||||
entities=entities,
|
||||
) or []
|
||||
|
||||
for relation in raw_relations:
|
||||
source = _relation_source(relation)
|
||||
target = _relation_target(relation)
|
||||
relation_type = _relation_type(relation)
|
||||
|
||||
if not source or not target:
|
||||
continue
|
||||
|
||||
edge_key = (
|
||||
source,
|
||||
relation_type,
|
||||
target,
|
||||
)
|
||||
|
||||
if edge_key in existing_edges:
|
||||
continue
|
||||
|
||||
try:
|
||||
added = graph.add_edge(
|
||||
source_id=source,
|
||||
target_id=target,
|
||||
edge_type=relation_type,
|
||||
)
|
||||
|
||||
if added:
|
||||
edges_added += 1
|
||||
existing_edges.add(edge_key)
|
||||
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
return {
|
||||
"nodes_added": nodes_added,
|
||||
"edges_added": edges_added,
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
return {
|
||||
"nodes_added": 0,
|
||||
"edges_added": 0,
|
||||
"error": str(exc),
|
||||
}
|
||||
|
||||
|
||||
def _query_graph(query: str, graph: Any) -> dict:
|
||||
"""Internal graph query implementation."""
|
||||
if not isinstance(query, str):
|
||||
return {
|
||||
"query": query,
|
||||
"results": [],
|
||||
"count": 0,
|
||||
"error": "query must be a string",
|
||||
}
|
||||
|
||||
query = query.strip()
|
||||
|
||||
if not query:
|
||||
return {
|
||||
"query": query,
|
||||
"results": [],
|
||||
"count": 0,
|
||||
}
|
||||
|
||||
try:
|
||||
results: List[Dict[str, Any]] = []
|
||||
seen = set()
|
||||
|
||||
# Prefer ContextGraph.query() when available because it can provide
|
||||
# richer semantic/structural results.
|
||||
query_method = getattr(graph, "query", None)
|
||||
|
||||
if callable(query_method):
|
||||
try:
|
||||
matches = query_method(query) or []
|
||||
|
||||
for match in matches:
|
||||
if not isinstance(match, dict):
|
||||
continue
|
||||
|
||||
node = match.get("node") or {}
|
||||
|
||||
if not isinstance(node, dict):
|
||||
node = _json_safe(node)
|
||||
|
||||
node_id = (
|
||||
node.get("id")
|
||||
or node.get("node_id")
|
||||
or match.get("id")
|
||||
)
|
||||
|
||||
if not node_id:
|
||||
continue
|
||||
|
||||
node_id = str(node_id)
|
||||
|
||||
if node_id in seen:
|
||||
continue
|
||||
|
||||
seen.add(node_id)
|
||||
|
||||
results.append(
|
||||
{
|
||||
"id": node_id,
|
||||
"type": (
|
||||
node.get("type")
|
||||
or node.get("node_type")
|
||||
or ""
|
||||
),
|
||||
"content": str(
|
||||
match.get("content")
|
||||
or node.get("content")
|
||||
or (
|
||||
node.get("properties") or {}
|
||||
).get("content", "")
|
||||
)[:500],
|
||||
"score": round(
|
||||
float(match.get("score") or 0.0),
|
||||
4,
|
||||
),
|
||||
}
|
||||
)
|
||||
|
||||
except Exception:
|
||||
# Fall back to deterministic keyword search below.
|
||||
pass
|
||||
|
||||
# Deterministic fallback/search enrichment.
|
||||
query_lower = query.lower()
|
||||
|
||||
for node in graph.find_nodes() or []:
|
||||
if isinstance(node, dict):
|
||||
node_id = (
|
||||
node.get("id")
|
||||
or node.get("node_id")
|
||||
or ""
|
||||
)
|
||||
node_type = (
|
||||
node.get("type")
|
||||
or node.get("node_type")
|
||||
or ""
|
||||
)
|
||||
|
||||
properties = node.get("properties") or {}
|
||||
|
||||
content = (
|
||||
node.get("content")
|
||||
or properties.get("content")
|
||||
or ""
|
||||
)
|
||||
|
||||
else:
|
||||
node_id = getattr(
|
||||
node,
|
||||
"id",
|
||||
getattr(node, "node_id", ""),
|
||||
)
|
||||
node_type = getattr(
|
||||
node,
|
||||
"node_type",
|
||||
getattr(node, "type", ""),
|
||||
)
|
||||
content = getattr(node, "content", "")
|
||||
|
||||
node_id = str(node_id or "")
|
||||
node_type = str(node_type or "")
|
||||
content = str(content or "")
|
||||
|
||||
if not node_id or node_id in seen:
|
||||
continue
|
||||
|
||||
haystack = " ".join(
|
||||
(
|
||||
node_id,
|
||||
node_type,
|
||||
content,
|
||||
)
|
||||
).lower()
|
||||
|
||||
if query_lower in haystack:
|
||||
seen.add(node_id)
|
||||
|
||||
results.append(
|
||||
{
|
||||
"id": node_id,
|
||||
"type": node_type,
|
||||
"content": content[:500],
|
||||
"score": 1.0,
|
||||
}
|
||||
)
|
||||
|
||||
return {
|
||||
"query": query,
|
||||
"results": results,
|
||||
"count": len(results),
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
return {
|
||||
"query": query,
|
||||
"results": [],
|
||||
"count": 0,
|
||||
"error": str(exc),
|
||||
}
|
||||
|
||||
|
||||
def semantica_kg_tools(
|
||||
graph: Optional[Any] = None,
|
||||
) -> List[Any]:
|
||||
"""
|
||||
Return Google ADK FunctionTools bound to a shared ContextGraph instance.
|
||||
|
||||
Args:
|
||||
graph:
|
||||
Optional Semantica ContextGraph. When supplied, all returned tools
|
||||
operate on this same graph instance.
|
||||
|
||||
Returns:
|
||||
A list containing FunctionTools for:
|
||||
- extract_entities
|
||||
- extract_relations
|
||||
- add_to_graph
|
||||
- query_graph
|
||||
|
||||
Raises:
|
||||
ImportError:
|
||||
If google-adk is not installed.
|
||||
"""
|
||||
if not ADK_AVAILABLE or FunctionTool is None:
|
||||
raise ImportError(
|
||||
"Google ADK is required for semantica_kg_tools(). "
|
||||
"Install it with: pip install semantica[google-adk]"
|
||||
)
|
||||
|
||||
shared_graph = graph if graph is not None else _get_default_graph()
|
||||
|
||||
def add_to_shared_graph(text: str) -> dict:
|
||||
"""Extract entities and relationships from text and add them to the shared Semantica graph."""
|
||||
return _add_to_graph(text, shared_graph)
|
||||
|
||||
def query_shared_graph(query: str) -> dict:
|
||||
"""Query the shared Semantica knowledge graph by keyword."""
|
||||
return _query_graph(query, shared_graph)
|
||||
|
||||
# FunctionTool derives the tool name/schema from the wrapped callable and
|
||||
# its docstring, which is exactly the ADK convention we want.
|
||||
return [
|
||||
FunctionTool(extract_entities),
|
||||
FunctionTool(extract_relations),
|
||||
FunctionTool(add_to_shared_graph),
|
||||
FunctionTool(query_shared_graph),
|
||||
]
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ADK_AVAILABLE",
|
||||
"extract_entities",
|
||||
"extract_relations",
|
||||
"add_to_graph",
|
||||
"query_graph",
|
||||
"semantica_kg_tools",
|
||||
]
|
||||
@@ -1,646 +0,0 @@
|
||||
"""
|
||||
Semantica-backed Google ADK session service.
|
||||
|
||||
Session metadata, state, and event history are represented as nodes in a
|
||||
Semantica ContextGraph instead of being kept only in ADK's in-memory store.
|
||||
|
||||
Google ADK is an optional dependency.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import copy
|
||||
import inspect
|
||||
import threading
|
||||
import urllib.parse
|
||||
import uuid
|
||||
from datetime import datetime
|
||||
from typing import Any, List, Optional
|
||||
|
||||
try:
|
||||
from google.adk.events import Event
|
||||
from google.adk.sessions import BaseSessionService, Session
|
||||
try:
|
||||
from google.adk.sessions import ListSessionsResponse
|
||||
except ImportError:
|
||||
# Not every google-adk release re-exports ListSessionsResponse from
|
||||
# the sessions package __init__; it always lives in
|
||||
# base_session_service.
|
||||
from google.adk.sessions.base_session_service import ListSessionsResponse
|
||||
try:
|
||||
from google.adk.sessions import GetSessionConfig
|
||||
except ImportError:
|
||||
from google.adk.sessions.base_session_service import GetSessionConfig
|
||||
ADK_AVAILABLE = True
|
||||
except (ImportError, ModuleNotFoundError):
|
||||
ADK_AVAILABLE = False
|
||||
BaseSessionService = object
|
||||
Session = Any
|
||||
Event = Any
|
||||
ListSessionsResponse = Any
|
||||
GetSessionConfig = Any
|
||||
|
||||
|
||||
class SemanticaSessionService(BaseSessionService):
|
||||
"""
|
||||
Google ADK SessionService backed by a Semantica ContextGraph.
|
||||
|
||||
Graph structure:
|
||||
|
||||
ADKSession
|
||||
|
|
||||
+-- HAS_EVENT --> ADKEvent
|
||||
|
||||
Session metadata and state are stored in the ContextGraph node metadata.
|
||||
"""
|
||||
|
||||
def __init__(self, graph: Optional[Any] = None) -> None:
|
||||
if not ADK_AVAILABLE:
|
||||
raise ImportError(
|
||||
"Google ADK is required for SemanticaSessionService. "
|
||||
"Install it with: pip install semantica[google-adk]"
|
||||
)
|
||||
|
||||
super().__init__()
|
||||
|
||||
if graph is None:
|
||||
from semantica.context import ContextGraph
|
||||
|
||||
graph = ContextGraph()
|
||||
|
||||
self.graph = graph
|
||||
self._lock = threading.RLock()
|
||||
|
||||
# Graph helpers
|
||||
|
||||
@staticmethod
|
||||
def _node_id(app_name: str, user_id: str, session_id: str) -> str:
|
||||
"""Return the internal ContextGraph node ID for a session.
|
||||
|
||||
Each component is percent-encoded before joining so a ':' inside
|
||||
app_name/user_id/session_id can never be mistaken for the
|
||||
separator: without this, distinct identities such as
|
||||
(app_name="tenant:A", user_id="alice") and
|
||||
(app_name="tenant", user_id="A:alice") would collide on the same
|
||||
node ID.
|
||||
"""
|
||||
parts = (
|
||||
urllib.parse.quote(part, safe="")
|
||||
for part in (app_name, user_id, session_id)
|
||||
)
|
||||
return "adk-session:" + ":".join(parts)
|
||||
|
||||
@staticmethod
|
||||
def _event_node_id(event: Any) -> str:
|
||||
"""Return the internal ContextGraph node ID for an event."""
|
||||
event_id = getattr(event, "id", None)
|
||||
|
||||
if event_id:
|
||||
return f"adk-event:{event_id}"
|
||||
|
||||
return f"adk-event:{uuid.uuid4()}"
|
||||
|
||||
@staticmethod
|
||||
def _safe_dict(value: Any) -> dict:
|
||||
"""Convert common Python/Pydantic objects into a dictionary."""
|
||||
if value is None:
|
||||
return {}
|
||||
|
||||
if isinstance(value, dict):
|
||||
return copy.deepcopy(value)
|
||||
|
||||
if hasattr(value, "model_dump"):
|
||||
try:
|
||||
return copy.deepcopy(value.model_dump())
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if hasattr(value, "dict"):
|
||||
try:
|
||||
return copy.deepcopy(value.dict())
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
try:
|
||||
return {
|
||||
key: copy.deepcopy(item)
|
||||
for key, item in vars(value).items()
|
||||
if not key.startswith("_")
|
||||
}
|
||||
except Exception:
|
||||
return {}
|
||||
|
||||
@staticmethod
|
||||
def _node_properties(node: Any) -> dict:
|
||||
"""
|
||||
Extract application properties from a ContextGraph node.
|
||||
"""
|
||||
if isinstance(node, dict):
|
||||
metadata = node.get("metadata")
|
||||
|
||||
if isinstance(metadata, dict):
|
||||
return copy.deepcopy(metadata)
|
||||
|
||||
properties = node.get("properties")
|
||||
|
||||
if isinstance(properties, dict):
|
||||
return copy.deepcopy(properties)
|
||||
|
||||
return {}
|
||||
|
||||
metadata = getattr(node, "metadata", None)
|
||||
|
||||
if isinstance(metadata, dict):
|
||||
return copy.deepcopy(metadata)
|
||||
|
||||
properties = getattr(node, "properties", None)
|
||||
|
||||
if isinstance(properties, dict):
|
||||
return copy.deepcopy(properties)
|
||||
|
||||
return {}
|
||||
|
||||
def _find_session_node(
|
||||
self,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
session_id: str,
|
||||
) -> Optional[Any]:
|
||||
"""Find a session node by its logical ADK session ID."""
