docs: replace all CardGroup/Card blocks with animated bullet points across all 50 docs pages (#648)

- Fix What's new → link in Info banner (now a proper <a> tag, always clickable) - Replace 4-stat CardGroup on index with inline premium stats row - Convert every <CardGroup>/<Card> block site-wide to markdown bullet lists: content sections → bold-title bullets with sub-bullets, nav cards → [Title](href) — description - Add cursor-animated list item hover effects to custom.css: green inset left border, subtle background tint, marker color change on hover - Affects index, getting-started, quickstart, concepts, modules, faq, architecture, installation, cookbook, glossary, learning-more, explorer-setup, cli-setup, community, contributing-guide, governance, citation, project-license, all integrations pages, and all 20+ reference module pages
2026-08-29 04:26:20 +00:00 · 2026-06-17 23:18:40 +05:30
parent 0f9a651527
commit 25289023fe
50 changed files with 587 additions and 1522 deletions
@@ -185,17 +185,7 @@ Centralized `ConfigManager` with environment variable overrides. No magic defaul
 | **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) |
-<CardGroup cols={2}>
+- [Modules](modules) — Full module documentation with code examples.
-  <Card title="Modules" icon="cubes" href="modules">
+- [Learning More](learning-more) — Configuration reference, performance guide, and troubleshooting.
-    Full module documentation with code examples.
+- [Pipeline Reference](reference/pipeline) — Pipeline orchestration, workers, and retry policies.
-  </Card>
+- [Core Reference](reference/core) — Framework lifecycle, plugin registry, and configuration.
  <Card title="