|
||||
expected_node_id = self._node_id(app_name, user_id, session_id)
|
||||
|
||||
for node in self.graph.find_nodes() or []:
|
||||
if not isinstance(node, dict):
|
||||
continue
|
||||
|
||||
# Fast path: ContextGraph node ID.
|
||||
if str(node.get("id")) == expected_node_id:
|
||||
return node
|
||||
|
||||
# Fallback: logical ID stored in metadata.
|
||||
metadata = node.get("metadata")
|
||||
|
||||
if (
|
||||
isinstance(metadata, dict)
|
||||
and str(metadata.get("session_id")) == str(session_id)
|
||||
and str(metadata.get("app_name")) == str(app_name)
|
||||
and str(metadata.get("user_id")) == str(user_id)
|
||||
):
|
||||
return node
|
||||
|
||||
return None
|
||||
|
||||
def _find_node_by_id(
|
||||
self,
|
||||
node_id: str,
|
||||
) -> Optional[Any]:
|
||||
"""Find a ContextGraph node by graph node ID."""
|
||||
for node in self.graph.find_nodes() or []:
|
||||
if isinstance(node, dict) and str(node.get("id")) == str(node_id):
|
||||
return node
|
||||
|
||||
return None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Event helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@staticmethod
|
||||
def _serialize_event(event: Any) -> dict:
|
||||
"""Serialize an ADK Event into ContextGraph metadata."""
|
||||
data = SemanticaSessionService._safe_dict(event)
|
||||
|
||||
for field in (
|
||||
"id",
|
||||
"invocation_id",
|
||||
"author",
|
||||
"timestamp",
|
||||
"partial",
|
||||
"turn_complete",
|
||||
"branch",
|
||||
):
|
||||
if field not in data and hasattr(event, field):
|
||||
value = getattr(event, field)
|
||||
|
||||
if isinstance(value, datetime):
|
||||
value = value.isoformat()
|
||||
|
||||
data[field] = copy.deepcopy(value)
|
||||
|
||||
return data
|
||||
|
||||
def _event_nodes(
|
||||
self,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
session_id: str,
|
||||
) -> List[Any]:
|
||||
"""Return all event nodes connected to a session."""
|
||||
session_node_id = self._node_id(app_name, user_id, session_id)
|
||||
|
||||
events: List[Any] = []
|
||||
|
||||
for edge in self.graph.find_edges() or []:
|
||||
if not isinstance(edge, dict):
|
||||
continue
|
||||
|
||||
if edge.get("source") != session_node_id:
|
||||
continue
|
||||
|
||||
if edge.get("type") != "HAS_EVENT":
|
||||
continue
|
||||
|
||||
target = edge.get("target")
|
||||
|
||||
if target is None:
|
||||
continue
|
||||
|
||||
node = self._find_node_by_id(str(target))
|
||||
|
||||
if node is not None:
|
||||
events.append(node)
|
||||
|
||||
return events
|
||||
|
||||
@staticmethod
|
||||
def _event_timestamp(node: Any) -> str:
|
||||
"""Return a sortable timestamp for an event node."""
|
||||
properties = SemanticaSessionService._node_properties(node)
|
||||
timestamp = properties.get("timestamp")
|
||||
|
||||
if timestamp is None:
|
||||
return ""
|
||||
|
||||
return str(timestamp)
|
||||
|
||||
def _event_from_node(
|
||||
self,
|
||||
node: Any,
|
||||
) -> Any:
|
||||
"""
|
||||
Reconstruct an ADK Event from its stored metadata.
|
||||
"""
|
||||
properties = self._node_properties(node)
|
||||
|
||||
graph_node_id = node.get("id") if isinstance(node, dict) else None
|
||||
event_id = properties.get("id")
|
||||
|
||||
if not event_id and graph_node_id:
|
||||
graph_node_id = str(graph_node_id)
|
||||
if graph_node_id.startswith("adk-event:"):
|
||||
event_id = graph_node_id[len("adk-event:"):]
|
||||
|
||||
if event_id:
|
||||
properties["id"] = event_id
|
||||
|
||||
# ContextGraph-specific values should never become Event fields.
|
||||
properties.pop("session_id", None)
|
||||
properties.pop("app_name", None)
|
||||
properties.pop("user_id", None)
|
||||
|
||||
try:
|
||||
return Event(**properties)
|
||||
except Exception:
|
||||
return properties
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Session helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@staticmethod
|
||||
def _session_kwargs(
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
session_id: str,
|
||||
state: Optional[dict],
|
||||
events: Optional[List[Any]],
|
||||
) -> dict:
|
||||
"""Build kwargs for the ADK Session model."""
|
||||
return {
|
||||
"app_name": app_name,
|
||||
"user_id": user_id,
|
||||
"id": session_id,
|
||||
"state": copy.deepcopy(state or {}),
|
||||
"events": list(events or []),
|
||||
}
|
||||
|
||||
def _session_from_node(
|
||||
self,
|
||||
node: Any,
|
||||
) -> Session:
|
||||
"""Reconstruct an ADK Session from a ContextGraph node."""
|
||||
properties = self._node_properties(node)
|
||||
|
||||
session_id = str(properties.get("session_id") or "")
|
||||
app_name = str(properties.get("app_name") or "")
|
||||
user_id = str(properties.get("user_id") or "")
|
||||
|
||||
# Fallback to the graph node ID.
|
||||
if not session_id:
|
||||
graph_node_id = node.get("id") if isinstance(node, dict) else None
|
||||
|
||||
if graph_node_id:
|
||||
graph_node_id = str(graph_node_id)
|
||||
if graph_node_id.startswith("adk-session:"):
|
||||
# Each component is percent-encoded by _node_id(), so
|
||||
# splitting on ':' after the prefix always yields
|
||||
# exactly 3 parts regardless of what characters the
|
||||
# original app_name/user_id/session_id contained.
|
||||
parts = graph_node_id[len("adk-session:"):].split(":")
|
||||
if len(parts) == 3:
|
||||
decoded = [urllib.parse.unquote(part) for part in parts]
|
||||
app_name = app_name or decoded[0]
|
||||
user_id = user_id or decoded[1]
|
||||
session_id = decoded[2]
|
||||
else:
|
||||
session_id = graph_node_id[len("adk-session:"):]
|
||||
else:
|
||||
session_id = graph_node_id
|
||||
|
||||
state = properties.get("state") or {}
|
||||
|
||||
if not isinstance(state, dict):
|
||||
state = {}
|
||||
|
||||
event_nodes = self._event_nodes(app_name, user_id, session_id)
|
||||
event_nodes.sort(key=self._event_timestamp)
|
||||
|
||||
events = [self._event_from_node(node) for node in event_nodes]
|
||||
|
||||
return Session(
|
||||
**self._session_kwargs(
|
||||
app_name=app_name,
|
||||
user_id=user_id,
|
||||
session_id=session_id,
|
||||
state=state,
|
||||
events=events,
|
||||
)
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# ADK SessionService implementation
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
async def create_session(
|
||||
self,
|
||||
*,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
state: Optional[dict[str, Any]] = None,
|
||||
session_id: Optional[str] = None,
|
||||
) -> Session:
|
||||
"""Create and persist an ADK session."""
|
||||
return await asyncio.to_thread(
|
||||
self._create_session_sync, app_name, user_id, state, session_id
|
||||
)
|
||||
|
||||
def _create_session_sync(
|
||||
self,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
state: Optional[dict[str, Any]],
|
||||
session_id: Optional[str],
|
||||
) -> Session:
|
||||
with self._lock:
|
||||
session_id = session_id or str(uuid.uuid4())
|
||||
|
||||
if self._find_session_node(app_name, user_id, session_id) is not None:
|
||||
raise ValueError(f"Session already exists: {session_id}")
|
||||
|
||||
self.graph.add_node(
|
||||
node_id=self._node_id(app_name, user_id, session_id),
|
||||
node_type="ADKSession",
|
||||
app_name=app_name,
|
||||
user_id=user_id,
|
||||
session_id=session_id,
|
||||
state=copy.deepcopy(state or {}),
|
||||
created_at=datetime.now().isoformat(),
|
||||
updated_at=datetime.now().isoformat(),
|
||||
)
|
||||
|
||||
return Session(
|
||||
**self._session_kwargs(
|
||||
app_name=app_name,
|
||||
user_id=user_id,
|
||||
session_id=session_id,
|
||||
state=state,
|
||||
events=[],
|
||||
)
|
||||
)
|
||||
|
||||
async def get_session(
|
||||
self,
|
||||
*,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
session_id: str,
|
||||
config: Optional[GetSessionConfig] = None,
|
||||
) -> Optional[Session]:
|
||||
"""Retrieve an ADK session from ContextGraph."""
|
||||
return await asyncio.to_thread(
|
||||
self._get_session_sync, app_name, user_id, session_id, config
|
||||
)
|
||||
|
||||
def _get_session_sync(
|
||||
self,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
session_id: str,
|
||||
config: Optional[GetSessionConfig],
|
||||
) -> Optional[Session]:
|
||||
with self._lock:
|
||||
node = self._find_session_node(app_name, user_id, session_id)
|
||||
|
||||
if node is None:
|
||||
return None
|
||||
|
||||
properties = self._node_properties(node)
|
||||
if properties.get("app_name") != app_name:
|
||||
return None
|
||||
if properties.get("user_id") != user_id:
|
||||
return None
|
||||
|
||||
session = self._session_from_node(node)
|
||||
|
||||
# Bound the returned event history the same way ADK's own
|
||||
# InMemorySessionService does, outside the lock since it only
|
||||
# trims the already-built Session object.
|
||||
if config:
|
||||
if config.num_recent_events:
|
||||
session.events = session.events[-config.num_recent_events:]
|
||||
if config.after_timestamp:
|
||||
i = len(session.events) - 1
|
||||
while i >= 0:
|
||||
if session.events[i].timestamp < config.after_timestamp:
|
||||
break
|
||||
i -= 1
|
||||
if i >= 0:
|
||||
session.events = session.events[i + 1:]
|
||||
|
||||
return session
|
||||
|
||||
async def append_event(
|
||||
self,
|
||||
session: Session,
|
||||
event: Event,
|
||||
) -> Event:
|
||||
"""Persist an ADK event and associate it with a session."""
|
||||
# ADK's own base implementation is a no-op for partial/streaming
|
||||
# events (it returns before touching session.events or state), so
|
||||
# a graph-backed session must not persist them either -- otherwise
|
||||
# every intermediate chunk of a streamed response becomes a
|
||||
# permanent event node.
|
||||
if getattr(event, "partial", False):
|
||||
return event
|
||||
|
||||
await asyncio.to_thread(self._append_event_sync, session, event)
|
||||
return event
|
||||
|
||||
def _append_event_sync(self, session: Session, event: Event) -> None:
|
||||
with self._lock:
|
||||
session_id = str(session.id)
|
||||
app_name = str(session.app_name)
|
||||
user_id = str(session.user_id)
|
||||
|
||||
session_node = self._find_session_node(app_name, user_id, session_id)
|
||||
|
||||
if session_node is None:
|
||||
raise ValueError(f"Session does not exist: {session_id}")
|
||||
|
||||
# Verify cross-tenant security
|
||||
properties = self._node_properties(session_node)
|
||||
if properties.get("app_name") != app_name or properties.get("user_id") != user_id:
|
||||
raise ValueError("Cross-tenant session write denied: app_name or user_id mismatch.")
|
||||
|
||||
# Apply ADK in-memory event and state delta semantics. This
|
||||
# runs inside asyncio.to_thread's worker thread, which has no
|
||||
# event loop of its own, so a coroutine base implementation is
|
||||
# driven with a private event loop scoped to this one call.
|
||||
base_append = getattr(super(), "append_event", None)
|
||||
if base_append is not None:
|
||||
if inspect.iscoroutinefunction(base_append):
|
||||
asyncio.run(base_append(session, event))
|
||||
else:
|
||||
base_append(session, event)
|
||||
else:
|
||||
if hasattr(session, "events"):
|
||||
session.events.append(event)
|
||||
|
||||
event_node_id = self._event_node_id(event)
|
||||
event_data = self._serialize_event(event)
|
||||
|
||||
self.graph.add_node(
|
||||
node_id=event_node_id,
|
||||
node_type="ADKEvent",
|
||||
session_id=session_id,
|
||||
**event_data,
|
||||
)
|
||||
|
||||
self.graph.add_edge(
|
||||
source_id=self._node_id(app_name, user_id, session_id),
|
||||
target_id=event_node_id,
|
||||
edge_type="HAS_EVENT",
|
||||
)
|
||||
|
||||
# ContextGraph's supported mutation API is add_node_attribute().
|
||||
self.graph.add_node_attribute(
|
||||
self._node_id(app_name, user_id, session_id),
|
||||
{
|
||||
"state": self._safe_dict(getattr(session, "state", {})),
|
||||
"updated_at": (datetime.now().isoformat()),
|
||||
},
|
||||
)
|
||||
|
||||
async def delete_session(
|
||||
self,
|
||||
*,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
session_id: str,
|
||||
) -> None:
|
||||
"""Delete a session and all of its graph-backed events."""
|
||||
await asyncio.to_thread(
|
||||
self._delete_session_sync, app_name, user_id, session_id
|
||||
)
|
||||
|
||||
def _delete_session_sync(
|
||||
self,
|
||||
app_name: str,
|
||||
user_id: str,
|
||||
session_id: str,
|
||||
) -> None:
|
||||
with self._lock:
|
||||
session_node = self._find_session_node(app_name, user_id, session_id)
|
||||
if session_node is None:
|
||||
return
|
||||
|
||||
properties = self._node_properties(session_node)
|
||||
|
||||
if properties.get("app_name") != app_name:
|
||||
return
|
||||
if properties.get("user_id") != user_id:
|
||||
return
|
||||
|
||||
session_node_id = self._node_id(app_name, user_id, session_id)
|
||||
event_node_ids = []
|
||||
|
||||
for edge in self.graph.find_edges() or []:
|
||||
if not isinstance(edge, dict):
|
||||
continue
|
||||
|
||||
if (
|
||||
edge.get("source") == session_node_id
|
||||
and edge.get("type") == "HAS_EVENT"
|
||||
and edge.get("target")
|
||||
):
|
||||
event_node_ids.append(str(edge["target"]))
|
||||
|
||||
for event_node_id in event_node_ids:
|
||||
self.graph.purge_node(event_node_id)
|
||||
|
||||
self.graph.purge_node(session_node_id)
|
||||
|
||||
async def list_sessions(
|
||||
self,
|
||||
*,
|
||||
app_name: str,
|
||||
user_id: Optional[str] = None,
|
||||
) -> ListSessionsResponse:
|
||||
"""List sessions for an app, optionally scoped to one user."""
|
||||
return await asyncio.to_thread(self._list_sessions_sync, app_name, user_id)
|
||||
|
||||
def _list_sessions_sync(
|
||||
self,
|
||||
app_name: str,
|
||||
user_id: Optional[str],
|
||||
) -> ListSessionsResponse:
|
||||
with self._lock:
|
||||
sessions: List[Session] = []
|
||||
|
||||
for node in self.graph.find_nodes(node_type="ADKSession") or []:
|
||||
if not isinstance(node, dict):
|
||||
continue
|
||||
|
||||
properties = self._node_properties(node)
|
||||
|
||||
if properties.get("app_name") != app_name:
|
||||
continue
|
||||
if user_id is not None and properties.get("user_id") != user_id:
|
||||
continue
|
||||
if not properties.get("session_id"):
|
||||
continue
|
||||
|
||||
sessions.append(self._session_from_node(node))
|
||||
|
||||
# Return the wrapped ListSessionsResponse
|
||||
if ListSessionsResponse is not Any and ListSessionsResponse is not object:
|
||||
return ListSessionsResponse(sessions=sessions)
|
||||
|
||||
return sessions
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ADK_AVAILABLE",
|
||||
"SemanticaSessionService",
|
||||
]
|
||||
@@ -0,0 +1,5 @@
|
||||
"""Entry point: python -m mcp.server"""
|
||||
from mcp.server import main
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -10,8 +10,8 @@ from __future__ import annotations
|
||||
import json
|
||||
import logging
|
||||
|
||||
from .. import __version__
|
||||
from ..session import get_graph
|
||||
from mcp import __version__
|
||||
from mcp.session import get_graph
|
||||
|
||||
log = logging.getLogger("semantica.mcp.resources")
|
||||
|
||||
@@ -6,8 +6,8 @@ Implements the Model Context Protocol so any MCP-compatible AI tool
|
||||
can interact with the Semantica knowledge graph.
|
||||
|
||||
Run:
|
||||
python -m semantica_mcp.mcp # via __main__.py
|
||||
python -m semantica_mcp.mcp.server # direct
|
||||
python -m mcp # via __main__.py
|
||||
python -m mcp.server # direct
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -17,9 +17,9 @@ import logging
|
||||
import sys
|
||||
from typing import Any
|
||||
|
||||
from . import __version__
|
||||
from .resources import RESOURCE_DEFINITIONS, handle_resource_read
|
||||
from .tools import TOOL_DEFINITIONS
|
||||
from mcp import __version__
|
||||
from mcp.resources import RESOURCE_DEFINITIONS, handle_resource_read
|
||||
from mcp.tools import TOOL_DEFINITIONS
|
||||
|
||||
log = logging.getLogger("semantica.mcp.server")
|
||||
|
||||
@@ -7,14 +7,14 @@ from __future__ import annotations
|
||||
import logging
|
||||
import os
|
||||
|
||||
from ..schemas import (
|
||||
from mcp.schemas import (
|
||||
ANALYZE_DECISION_IMPACT,
|
||||
FIND_PRECEDENTS,
|
||||
GET_CAUSAL_CHAIN,
|
||||
QUERY_DECISIONS,
|
||||
RECORD_DECISION,
|
||||
)
|
||||
from ..session import get_graph, is_persistence_safe
|
||||
from mcp.session import get_graph, is_persistence_safe
|
||||
|
||||
log = logging.getLogger("semantica.mcp.tools.decisions")
|
||||
|
||||
@@ -6,8 +6,8 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
|
||||
from ..schemas import EXPORT_GRAPH, GET_PROVENANCE
|
||||
from ..session import get_graph
|
||||
from mcp.schemas import EXPORT_GRAPH, GET_PROVENANCE
|
||||
from mcp.session import get_graph
|
||||
|
||||
log = logging.getLogger("semantica.mcp.tools.export")
|
||||
|
||||
@@ -7,7 +7,7 @@ from __future__ import annotations
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
from ..schemas import EXTRACT_ALL, EXTRACT_ENTITIES, EXTRACT_RELATIONS
|
||||
from mcp.schemas import EXTRACT_ALL, EXTRACT_ENTITIES, EXTRACT_RELATIONS
|
||||
|
||||
log = logging.getLogger("semantica.mcp.tools.extraction")
|
||||
|
||||
@@ -7,8 +7,8 @@ from __future__ import annotations
|
||||
import logging
|
||||
import os
|
||||
|
||||
from ..schemas import ADD_ENTITY, ADD_RELATIONSHIP, EMPTY, GET_ANALYTICS, SEARCH_GRAPH
|
||||
from ..session import get_graph, is_persistence_safe
|
||||
from mcp.schemas import ADD_ENTITY, ADD_RELATIONSHIP, EMPTY, GET_ANALYTICS, SEARCH_GRAPH
|
||||
from mcp.session import get_graph, is_persistence_safe
|
||||
|
||||
log = logging.getLogger("semantica.mcp.tools.graph")
|
||||
|
||||
@@ -6,7 +6,7 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
|
||||
from ..schemas import ABDUCTIVE_REASONING, RUN_REASONING
|
||||
from mcp.schemas import ABDUCTIVE_REASONING, RUN_REASONING
|
||||
|
||||
log = logging.getLogger("semantica.mcp.tools.reasoning")
|
||||
|
||||
+10
-41
@@ -47,11 +47,7 @@ dependencies = [
|
||||
"numpy>=2.0.2",
|
||||
"pandas>=1.3.0",
|
||||
"scipy>=1.13.1",
|
||||
# scikit-learn dropped Python 3.9 support at 1.7.0 (requires_python >=3.10),
|
||||
# so an unqualified >=1.7.2 floor is unsatisfiable on 3.9. Cap 3.9 to the
|
||||
# last 3.9-compatible release line; 3.10+ is left unconstrained.
|
||||
"scikit-learn>=1.6.1,<1.7.0; python_version < '3.10'",
|
||||
"scikit-learn>=1.7.2; python_version >= '3.10'",
|
||||
"scikit-learn>=1.7.2",
|
||||
"umap-learn>=0.5.12",
|
||||
# thinc (spacy's core dep) dropped Python 3.9 wheels at 8.3.10, and later
|
||||
# spacy patch releases (3.8.8+) require thinc>=8.3.9-only-on-3.10+ ranges,
|
||||
@@ -70,49 +66,24 @@ dependencies = [
|
||||
"seaborn>=0.13.2",
|
||||
"plotly>=6.8.0",
|
||||
"ipywidgets>=8.0.0",
|
||||
# requests dropped Python 3.9 support at 2.33.0 (requires_python >=3.10),
|
||||
# so an unqualified >=2.34.2 floor is unsatisfiable on 3.9. Cap 3.9 to the
|
||||
# last 3.9-compatible release; 3.10+ is left unconstrained.
|
||||
"requests>=2.32.5,<2.33.0; python_version < '3.10'",
|
||||
"requests>=2.34.2; python_version >= '3.10'",
|
||||
"requests>=2.34.2",
|
||||
"GitPython>=3.1.58",
|
||||
# chardet dropped Python 3.9 support at 6.0.0 (requires_python >=3.10), so
|
||||
# an unqualified >=7.4.3 floor is unsatisfiable on 3.9. Cap 3.9 to the last
|
||||
# 3.9-compatible release; 3.10+ is left unconstrained.
|
||||
"chardet>=5.2.0,<6.0.0; python_version < '3.10'",
|
||||
"chardet>=7.4.3; python_version >= '3.10'",
|
||||
"chardet>=7.4.3",
|
||||
"protobuf>=5.29.1,<8.0",
|
||||
# grpcio dropped Python 3.9 support at 1.81.0 (requires_python >=3.10), so
|
||||
# an unqualified >=1.81.1 floor is unsatisfiable on 3.9. Cap 3.9 to the last
|
||||
# 3.9-compatible release; 3.10+ is left unconstrained.
|
||||
"grpcio>=1.80.0,<1.81.0; python_version < '3.10'",
|
||||
"grpcio>=1.81.1; python_version >= '3.10'",
|
||||
"grpcio>=1.81.1",
|
||||
"beautifulsoup4>=4.15.0",
|
||||
"lxml>=6.1.1",
|
||||
"python-docx>=1.2.0",
|
||||
"openpyxl>=3.1.5",
|
||||
# pillow dropped Python 3.9 support at 12.0.0 (requires_python >=3.10), so
|
||||
# an unqualified >=12.2.0 floor is unsatisfiable on 3.9. Cap 3.9 to the last
|
||||
# 3.9-compatible release; 3.10+ is left unconstrained.
|
||||
"pillow>=11.3.0,<12.0.0; python_version < '3.10'",
|
||||
"pillow>=12.2.0; python_version >= '3.10'",
|
||||
"pillow>=12.2.0",
|
||||
"librosa>=0.9.0",
|
||||
"opencv-python>=4.13.0.92",
|
||||
"faiss-cpu>=1.7.0",
|
||||
"fastembed>=0.2.0",
|
||||
# onnxruntime stopped shipping cp39 wheels at 1.20.0 (its PyPI metadata
|
||||
# still claims requires_python >=3.9, but no matching wheel exists), so an
|
||||
# unqualified >=1.20.1 floor is unsatisfiable on 3.9. Cap 3.9 to the last
|
||||
# release with a cp39 wheel; 3.10+ is left unconstrained.
|
||||
"onnxruntime>=1.19.2,<1.20.0; python_version < '3.10'",
|
||||
"onnxruntime>=1.20.1; python_version >= '3.10'",
|
||||
"onnxruntime>=1.20.1",
|
||||
"tokenizers>=0.15.0",
|
||||
"pydantic>=2.13.4",
|
||||
# click dropped Python 3.9 support at 8.2.0 (requires_python >=3.10), so an
|
||||
# unqualified >=8.4.2 floor is unsatisfiable on 3.9. Cap 3.9 to the last
|
||||
# 3.9-compatible release; 3.10+ is left unconstrained.
|
||||
"click>=8.1.8,<8.2.0; python_version < '3.10'",
|
||||
"click>=8.4.2; python_version >= '3.10'",
|
||||
"click>=8.4.2",
|
||||
"rich>=12.5.0",
|
||||
"tqdm>=4.68.3",
|
||||
"pyyaml>=6.0",
|
||||
@@ -192,7 +163,7 @@ tripletstore-oxigraph = ["pyoxigraph>=0.5.0"]
|
||||
# ---- Vector Store Backends ----
|
||||
vectorstore-qdrant = ["qdrant-client>=1.0.0"]
|
||||
vectorstore-weaviate = ["weaviate-client>=4.0.0"]
|
||||
vectorstore-pinecone = ["pinecone>=3.0.0"]
|
||||
vectorstore-pinecone = ["pinecone-client>=3.0.0"]
|
||||
vectorstore-milvus = ["pymilvus>=2.0.0"]
|
||||
vectorstore-pgvector = ["psycopg[binary,pool]>=3.0.0", "pgvector>=0.2.0"]
|
||||
vectorstore-sqlite = ["sqlite-vec>=0.1.1"]
|
||||
@@ -246,7 +217,6 @@ agno = ["agno>=1.0.0"]
|
||||
# duplicate the prebuilt tooling users can install separately.
|
||||
crewai = ["crewai>=0.80.0"]
|
||||
langchain = ["langchain-core>=0.3.0"]
|
||||
google-adk = ["google-adk>=1.27.0; python_version >= '3.10'"]
|
||||
|
||||
# ---- File Watching ----
|
||||
watch = ["watchdog>=6.0.0"]
|
||||
@@ -277,7 +247,6 @@ dev = [
|
||||
# Explorer Dashboard
|
||||
explorer = [
|
||||
"fastapi>=0.109.2",
|
||||
"starlette>=0.53.0",
|
||||
"uvicorn[standard]>=0.22.0",
|
||||
"websockets>=15.0.1",
|
||||
"python-multipart>=0.0.7",
|
||||
@@ -295,7 +264,7 @@ explorer-lite = [
|
||||
# dependency-audit/security gates. Install it explicitly via ``semantica[crewai]``.
|
||||
all = [
|
||||
"semantica[dev,viz,infra,cloud,monitoring,watch,llm-all,models-huggingface,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,explorer]",
|
||||
"semantica[dev,viz,infra,cloud,monitoring,watch,llm-all,models-huggingface,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,agno,langchain,google-adk]"
|
||||
"semantica[dev,viz,infra,cloud,monitoring,watch,llm-all,models-huggingface,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,agno,langchain]"
|
||||
]
|
||||
|
||||
# ---------------- ENTRYPOINTS ----------------
|
||||
@@ -309,7 +278,7 @@ semantica-mcp = "semantica.mcp_server:main"
|
||||
# ---------------- TOOLING ----------------
|
||||
[tool.setuptools.packages.find]
|
||||
where = ["."]
|
||||
include = ["semantica*", "integrations*", "semantica_mcp*"]
|
||||
include = ["semantica*", "integrations*"]
|
||||
|
||||
[tool.setuptools.package-data]
|
||||
# Explicit patterns are more reliable than **/* across setuptools versions.
|
||||
|
||||
+1860
-2178
File diff suppressed because it is too large
Load Diff
+3
-3
@@ -4571,7 +4571,7 @@ def mcp_start(cli_ctx: CLIContext, transport: str, port: int) -> None:
|
||||
|
||||
def _action() -> None:
|
||||
import subprocess as sp
|
||||
cmd = [sys.executable, "-m", "semantica_mcp.mcp.server"]
|
||||
cmd = [sys.executable, "-m", "mcp.server"]
|
||||
if transport == "http":
|
||||
cmd += ["--port", str(port)]
|
||||
proc = sp.Popen(cmd)
|
||||
@@ -4614,7 +4614,7 @@ def mcp_list_tools(cli_ctx: CLIContext, local_json: bool) -> None:
|
||||
|
||||
def _action() -> None:
|
||||
try:
|
||||
from semantica_mcp.mcp.tools import __all__ as tools
|
||||
from mcp.tools import __all__ as tools
|
||||
except ImportError:
|
||||
tools = [
|
||||
"extract_entities", "extract_relations", "build_graph",
|
||||
@@ -4655,7 +4655,7 @@ def mcp_call(cli_ctx: CLIContext, tool_name: str, args: str, local_json: bool) -
|
||||
except json.JSONDecodeError as exc:
|
||||
raise click.ClickException(f"Invalid JSON in --args: {exc}") from exc
|
||||
try:
|
||||
from semantica_mcp.mcp.session import MCPSession
|
||||
from mcp.session import MCPSession
|
||||
session = MCPSession(config=cli_ctx.config.to_dict())
|
||||
result = session.call_tool(tool_name, **tool_args)
|
||||
except ImportError as exc:
|
||||
|
||||
@@ -65,11 +65,9 @@ import os
|
||||
import re
|
||||
import stat
|
||||
import tempfile
|
||||
import threading
|
||||
from collections import deque
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import date, datetime, timedelta, timezone
|
||||
from functools import wraps
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Tuple, Union
|
||||
|
||||
@@ -80,12 +78,6 @@ from ..utils.logging import get_logger
|
||||
from ..utils.progress_tracker import get_progress_tracker
|
||||
from ..utils.types import EntityDict, RelationshipDict
|
||||
from ._markdown_filesystem import find_filesystem_link
|
||||
from .markdown import (
|
||||
MarkdownIdentityError,
|
||||
MarkdownResourceNotFoundError,
|
||||
MarkdownRevisionConflictError,
|
||||
markdown_document_revision,
|
||||
)
|
||||
|
||||
|
||||
class _UniqueKeySafeLoader(yaml.SafeLoader):
|
||||
@@ -166,17 +158,6 @@ class MemoryItem:
|
||||
)
|
||||
|
||||
|
||||
def _with_memory_lock(method):
|
||||
"""Serialize AgentMemory state mutations and Markdown revision checks."""
|
||||
|
||||
@wraps(method)
|
||||
def locked(self, *args, **kwargs):
|
||||
with self._memory_lock:
|
||||
return method(self, *args, **kwargs)
|
||||
|
||||
return locked
|
||||
|
||||
|
||||
class AgentMemory:
|
||||
"""
|
||||
Agent memory manager with RAG integration and Hierarchical Memory.
|
||||
@@ -216,7 +197,6 @@ class AgentMemory:
|
||||
self.logger = get_logger("agent_memory")
|
||||
self.config = config or {}
|
||||
self.config.update(kwargs)
|
||||
self._memory_lock = threading.RLock()
|
||||
|
||||
self.vector_store = self.config.get("vector_store")
|
||||
self.knowledge_graph = self.config.get("knowledge_graph")
|
||||
@@ -269,7 +249,6 @@ class AgentMemory:
|
||||
|
||||
self.logger.info(f"Saved agent memory to {path}")
|
||||
|
||||
@_with_memory_lock
|
||||
def load(self, path: str) -> None:
|
||||
"""
|
||||
Load memory state from disk.
|
||||
@@ -319,7 +298,6 @@ class AgentMemory:
|
||||
|
||||
self.logger.info(f"Loaded agent memory from {path}")
|
||||
|
||||
@_with_memory_lock
|
||||
def store(
|
||||
self,
|
||||
content: str,
|
||||
@@ -596,7 +574,6 @@ class AgentMemory:
|
||||
"relationships": memory_item.relationships,
|
||||
}
|
||||
|
||||
@_with_memory_lock
|
||||
def delete_memory(self, memory_id: str, *, skip_vector: bool = False) -> bool:
|
||||
"""
|
||||
Delete memory item.
|
||||
@@ -648,7 +625,6 @@ class AgentMemory:
|
||||
self.logger.debug(f"Deleted memory item: {memory_id}")
|
||||
return True
|
||||
|
||||
@_with_memory_lock
|
||||
def vector_ids_for(self, memory_id: str) -> List[str]:
|
||||
"""Return the vector-store ids owned by a memory item.
|
||||
|
||||
@@ -1160,7 +1136,6 @@ class AgentMemory:
|
||||
"""
|
||||
return self.get_memory(memory_id)
|
||||
|
||||
@_with_memory_lock
|
||||
def update(
|
||||
self,
|
||||
memory_id: str,
|
||||
@@ -1441,13 +1416,6 @@ class AgentMemory:
|
||||
|
||||
return results
|
||||
|
||||
@_with_memory_lock
|
||||
def list_snapshot(
|
||||
self, *, limit: int = 100, offset: int = 0
|
||||
) -> Tuple[List[Dict[str, Any]], int]:
|
||||
"""Return one memory page and its total from the same locked state."""
|
||||
return self.list(limit=limit, offset=offset), len(self.memory_items)
|
||||
|
||||
def get_by_conversation(
|
||||
self, conversation_id: str, limit: int = 100
|
||||
) -> List[Dict[str, Any]]:
|
||||
@@ -1663,88 +1631,6 @@ class AgentMemory:
|
||||
updated += 1
|
||||
return updated
|
||||
|
||||
@_with_memory_lock
|
||||
def export_item_markdown(self, memory_id: str) -> str:
|
||||
"""Return one existing memory item as canonical Markdown.
|
||||
|
||||
Args:
|
||||
memory_id: Stable identifier of the memory item to export.
|
||||
|
||||
Returns:
|
||||
Canonical Markdown containing the memory frontmatter and body.
|
||||
|
||||
Raises:
|
||||
MarkdownResourceNotFoundError: If ``memory_id`` does not exist.
|
||||
"""
|
||||
memory = self.get(memory_id)
|
||||
if memory is None:
|
||||
raise MarkdownResourceNotFoundError(
|
||||
f"AgentMemory item {memory_id!r} was not found."
|
||||
)
|
||||
return self._memory_to_markdown(memory)
|
||||
|
||||
@_with_memory_lock
|
||||
def apply_item_markdown(
|
||||
self,
|
||||
memory_id: str,
|
||||
document: str,
|
||||
*,
|
||||
expected_revision: Optional[str] = None,
|
||||
) -> bool:
|
||||
"""Validate and atomically replace one existing memory item.
|
||||
|
||||
Args:
|
||||
memory_id: Stable identifier of the memory item to update.
|
||||
document: Canonical Markdown containing the replacement item.
|
||||
expected_revision: Optional revision returned by
|
||||
:meth:`export_item_markdown`. A mismatch rejects stale edits.
|
||||
|
||||
Returns:
|
||||
``True`` when the item changed, otherwise ``False``.
|
||||
|
||||
Raises:
|
||||
ValueError: If the Markdown or frontmatter is invalid.
|
||||
MarkdownIdentityError: If the frontmatter changes the memory ID.
|
||||
MarkdownResourceNotFoundError: If ``memory_id`` does not exist.
|
||||
MarkdownRevisionConflictError: If ``expected_revision`` is stale.
|
||||
RuntimeError: If the validated item cannot be persisted.
|
||||
"""
|
||||
memory = self._markdown_to_memory_dict(document, source=f"memory {memory_id!r}")
|
||||
document_id = memory["memory_id"]
|
||||
if document_id != memory_id:
|
||||
raise MarkdownIdentityError(
|
||||
f"Frontmatter id {document_id!r} does not match resource id "
|
||||
f"{memory_id!r}."
|
||||
)
|
||||
if not self.exists(memory_id):
|
||||
raise MarkdownResourceNotFoundError(
|
||||
f"AgentMemory item {memory_id!r} was not found."
|
||||
)
|
||||
if expected_revision is not None:
|
||||
# _memory_lock is an RLock; this re-entrant call into
|
||||
# export_item_markdown (also @_with_memory_lock) is intentional
|
||||
# and safe because RLock allows the same thread to re-acquire.
|
||||
current_revision = markdown_document_revision(
|
||||
self.export_item_markdown(memory_id)
|
||||
)
|
||||
if current_revision != expected_revision:
|
||||
raise MarkdownRevisionConflictError(current_revision)
|
||||
if self._markdown_record_matches(memory_id, memory):
|
||||
return False
|
||||
|
||||
success = self._replace_memory_item(
|
||||
memory_id,
|
||||
memory["content"],
|
||||
metadata=memory["metadata"],
|
||||
entities=memory["entities"],
|
||||
relationships=memory["relationships"],
|
||||
timestamp=memory["timestamp"],
|
||||
skip_graph=True,
|
||||
)
|
||||
if not success:
|
||||
raise RuntimeError(f"AgentMemory item {memory_id!r} could not be replaced.")
|
||||
return True
|
||||
|
||||
# Export/Import
|
||||
def export(
|
||||
self,
|
||||
@@ -1793,7 +1679,6 @@ class AgentMemory:
|
||||
return self._export_markdown(memories, destination=destination)
|
||||
return export_data
|
||||
|
||||
@_with_memory_lock
|
||||
def import_data(
|
||||
self, data: Union[str, Path, Dict[str, Any]], format: str = "json"
|
||||
) -> int:
|
||||
|
||||
@@ -131,12 +131,6 @@ from ..utils.progress_tracker import get_progress_tracker
|
||||
from ..utils.skos import is_skos_hierarchy_edge, validate_skos_hierarchy
|
||||
from ._markdown_filesystem import find_filesystem_link
|
||||
from .entity_linker import EntityLinker
|
||||
from .markdown import (
|
||||
MarkdownIdentityError,
|
||||
MarkdownResourceNotFoundError,
|
||||
MarkdownRevisionConflictError,
|
||||
markdown_document_revision,
|
||||
)
|
||||
|
||||
|
||||
class _UniqueKeySafeLoader(yaml.SafeLoader):
|
||||
@@ -1173,157 +1167,6 @@ class ContextGraph:
|
||||
)
|
||||
)
|
||||
|
||||
def export_node_markdown(self, node_id: str) -> str:
|
||||
"""Return one existing node as canonical Markdown.
|
||||
|
||||
Args:
|
||||
node_id: Stable identifier of the node to export.
|
||||
|
||||
Returns:
|
||||
Canonical Markdown containing the node frontmatter and body.
|
||||
|
||||
Raises:
|
||||
MarkdownResourceNotFoundError: If ``node_id`` does not exist.
|
||||
"""
|
||||
with self._lock:
|
||||
node = self.nodes.get(node_id)
|
||||
if node is None:
|
||||
raise MarkdownResourceNotFoundError(
|
||||
f"ContextGraph node {node_id!r} was not found."
|
||||
)
|
||||
return self._node_markdown_source(node)
|
||||
|
||||
def _node_markdown_source(self, node: ContextNode) -> str:
|
||||
frontmatter = {
|
||||
"id": node.node_id,
|
||||
"type": node.node_type,
|
||||
"properties": copy.deepcopy(node.properties),
|
||||
"metadata": copy.deepcopy(node.metadata),
|
||||
"valid_from": node.valid_from,
|
||||
"valid_until": node.valid_until,
|
||||
}
|
||||
return self._render_markdown_document(
|
||||
frontmatter, node.content, f"node {node.node_id!r}"
|
||||
)
|
||||
|
||||
def apply_node_markdown(
|
||||
self,
|
||||
node_id: str,
|
||||
document: str,
|
||||
*,
|
||||
expected_revision: Optional[str] = None,
|
||||
) -> bool:
|
||||
"""Validate and atomically replace one existing node.
|
||||
|
||||
Args:
|
||||
node_id: Stable identifier of the node to update.
|
||||
document: Canonical Markdown containing the replacement node.
|
||||
expected_revision: Optional revision returned by
|
||||
:meth:`export_node_markdown`. A mismatch rejects stale edits.
|
||||
|
||||
Returns:
|
||||
``True`` when the node changed, otherwise ``False``.
|
||||
|
||||
Raises:
|
||||
ValueError: If the Markdown or frontmatter is invalid.
|
||||
MarkdownIdentityError: If the frontmatter changes the node ID.
|
||||
MarkdownResourceNotFoundError: If ``node_id`` does not exist.
|
||||
MarkdownRevisionConflictError: If ``expected_revision`` is stale.
|
||||
"""
|
||||
source = f"node {node_id!r}"
|
||||
frontmatter, body = self._parse_markdown_document(document, source)
|
||||
candidate = self._parse_markdown_node(frontmatter, body, source)
|
||||
if candidate.node_id != node_id:
|
||||
raise MarkdownIdentityError(
|
||||
f"Frontmatter id {candidate.node_id!r} does not match resource id "
|
||||
f"{node_id!r}."
|
||||
)
|
||||
|
||||
with self._lock:
|
||||
existing = self.nodes.get(node_id)
|
||||
if existing is None:
|
||||
raise MarkdownResourceNotFoundError(
|
||||
f"ContextGraph node {node_id!r} was not found."
|
||||
)
|
||||
if expected_revision is not None:
|
||||
current_revision = markdown_document_revision(
|
||||
self._node_markdown_source(existing)
|
||||
)
|
||||
if current_revision != expected_revision:
|
||||
raise MarkdownRevisionConflictError(current_revision)
|
||||
if existing == candidate:
|
||||
return False
|
||||
|
||||
# Decision index rebuilding can still reject YAML-valid property
|
||||
# shapes, so retain every affected structure until commit succeeds.
|
||||
decision_state_before = {}
|
||||
if (
|
||||
existing.node_type.lower() == "decision"
|
||||
or candidate.node_type.lower() == "decision"
|
||||
):
|
||||
for attribute in (
|
||||
"_decisions",
|
||||
"_decision_index",
|
||||
"_entity_index",
|
||||
"_temporal_index",
|
||||
):
|
||||
if not hasattr(self, attribute):
|
||||
decision_state_before[attribute] = None
|
||||
elif attribute in {"_decision_index", "_entity_index"}:
|
||||
decision_state_before[attribute] = {
|
||||
key: set(values)
|
||||
for key, values in getattr(self, attribute).items()
|
||||
}
|
||||
elif attribute == "_temporal_index":
|
||||
decision_state_before[attribute] = list(
|
||||
getattr(self, attribute)
|
||||
)
|
||||
else:
|
||||
decision_state_before[attribute] = dict(
|
||||
getattr(self, attribute)
|
||||
)
|
||||
|
||||
old_type = existing.node_type
|
||||
try:
|
||||
old_bucket = self.node_type_index.get(old_type)
|
||||
if old_bucket is not None:
|
||||
old_bucket.discard(node_id)
|
||||
if not old_bucket:
|
||||
del self.node_type_index[old_type]
|
||||
|
||||
self.nodes[node_id] = candidate
|
||||
self.node_type_index[candidate.node_type].add(node_id)
|
||||
if (
|
||||
old_type.lower() == "decision"
|
||||
or candidate.node_type.lower() == "decision"
|
||||
):
|
||||
self._sync_decision_from_node(node_id)
|
||||
payload = candidate.to_dict()
|
||||
self._analytics_cache.clear()
|
||||
except Exception:
|
||||
self.nodes[node_id] = existing
|
||||
candidate_bucket = self.node_type_index.get(candidate.node_type)
|
||||
if candidate_bucket is not None:
|
||||
candidate_bucket.discard(node_id)
|
||||
if not candidate_bucket:
|
||||
del self.node_type_index[candidate.node_type]
|
||||
self.node_type_index[old_type].add(node_id)
|
||||
for attribute, state in decision_state_before.items():
|
||||
if state is None:
|
||||
if hasattr(self, attribute):
|
||||
delattr(self, attribute)
|
||||
else:
|
||||
restored = (
|
||||
defaultdict(set, state)
|
||||
if attribute in {"_decision_index", "_entity_index"}
|
||||
else state
|
||||
)
|
||||
setattr(self, attribute, restored)
|
||||
raise
|
||||
|
||||
self._emit_mutation("UPDATE_NODE", node_id, payload)
|
||||
return True
|
||||
|
||||
def save_to_file(
|
||||
self, path: Union[str, Path], format: str = "json"
|
||||
) -> None:
|
||||
@@ -5104,42 +4947,32 @@ class ContextGraph:
|
||||
def _sync_decision_from_node(self, node_id: str) -> None:
|
||||
"""Synchronise a single decision index entry from the node store.
|
||||
|
||||
Called after ``add_node_attribute`` mutates a decision node and after
|
||||
``apply_node_markdown`` replaces a node whose old or new type is
|
||||
``"decision"``, so that ``_decisions`` and the derived indexes stay
|
||||
consistent without requiring a full rebuild of all decisions.
|
||||
|
||||
Temporal index cleanup (``_temporal_index``) runs unconditionally
|
||||
before the node-type guard so that stale entries are removed even when
|
||||
transitioning a decision node to a non-decision type. Callers are
|
||||
expected to ensure this is only invoked when at least one of the
|
||||
current or previous node types is ``"decision"``; callers that bypass
|
||||
that invariant will have ``node_id`` silently removed from
|
||||
``_temporal_index`` even if it was never a decision node.
|
||||
Called after ``add_node_attribute`` mutates a decision node so that
|
||||
``_decisions`` and the derived indexes stay consistent without
|
||||
requiring a full rebuild of all decisions.
|
||||
"""
|
||||
node = self.nodes.get(node_id)
|
||||
if node is None:
|
||||
return
|
||||
if (getattr(node, "node_type", None) or "").lower() != "decision":
|
||||
return
|
||||
|
||||
if not hasattr(self, "_decisions"):
|
||||
# Indexes don't exist yet — a full rebuild is safer.
|
||||
self._rebuild_decision_indexes()
|
||||
return
|
||||
|
||||
# Remove stale index entries before deciding whether the current node
|
||||
# still belongs in the decision indexes.
|
||||
old = self._decisions.pop(node_id, None)
|
||||
# Remove stale index entries for this decision ID.
|
||||
old = self._decisions.get(node_id)
|
||||
if old:
|
||||
old_cat = old.get("category", "")
|
||||
if old_cat:
|
||||
if old_cat and node_id in self._decision_index.get(old_cat, set()):
|
||||
self._decision_index[old_cat].discard(node_id)
|
||||
for ent in old.get("entities", []):
|
||||
self._entity_index[ent].discard(node_id)
|
||||
self._temporal_index = [
|
||||
(nid, ts) for nid, ts in self._temporal_index if nid != node_id
|
||||
]
|
||||
|
||||
if node is None:
|
||||
return
|
||||
if (getattr(node, "node_type", None) or "").lower() != "decision":
|
||||
return
|
||||
self._temporal_index = [
|
||||
(nid, ts) for nid, ts in self._temporal_index if nid != node_id
|
||||
]
|
||||
|
||||
# Rebuild the entry for this node and re-insert index entries.
|
||||
meta: Dict[str, Any] = {}
|
||||
|
||||
@@ -1,25 +0,0 @@
|
||||
"""Shared revision helpers and errors for single-resource Markdown operations."""
|
||||
|
||||
import hashlib
|
||||
|
||||
|
||||
class MarkdownResourceNotFoundError(KeyError):
|
||||
"""Raised when a Markdown operation targets a missing resource."""
|
||||
|
||||
|
||||
class MarkdownIdentityError(ValueError):
|
||||
"""Raised when frontmatter changes a resource's stable identity."""
|
||||
|
||||
|
||||
class MarkdownRevisionConflictError(ValueError):
|
||||
"""Raised when a resource changed after an edit session began."""
|
||||
|
||||
def __init__(self, current_revision: str) -> None:
|
||||
super().__init__("Markdown resource revision does not match.")
|
||||
self.current_revision = current_revision
|
||||
|
||||
|
||||
def markdown_document_revision(source: str) -> str:
|
||||
"""Return the stable revision token for a canonical Markdown document."""
|
||||
digest = hashlib.sha256(source.encode("utf-8")).hexdigest()
|
||||
return f"sha256:{digest}"
|
||||
+74
-30
@@ -8,19 +8,16 @@ from contextlib import asynccontextmanager
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import Depends, FastAPI, HTTPException, Request
|
||||
from fastapi import Depends, FastAPI, HTTPException, Request, WebSocket, WebSocketDisconnect
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
|
||||
from .. import __version__
|
||||
from ..context.agent_memory import AgentMemory
|
||||
from ..context.context_graph import ContextGraph
|
||||
from .dependencies import anonymous_access_allowed, get_expected_api_key, require_auth
|
||||
from .markdown_resources import MarkdownResourceRegistry
|
||||
from .runtime import explorer_capabilities, install_mutation_bridge
|
||||
from .dependencies import anonymous_access_allowed, get_expected_api_key, is_valid_api_key, require_auth
|
||||
from .session import GraphSession
|
||||
from .ws import ConnectionManager, install_graph_updates_websocket
|
||||
from .ws import ConnectionManager
|
||||
|
||||
|
||||
def _read_int_env(name: str, default: int) -> int:
|
||||
@@ -56,23 +53,37 @@ def _read_explorer_settings() -> dict:
|
||||
}
|
||||
|
||||
|
||||
def _install_mutation_bridge(app: FastAPI, session: GraphSession) -> None:
|
||||
if getattr(session.graph, "_mutation_bridge_installed", False):
|
||||
return
|
||||
session.graph._mutation_bridge_installed = True
|
||||
previous_callback = getattr(session.graph, "mutation_callback", None)
|
||||
|
||||
def on_mutation(event_type: str, entity_id: str, payload: dict) -> None:
|
||||
session.handle_graph_mutation(event_type, entity_id, payload)
|
||||
if callable(previous_callback):
|
||||
previous_callback(event_type, entity_id, payload)
|
||||
loop = getattr(app.state, "event_loop", None)
|
||||
manager = getattr(app.state, "ws_manager", None)
|
||||
if loop is None or manager is None or loop.is_closed():
|
||||
return
|
||||
message = {
|
||||
"event_type": event_type,
|
||||
"entity_id": entity_id,
|
||||
"payload": payload,
|
||||
}
|
||||
asyncio.run_coroutine_threadsafe(
|
||||
manager.broadcast("graph_mutation", message),
|
||||
loop,
|
||||
)
|
||||
|
||||
session.graph.mutation_callback = on_mutation
|
||||
|
||||
|
||||
def create_app(
|
||||
session: Optional[GraphSession] = None,
|
||||
provenance_storage_path: Optional[str] = None,
|
||||
agent_memory: Optional[AgentMemory] = None,
|
||||
) -> FastAPI:
|
||||
"""Create an Explorer application over live graph and memory objects.
|
||||
|
||||
Args:
|
||||
session: Graph session exposed by the Explorer. A new in-memory graph
|
||||
session is created when omitted.
|
||||
provenance_storage_path: Optional per-app provenance database path.
|
||||
agent_memory: Existing AgentMemory instance to expose in the Memories
|
||||
workspace. The workspace is unavailable when omitted.
|
||||
|
||||
Returns:
|
||||
Configured FastAPI application.
|
||||
"""
|
||||
settings = _read_explorer_settings()
|
||||
prov_path = provenance_storage_path or settings.get("provenance_storage_path")
|
||||
if session is None:
|
||||
@@ -84,7 +95,6 @@ def create_app(
|
||||
active_session = session
|
||||
if prov_path is not None:
|
||||
active_session.set_provenance_storage_path(prov_path)
|
||||
markdown_resources = MarkdownResourceRegistry(active_session.graph, agent_memory)
|
||||
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI):
|
||||
@@ -107,9 +117,7 @@ def create_app(
|
||||
app.state.event_loop = asyncio.get_running_loop()
|
||||
app.state.ws_manager = ConnectionManager()
|
||||
app.state.session = active_session
|
||||
app.state.agent_memory = agent_memory
|
||||
app.state.markdown_resources = markdown_resources
|
||||
install_mutation_bridge(app, active_session)
|
||||
_install_mutation_bridge(app, active_session)
|
||||
yield
|
||||
|
||||
app = FastAPI(
|
||||
@@ -131,7 +139,7 @@ def create_app(
|
||||
CORSMiddleware,
|
||||
allow_origins=settings["allowed_origins"],
|
||||
allow_credentials=_allow_credentials,
|
||||
allow_methods=["GET", "POST", "PUT", "DELETE", "OPTIONS"],
|
||||
allow_methods=["GET", "POST", "DELETE", "OPTIONS"],
|
||||
allow_headers=["Content-Type", "Authorization", "X-API-Key"],
|
||||
max_age=600,
|
||||
)
|
||||
@@ -162,8 +170,6 @@ def create_app(
|
||||
from .routes.enrich import router as enrich_router
|
||||
from .routes.export_import import router as export_import_router
|
||||
from .routes.graph import router as graph_router
|
||||
from .routes.markdown import router as markdown_router
|
||||
from .routes.memories import router as memories_router
|
||||
from .routes.ontology import router as ontology_router
|
||||
from .routes.provenance import router as provenance_router
|
||||
from .routes.sparql import router as sparql_router
|
||||
@@ -177,15 +183,54 @@ def create_app(
|
||||
app.include_router(temporal_router, dependencies=_auth)
|
||||
app.include_router(enrich_router, dependencies=_auth)
|
||||
app.include_router(export_import_router, dependencies=_auth)
|
||||
app.include_router(markdown_router, dependencies=_auth)
|
||||
app.include_router(memories_router, dependencies=_auth)
|
||||
app.include_router(annotations_router, dependencies=_auth)
|
||||
app.include_router(sparql_router, dependencies=_auth)
|
||||
app.include_router(provenance_router, dependencies=_auth)
|
||||
app.include_router(vocabulary_router, dependencies=_auth)
|
||||
app.include_router(ontology_router, dependencies=_auth)
|
||||
|
||||
install_graph_updates_websocket(app, settings["allowed_origins"])
|
||||
_WS_MAX_MESSAGE_BYTES = 64 * 1024 # 64 KB — control messages only
|
||||
|
||||
@app.websocket("/ws/graph-updates")
|
||||
async def websocket_endpoint(websocket: WebSocket):
|
||||
# CORSMiddleware doesn't cover WebSocket handshakes (Starlette's
|
||||
# CORS support only wraps HTTP), so under SEMANTICA_ALLOW_ANONYMOUS
|
||||
# the key check below accepts any origin — loopback binding isn't a
|
||||
# boundary against a browser, since any page the operator has open
|
||||
# can still reach ws://localhost:.../ws/graph-updates directly.
|
||||
# Reject a foreign Origin explicitly here, against the same
|
||||
# allowlist CORSMiddleware already enforces for HTTP
|
||||
# (GHSA-4643-wpgq-w329). Browsers always send Origin on a
|
||||
# cross-origin WebSocket handshake; native/CLI clients omit it
|
||||
# entirely, so a missing Origin is allowed through — the browser is
|
||||
# the only threat this check is closing.
|
||||
origin = websocket.headers.get("origin")
|
||||
allowed_origins = app.state.explorer_settings["allowed_origins"]
|
||||
if origin is not None and origin not in allowed_origins:
|
||||
await websocket.close(code=4403) # forbidden
|
||||
return
|
||||
|
||||
# Browsers can't set custom headers on a WebSocket handshake, so
|
||||
# accept the key via header (non-browser clients) or query param
|
||||
# (browser clients), same SEMANTICA_API_KEY the REST routes check.
|
||||
candidate = websocket.headers.get("x-api-key") or websocket.query_params.get("api_key")
|
||||
if not is_valid_api_key(candidate):
|
||||
await websocket.close(code=4401) # unauthorized
|
||||
return
|
||||
|
||||
manager: ConnectionManager = app.state.ws_manager
|
||||
await manager.connect(websocket)
|
||||
await manager.send_personal(websocket, "connection_ack", {"connected": True})
|
||||
try:
|
||||
while True:
|
||||
message = await websocket.receive_text()
|
||||
if len(message) > _WS_MAX_MESSAGE_BYTES:
|
||||
await websocket.close(code=1009) # 1009 = message too big
|
||||
break
|
||||
if message.strip().lower() == "ping":
|
||||
await manager.send_personal(websocket, "pong", {"ok": True})
|
||||
except WebSocketDisconnect:
|
||||
manager.disconnect(websocket)
|
||||
|
||||
@app.get("/", include_in_schema=False)
|
||||
async def root():
|
||||
@@ -224,7 +269,6 @@ def create_app(
|
||||
"name": "Semantica Knowledge Explorer",
|
||||
"version": __version__,
|
||||
"status": "active",
|
||||
"capabilities": explorer_capabilities(agent_memory),
|
||||
}
|
||||
|
||||
static_dir = Path(__file__).resolve().parent.parent / "static"
|
||||
|
||||
@@ -14,8 +14,6 @@ from typing import Optional
|
||||
from fastapi import Request, HTTPException, Security, status
|
||||
from fastapi.security.api_key import APIKeyHeader
|
||||
|
||||
from ..context.agent_memory import AgentMemory
|
||||
from .markdown_resources import MarkdownResourceRegistry
|
||||
from .session import GraphSession
|
||||
|
||||
_api_key_header = APIKeyHeader(name="X-API-Key", auto_error=False)
|
||||
@@ -82,25 +80,3 @@ def get_session(request: Request) -> GraphSession:
|
||||
detail="GraphSession not initialized."
|
||||
)
|
||||
return request.app.state.session
|
||||
|
||||
|
||||
def get_markdown_resources(request: Request) -> MarkdownResourceRegistry:
|
||||
"""Retrieve the Markdown resource registry stored on ``app.state``."""
|
||||
resources = getattr(request.app.state, "markdown_resources", None)
|
||||
if resources is None:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
|
||||
detail="Markdown resources are not initialized.",
|
||||
)
|
||||
return resources
|
||||
|
||||
|
||||
def get_agent_memory(request: Request) -> AgentMemory:
|
||||
"""Retrieve the optional AgentMemory configured for Explorer."""
|
||||
memory = getattr(request.app.state, "agent_memory", None)
|
||||
if memory is None:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
|
||||
detail="AgentMemory is not configured for this Explorer instance.",
|
||||
)
|
||||
return memory
|
||||
|
||||
@@ -1,283 +0,0 @@
|
||||
"""Single-resource Markdown access for Explorer."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
from typing import Callable, Dict, Optional, Protocol, TypeVar
|
||||
|
||||
import yaml
|
||||
|
||||
from ..context.agent_memory import AgentMemory
|
||||
from ..context.context_graph import ContextGraph
|
||||
from ..context.markdown import (
|
||||
MarkdownIdentityError,
|
||||
MarkdownResourceNotFoundError,
|
||||
MarkdownRevisionConflictError,
|
||||
markdown_document_revision,
|
||||
)
|
||||
|
||||
|
||||
class MarkdownResourceKind(str, Enum):
|
||||
CONTEXT_NODE = "context-node"
|
||||
AGENT_MEMORY = "agent-memory"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class MarkdownResourceRef:
|
||||
kind: MarkdownResourceKind
|
||||
id: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class MarkdownDocument:
|
||||
resource: MarkdownResourceRef
|
||||
source: str
|
||||
body: str
|
||||
revision: str
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class MarkdownApplyResult(MarkdownDocument):
|
||||
changed: bool
|
||||
|
||||
|
||||
class MarkdownResourceError(Exception):
|
||||
"""Base class for safe, structured Explorer Markdown failures."""
|
||||
|
||||
code = "markdown_resource_error"
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
message: str,
|
||||
*,
|
||||
field: Optional[str] = None,
|
||||
current_revision: Optional[str] = None,
|
||||
) -> None:
|
||||
super().__init__(message)
|
||||
self.message = message
|
||||
self.field = field
|
||||
self.current_revision = current_revision
|
||||
|
||||
|
||||
class MarkdownResourceNotFound(MarkdownResourceError):
|
||||
code = "markdown_resource_not_found"
|
||||
|
||||
|
||||
class InvalidMarkdownFrontmatter(MarkdownResourceError):
|
||||
code = "invalid_markdown_frontmatter"
|
||||
|
||||
|
||||
class ResourceIdentityMismatch(MarkdownResourceError):
|
||||
code = "resource_identity_mismatch"
|
||||
|
||||
|
||||
class MarkdownRevisionConflict(MarkdownResourceError):
|
||||
code = "markdown_revision_conflict"
|
||||
|
||||
|
||||
class MarkdownSaveFailed(MarkdownResourceError):
|
||||
code = "markdown_save_failed"
|
||||
|
||||
|
||||
class MarkdownAdapter(Protocol):
|
||||
def export(self, resource_id: str) -> str:
|
||||
...
|
||||
|
||||
def apply(self, resource_id: str, source: str, expected_revision: str) -> bool:
|
||||
...
|
||||
|
||||
|
||||
_Result = TypeVar("_Result")
|
||||
|
||||
|
||||
def _translate_domain_errors(operation: Callable[[], _Result]) -> _Result:
|
||||
try:
|
||||
return operation()
|
||||
except MarkdownResourceNotFoundError as exc:
|
||||
raise MarkdownResourceNotFound(str(exc.args[0])) from exc
|
||||
except MarkdownRevisionConflictError as exc:
|
||||
raise MarkdownRevisionConflict(
|
||||
"This item changed after editing began. Reload the latest "
|
||||
"version before applying.",
|
||||
current_revision=exc.current_revision,
|
||||
) from exc
|
||||
except MarkdownIdentityError as exc:
|
||||
raise ResourceIdentityMismatch(str(exc), field="id") from exc
|
||||
except ValueError as exc:
|
||||
raise InvalidMarkdownFrontmatter(_safe_validation_message(exc)) from exc
|
||||
|
||||
|
||||
class ContextGraphNodeMarkdownAdapter:
|
||||
def __init__(self, graph: ContextGraph) -> None:
|
||||
self._graph = graph
|
||||
|
||||
def export(self, resource_id: str) -> str:
|
||||
return _translate_domain_errors(
|
||||
lambda: self._graph.export_node_markdown(resource_id)
|
||||
)
|
||||
|
||||
def apply(self, resource_id: str, source: str, expected_revision: str) -> bool:
|
||||
return _translate_domain_errors(
|
||||
lambda: self._graph.apply_node_markdown(
|
||||
resource_id,
|
||||
source,
|
||||
expected_revision=expected_revision,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
class AgentMemoryItemMarkdownAdapter:
|
||||
def __init__(self, memory: AgentMemory) -> None:
|
||||
self._memory = memory
|
||||
|
||||
def export(self, resource_id: str) -> str:
|
||||
return _translate_domain_errors(
|
||||
lambda: self._memory.export_item_markdown(resource_id)
|
||||
)
|
||||
|
||||
def apply(self, resource_id: str, source: str, expected_revision: str) -> bool:
|
||||
return _translate_domain_errors(
|
||||
lambda: self._memory.apply_item_markdown(
|
||||
resource_id,
|
||||
source,
|
||||
expected_revision=expected_revision,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def _safe_validation_message(exc: ValueError) -> str:
|
||||
if isinstance(exc.__cause__, yaml.YAMLError):
|
||||
return "Markdown frontmatter contains invalid YAML."
|
||||
return str(exc)
|
||||
|
||||
|
||||
def document_revision(source: str) -> str:
|
||||
"""Return the stable revision token for canonical Markdown.
|
||||
|
||||
Args:
|
||||
source: Canonical Markdown source.
|
||||
|
||||
Returns:
|
||||
A SHA-256 revision token suitable for optimistic concurrency checks.
|
||||
"""
|
||||
return markdown_document_revision(source)
|
||||
|
||||
|
||||
def markdown_body(source: str) -> str:
|
||||
"""Extract the body from canonical Markdown emitted by a domain model."""
|
||||
lines = source.splitlines(keepends=True)
|
||||
if not lines or lines[0].rstrip("\r\n") != "---":
|
||||
raise MarkdownSaveFailed("The resource produced invalid canonical Markdown.")
|
||||
closing_index = next(
|
||||
(
|
||||
index
|
||||
for index, line in enumerate(lines[1:], start=1)
|
||||
if line.rstrip("\r\n") == "---"
|
||||
),
|
||||
None,
|
||||
)
|
||||
if closing_index is None:
|
||||
raise MarkdownSaveFailed("The resource produced invalid canonical Markdown.")
|
||||
body = "".join(lines[closing_index + 1 :])
|
||||
if body.startswith("\r\n"):
|
||||
return body[2:]
|
||||
if body.startswith("\n"):
|
||||
return body[1:]
|
||||
return body
|
||||
|
||||
|
||||
class MarkdownResourceRegistry:
|
||||
"""Route Markdown operations to their owning domain models."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
context_graph: ContextGraph,
|
||||
agent_memory: Optional[AgentMemory] = None,
|
||||
) -> None:
|
||||
self._adapters: Dict[MarkdownResourceKind, MarkdownAdapter] = {
|
||||
MarkdownResourceKind.CONTEXT_NODE: ContextGraphNodeMarkdownAdapter(
|
||||
context_graph
|
||||
)
|
||||
}
|
||||
if agent_memory is not None:
|
||||
self._adapters[
|
||||
MarkdownResourceKind.AGENT_MEMORY
|
||||
] = AgentMemoryItemMarkdownAdapter(agent_memory)
|
||||
|
||||
def _adapter(self, kind: MarkdownResourceKind) -> MarkdownAdapter:
|
||||
adapter = self._adapters.get(kind)
|
||||
if adapter is None:
|
||||
raise MarkdownResourceNotFound(
|
||||
f"Markdown resource kind {kind.value!r} is not available."
|
||||
)
|
||||
return adapter
|
||||
|
||||
def read(self, ref: MarkdownResourceRef) -> MarkdownDocument:
|
||||
"""Read one resource as canonical Markdown.
|
||||
|
||||
Args:
|
||||
ref: Explicit resource kind and stable identifier.
|
||||
|
||||
Returns:
|
||||
The canonical source, body, and current revision.
|
||||
|
||||
Raises:
|
||||
MarkdownResourceError: If the resource is unavailable or invalid.
|
||||
"""
|
||||
try:
|
||||
source = self._adapter(ref.kind).export(ref.id)
|
||||
except MarkdownResourceError:
|
||||
raise
|
||||
except Exception as exc:
|
||||
raise MarkdownSaveFailed(
|
||||
"The Markdown resource could not be read."
|
||||
) from exc
|
||||
return MarkdownDocument(
|
||||
resource=ref,
|
||||
source=source,
|
||||
body=markdown_body(source),
|
||||
revision=document_revision(source),
|
||||
)
|
||||
|
||||
def apply(
|
||||
self,
|
||||
ref: MarkdownResourceRef,
|
||||
markdown: str,
|
||||
expected_revision: str,
|
||||
) -> MarkdownApplyResult:
|
||||
"""Apply validated Markdown to one existing resource.
|
||||
|
||||
Args:
|
||||
ref: Explicit resource kind and stable identifier.
|
||||
markdown: Replacement canonical Markdown.
|
||||
expected_revision: Revision observed when editing began.
|
||||
|
||||
Returns:
|
||||
The saved canonical document and whether it changed.
|
||||
|
||||
Raises:
|
||||
MarkdownResourceError: If validation, identity, persistence, or
|
||||
revision checks fail.
|
||||
"""
|
||||
try:
|
||||
changed = self._adapter(ref.kind).apply(
|
||||
ref.id,
|
||||
markdown,
|
||||
expected_revision,
|
||||
)
|
||||
except MarkdownResourceError:
|
||||
raise
|
||||
except Exception as exc:
|
||||
raise MarkdownSaveFailed(
|
||||
"The edit could not be applied. The existing item was not changed."
|
||||
) from exc
|
||||
|
||||
saved = self.read(ref)
|
||||
return MarkdownApplyResult(
|
||||
resource=saved.resource,
|
||||
source=saved.source,
|
||||
body=saved.body,
|
||||
revision=saved.revision,
|
||||
changed=changed,
|
||||
)
|
||||
@@ -87,13 +87,6 @@ def _node_response(node: dict) -> NodeResponse:
|
||||
return NodeResponse(**node)
|
||||
|
||||
|
||||
async def _get_node_or_404(node_id: str, session: GraphSession) -> NodeResponse:
|
||||
node = await asyncio.to_thread(session.get_node, node_id)
|
||||
if node is None:
|
||||
raise HTTPException(status_code=404, detail=f"Node '{node_id}' not found")
|
||||
return _node_response(node)
|
||||
|
||||
|
||||
def _edge_response(edge: dict) -> EdgeResponse:
|
||||
return EdgeResponse(**edge)
|
||||
|
||||
@@ -128,20 +121,15 @@ async def list_nodes(
|
||||
)
|
||||
|
||||
|
||||
@router.get("/node", response_model=NodeResponse)
|
||||
async def get_node_by_query(
|
||||
node_id: str = Query(..., description="Exact node ID"),
|
||||
session: GraphSession = Depends(get_session),
|
||||
):
|
||||
return await _get_node_or_404(node_id, session)
|
||||
|
||||
|
||||
@router.get("/node/{node_id}", response_model=NodeResponse)
|
||||
async def get_node(
|
||||
node_id: str,
|
||||
session: GraphSession = Depends(get_session),
|
||||
):
|
||||
return await _get_node_or_404(node_id, session)
|
||||
node = await asyncio.to_thread(session.get_node, node_id)
|
||||
if node is None:
|
||||
raise HTTPException(status_code=404, detail=f"Node '{node_id}' not found")
|
||||
return _node_response(node)
|
||||
|
||||
|
||||
@router.get("/node/{node_id}/neighbors", response_model=list[NeighborResponse])
|
||||
@@ -453,7 +441,7 @@ async def distance_matrix(
|
||||
embeddings = _get_cached_embeddings(session)
|
||||
src_embedding = embeddings.get(src)
|
||||
tgt_embedding = embeddings.get(tgt)
|
||||
|
||||
|
||||
if src_embedding is None or tgt_embedding is None:
|
||||
val = None
|
||||
else:
|
||||
@@ -463,7 +451,7 @@ async def distance_matrix(
|
||||
tgt_vec = np.array(tgt_embedding)
|
||||
sim = np.dot(src_vec, tgt_vec) / (np.linalg.norm(src_vec) * np.linalg.norm(tgt_vec))
|
||||
val = 1.0 - float(sim) if isinstance(sim, (int, float)) else None
|
||||
|
||||
|
||||
matrix[i][j] = val
|
||||
matrix[j][i] = val
|
||||
elif path_finder is not None:
|
||||
|
||||
@@ -1,115 +0,0 @@
|
||||
"""Explorer routes for canonical Markdown resources."""
|
||||
|
||||
from typing import NoReturn
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, status
|
||||
|
||||
from ..dependencies import get_markdown_resources
|
||||
from ..markdown_resources import (
|
||||
InvalidMarkdownFrontmatter,
|
||||
MarkdownApplyResult,
|
||||
MarkdownDocument,
|
||||
MarkdownResourceError,
|
||||
MarkdownResourceKind,
|
||||
MarkdownResourceNotFound,
|
||||
MarkdownResourceRef,
|
||||
MarkdownResourceRegistry,
|
||||
MarkdownRevisionConflict,
|
||||
ResourceIdentityMismatch,
|
||||
)
|
||||
from ..schemas import (
|
||||
MarkdownApplyRequest,
|
||||
MarkdownApplyResponse,
|
||||
MarkdownDocumentResponse,
|
||||
)
|
||||
|
||||
router = APIRouter(prefix="/api/markdown", tags=["markdown"])
|
||||
|
||||
|
||||
def _resource_ref(kind: str, resource_id: str) -> MarkdownResourceRef:
|
||||
try:
|
||||
resource_kind = MarkdownResourceKind(kind)
|
||||
except ValueError:
|
||||
_raise_http_error(
|
||||
MarkdownResourceNotFound(
|
||||
f"Markdown resource kind {kind!r} is not available."
|
||||
)
|
||||
)
|
||||
return MarkdownResourceRef(kind=resource_kind, id=resource_id)
|
||||
|
||||
|
||||
def _error_detail(error: MarkdownResourceError) -> dict:
|
||||
detail = {"code": error.code, "message": error.message}
|
||||
if error.field is not None:
|
||||
detail["field"] = error.field
|
||||
if error.current_revision is not None:
|
||||
detail["current_revision"] = error.current_revision
|
||||
return detail
|
||||
|
||||
|
||||
def _raise_http_error(error: MarkdownResourceError) -> NoReturn:
|
||||
if isinstance(error, MarkdownResourceNotFound):
|
||||
status_code = status.HTTP_404_NOT_FOUND
|
||||
elif isinstance(error, MarkdownRevisionConflict):
|
||||
status_code = status.HTTP_409_CONFLICT
|
||||
elif isinstance(error, (InvalidMarkdownFrontmatter, ResourceIdentityMismatch)):
|
||||
status_code = status.HTTP_422_UNPROCESSABLE_ENTITY
|
||||
else:
|
||||
status_code = status.HTTP_500_INTERNAL_SERVER_ERROR
|
||||
raise HTTPException(status_code=status_code, detail=_error_detail(error)) from error
|
||||
|
||||
|
||||
def _document_response(
|
||||
document: MarkdownDocument,
|
||||
) -> MarkdownDocumentResponse:
|
||||
return MarkdownDocumentResponse(
|
||||
resource={
|
||||
"kind": document.resource.kind.value,
|
||||
"id": document.resource.id,
|
||||
},
|
||||
source=document.source,
|
||||
body=document.body,
|
||||
revision=document.revision,
|
||||
editable=True,
|
||||
)
|
||||
|
||||
|
||||
def _apply_response(result: MarkdownApplyResult) -> MarkdownApplyResponse:
|
||||
document = _document_response(result)
|
||||
return MarkdownApplyResponse(**document.model_dump(), changed=result.changed)
|
||||
|
||||
|
||||
@router.get(
|
||||
"/{kind}/{resource_id:path}",
|
||||
response_model=MarkdownDocumentResponse,
|
||||
)
|
||||
def read_markdown_resource(
|
||||
kind: str,
|
||||
resource_id: str,
|
||||
resources: MarkdownResourceRegistry = Depends(get_markdown_resources),
|
||||
) -> MarkdownDocumentResponse:
|
||||
try:
|
||||
return _document_response(resources.read(_resource_ref(kind, resource_id)))
|
||||
except MarkdownResourceError as error:
|
||||
_raise_http_error(error)
|
||||
|
||||
|
||||
@router.put(
|
||||
"/{kind}/{resource_id:path}",
|
||||
response_model=MarkdownApplyResponse,
|
||||
)
|
||||
def apply_markdown_resource(
|
||||
kind: str,
|
||||
resource_id: str,
|
||||
request: MarkdownApplyRequest,
|
||||
resources: MarkdownResourceRegistry = Depends(get_markdown_resources),
|
||||
) -> MarkdownApplyResponse:
|
||||
try:
|
||||
result = resources.apply(
|
||||
_resource_ref(kind, resource_id),
|
||||
request.markdown,
|
||||
request.expected_revision,
|
||||
)
|
||||
return _apply_response(result)
|
||||
except MarkdownResourceError as error:
|
||||
_raise_http_error(error)
|
||||
@@ -1,41 +0,0 @@
|
||||
"""Minimal AgentMemory selection surface for Explorer."""
|
||||
|
||||
from fastapi import APIRouter, Depends, Query
|
||||
|
||||
from ...context.agent_memory import AgentMemory
|
||||
from ..dependencies import get_agent_memory
|
||||
from ..schemas import MemoryListResponse, MemorySummaryResponse
|
||||
|
||||
router = APIRouter(prefix="/api/memories", tags=["memories"])
|
||||
|
||||
|
||||
@router.get("", response_model=MemoryListResponse)
|
||||
def list_memories(
|
||||
skip: int = Query(default=0, ge=0),
|
||||
limit: int = Query(default=100, ge=1, le=100),
|
||||
memory: AgentMemory = Depends(get_agent_memory),
|
||||
) -> MemoryListResponse:
|
||||
records, total = memory.list_snapshot(offset=skip, limit=limit)
|
||||
items = []
|
||||
for record in records:
|
||||
metadata = record.get("metadata") or {}
|
||||
content = record.get("content") or ""
|
||||
excerpt = " ".join(str(content).split())[:160]
|
||||
items.append(
|
||||
MemorySummaryResponse(
|
||||
id=record["memory_id"],
|
||||
type=str(metadata.get("type") or "general"),
|
||||
excerpt=excerpt,
|
||||
updated_at=(
|
||||
str(metadata["updated_at"])
|
||||
if metadata.get("updated_at") is not None
|
||||
else None
|
||||
),
|
||||
)
|
||||
)
|
||||
return MemoryListResponse(
|
||||
items=items,
|
||||
total=total,
|
||||
skip=skip,
|
||||
limit=limit,
|
||||
)
|
||||
@@ -234,12 +234,6 @@ class EntityDetailResponse(BaseModel):
|
||||
properties: Dict[str, Any] = Field(default_factory=dict)
|
||||
|
||||
|
||||
class OntologyGraphResponse(BaseModel):
|
||||
uri: str
|
||||
nodes: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
edges: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
|
||||
|
||||
class SKOSScheme(BaseModel):
|
||||
uri: str
|
||||
title: str
|
||||
@@ -670,7 +664,6 @@ def _convert_ontology_to_graph(ontology_dict: Dict[str, Any]) -> Tuple[List[Dict
|
||||
"rdfs:label": cls.get("label", cls.get("name", "")),
|
||||
"rdfs:comment": cls.get("description", ""),
|
||||
"uri": cls_uri,
|
||||
"scheme_uri": ontology_uri,
|
||||
},
|
||||
}
|
||||
nodes.append(node)
|
||||
@@ -687,21 +680,14 @@ def _convert_ontology_to_graph(ontology_dict: Dict[str, Any]) -> Tuple[List[Dict
|
||||
# Add property nodes and edges
|
||||
for prop in ontology_dict.get("properties", []):
|
||||
prop_uri = prop.get("uri", f"temp:prop:{uuid.uuid4().hex[:12]}")
|
||||
property_type = {
|
||||
"object": "owl:ObjectProperty",
|
||||
"data": "owl:DatatypeProperty",
|
||||
"datatype": "owl:DatatypeProperty",
|
||||
"annotation": "owl:AnnotationProperty",
|
||||
}.get(str(prop.get("type", "object")).lower(), "owl:ObjectProperty")
|
||||
node = {
|
||||
"id": prop_uri,
|
||||
"type": property_type,
|
||||
"type": f"owl:{prop.get('type', 'Object').title()}Property",
|
||||
"content": prop.get("name", prop.get("label", "")),
|
||||
"properties": {
|
||||
"rdfs:label": prop.get("label", prop.get("name", "")),
|
||||
"rdfs:comment": prop.get("description", ""),
|
||||
"uri": prop_uri,
|
||||
"scheme_uri": ontology_uri,
|
||||
},
|
||||
}
|
||||
nodes.append(node)
|
||||
@@ -762,38 +748,14 @@ def _node_source_ontology(node: Dict[str, Any]) -> Optional[str]:
|
||||
)
|
||||
|
||||
|
||||
def _node_belongs_to_ontology(
|
||||
node: Dict[str, Any],
|
||||
ontology_uri: str,
|
||||
known_ontology_uris: Optional[set[str]] = None,
|
||||
) -> bool:
|
||||
def _node_belongs_to_ontology(node: Dict[str, Any], ontology_uri: str) -> bool:
|
||||
nid = node.get("id", "")
|
||||
if nid == ontology_uri:
|
||||
return True
|
||||
owner = _node_source_ontology(node)
|
||||
if owner:
|
||||
return owner == ontology_uri
|
||||
if known_ontology_uris:
|
||||
namespace_owners = [
|
||||
candidate
|
||||
for candidate in known_ontology_uris
|
||||
if nid == candidate
|
||||
or nid.startswith(
|
||||
(candidate.rstrip("#/") + "#", candidate.rstrip("#/") + "/")
|
||||
)
|
||||
]
|
||||
if namespace_owners and max(namespace_owners, key=len) != ontology_uri:
|
||||
return False
|
||||
if _node_source_ontology(node) == ontology_uri:
|
||||
return True
|
||||
stem = ontology_uri.rstrip("#/")
|
||||
if not nid.startswith((stem + "#", stem + "/")):
|
||||
return False
|
||||
# Prefix ownership only extends to names minted directly in the
|
||||
# ontology's namespace (<stem>#Term or <stem>/Term). Any further
|
||||
# delimiter marks a nested vocabulary (<stem>/child#Term,
|
||||
# <stem>/child/Term), which must not be absorbed into the parent
|
||||
# until it is registered or carries an explicit owner.
|
||||
local_name = nid[len(stem) + 1 :]
|
||||
return "#" not in local_name and "/" not in local_name
|
||||
return nid.startswith((stem + "#", stem + "/"))
|
||||
|
||||
|
||||
def _is_ontology_entity(node: Dict[str, Any]) -> bool:
|
||||
@@ -1259,8 +1221,7 @@ def _parse_rdf_sync(content: bytes, fmt: str) -> tuple:
|
||||
metadata.setdefault("description", str(obj))
|
||||
break
|
||||
|
||||
synthetic_uri = "uri" not in metadata
|
||||
if synthetic_uri:
|
||||
if "uri" not in metadata:
|
||||
metadata["uri"] = f"urn:semantica:onto:{uuid.uuid4().hex[:8]}"
|
||||
metadata.setdefault("name", metadata["uri"].rsplit("/", 1)[-1].rsplit("#", 1)[-1] or "Unnamed")
|
||||
metadata["triple_count"] = len(g)
|
||||
@@ -1307,20 +1268,6 @@ def _parse_rdf_sync(content: bytes, fmt: str) -> tuple:
|
||||
"weight": 1.0,
|
||||
})
|
||||
|
||||
if synthetic_uri:
|
||||
# No owl:Ontology / skos:ConceptScheme declaration exists, so the
|
||||
# synthetic registry URI shares no namespace with any node. Ownership
|
||||
# must be recorded explicitly, and the editor needs a matching graph
|
||||
# node, or the registered ontology resolves to an empty core and 404s.
|
||||
for node in nodes:
|
||||
node["properties"].setdefault("scheme_uri", metadata["uri"])
|
||||
nodes.append({
|
||||
"id": metadata["uri"],
|
||||
"type": "owl:Ontology",
|
||||
"content": metadata["name"],
|
||||
"properties": {"rdfs:label": metadata["name"], "uri": metadata["uri"]},
|
||||
})
|
||||
|
||||
return nodes, edges, metadata
|
||||
|
||||
|
||||
@@ -1821,107 +1768,6 @@ async def search_entities(
|
||||
return results
|
||||
|
||||
|
||||
@router.get("/graph", response_model=OntologyGraphResponse)
|
||||
async def get_ontology_graph(
|
||||
request: Request,
|
||||
uri: str = Query(..., min_length=1),
|
||||
session: GraphSession = Depends(get_session),
|
||||
):
|
||||
"""Return the editable schema subgraph for one registered ontology."""
|
||||
registry = _get_registry(request)
|
||||
ontology_nodes: List[Dict[str, Any]] = []
|
||||
for node_type in _ONTOLOGY_TYPES:
|
||||
nodes, _ = await asyncio.to_thread(
|
||||
session.get_nodes, node_type=node_type, skip=0, limit=2**63 - 1
|
||||
)
|
||||
ontology_nodes.extend(nodes)
|
||||
known_ontology_uris = set(registry) | {
|
||||
str(node.get("id", "")) for node in ontology_nodes if node.get("id")
|
||||
}
|
||||
if uri not in known_ontology_uris:
|
||||
raise HTTPException(status_code=404, detail="Ontology not found in registry.")
|
||||
|
||||
schema_types = _CLASS_TYPES | _PROPERTY_TYPES | _CONCEPT_TYPES | _ONTOLOGY_TYPES
|
||||
candidates_by_id: Dict[str, Dict[str, Any]] = {}
|
||||
for node_type in schema_types:
|
||||
nodes, _ = await asyncio.to_thread(
|
||||
session.get_nodes, node_type=node_type, skip=0, limit=2**63 - 1
|
||||
)
|
||||
candidates_by_id.update(
|
||||
(str(node.get("id", "")), node) for node in nodes if node.get("id")
|
||||
)
|
||||
|
||||
core_node_ids = {
|
||||
str(node.get("id", ""))
|
||||
for node in candidates_by_id.values()
|
||||
if _node_belongs_to_ontology(node, uri, known_ontology_uris)
|
||||
}
|
||||
if not core_node_ids:
|
||||
raise HTTPException(status_code=404, detail="Ontology graph not found.")
|
||||
|
||||
structure_edge_types = {
|
||||
"rdf:type",
|
||||
"rdfs:subClassOf",
|
||||
"rdfs:domain",
|
||||
"rdfs:range",
|
||||
"owl:disjointWith",
|
||||
"owl:equivalentClass",
|
||||
"owl:equivalentProperty",
|
||||
"owl:inverseOf",
|
||||
"skos:broader",
|
||||
"skos:narrower",
|
||||
"skos:related",
|
||||
}
|
||||
selected_edges: List[Dict[str, Any]] = []
|
||||
for edge_type in structure_edge_types:
|
||||
edges, _ = await asyncio.to_thread(
|
||||
session.get_edges,
|
||||
edge_type=edge_type,
|
||||
skip=0,
|
||||
limit=2**63 - 1,
|
||||
)
|
||||
# Keep only edges whose source is a core node: the requested ontology
|
||||
# may reference outward (e.g. rdfs:range to an external vocabulary),
|
||||
# but an unrelated ontology's property pointing at a core class must
|
||||
# not leak inward.
|
||||
selected_edges.extend(
|
||||
edge for edge in edges
|
||||
if str(edge.get("source", "")) in core_node_ids
|
||||
)
|
||||
if (
|
||||
len(core_node_ids) > _MAX_ANALYSIS_NODES
|
||||
or len(selected_edges) > _MAX_ANALYSIS_NODES
|
||||
):
|
||||
raise HTTPException(
|
||||
status_code=413,
|
||||
detail=(
|
||||
"Ontology editor graph exceeds the maximum size "
|
||||
f"({_MAX_ANALYSIS_NODES} nodes or edges)."
|
||||
),
|
||||
)
|
||||
|
||||
selected_node_ids = set(core_node_ids)
|
||||
for edge in selected_edges:
|
||||
selected_node_ids.add(str(edge.get("source", "")))
|
||||
selected_node_ids.add(str(edge.get("target", "")))
|
||||
|
||||
selected_nodes = [candidates_by_id[node_id] for node_id in core_node_ids]
|
||||
for node_id in selected_node_ids - core_node_ids:
|
||||
external = await asyncio.to_thread(session.get_node, node_id)
|
||||
if external is not None:
|
||||
selected_nodes.append(external)
|
||||
selected_nodes.sort(key=lambda node: str(node.get("id", "")))
|
||||
selected_edges.sort(
|
||||
key=lambda edge: (
|
||||
str(edge.get("source", "")),
|
||||
str(edge.get("type", "")),
|
||||
str(edge.get("target", "")),
|
||||
str(edge.get("id", "")),
|
||||
)
|
||||
)
|
||||
return OntologyGraphResponse(uri=uri, nodes=selected_nodes, edges=selected_edges)
|
||||
|
||||
|
||||
@router.get("/entity/{entity_uri:path}", response_model=EntityDetailResponse)
|
||||
async def get_entity_detail(
|
||||
entity_uri: str,
|
||||
@@ -2877,8 +2723,7 @@ async def validate_shacl(
|
||||
status="error",
|
||||
message=(
|
||||
f"SHACL Turtle size ({len(_shacl_bytes)} bytes) "
|
||||
f"exceeds maximum allowed size ({_MAX_SHACL_TURTLE_BYTES} bytes); "
|
||||
f"set SEMANTICA_MAX_SHACL_TURTLE_BYTES to raise the limit."
|
||||
f"exceeds maximum allowed size ({_MAX_SHACL_TURTLE_BYTES} bytes)."
|
||||
),
|
||||
violations=[],
|
||||
)
|
||||
@@ -2895,8 +2740,7 @@ async def validate_shacl(
|
||||
status="error",
|
||||
message=(
|
||||
f"SHACL graph triple count ({len(g)}) "
|
||||
f"exceeds maximum allowed limit ({_MAX_SHACL_TRIPLES}); "
|
||||
f"set SEMANTICA_MAX_SHACL_TRIPLES to raise the limit."
|
||||
f"exceeds maximum allowed limit ({_MAX_SHACL_TRIPLES})."
|
||||
),
|
||||
violations=[],
|
||||
)
|
||||
@@ -2947,8 +2791,7 @@ async def validate_shacl(
|
||||
conforms=False,
|
||||
status="error",
|
||||
message=(
|
||||
f"SHACL validation timed out after {_MAX_SHACL_TIMEOUT_SECONDS} seconds; "
|
||||
f"set SEMANTICA_MAX_SHACL_TIMEOUT to raise the timeout."
|
||||
f"SHACL validation timed out after {_MAX_SHACL_TIMEOUT_SECONDS} seconds."
|
||||
),
|
||||
violations=[],
|
||||
)
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user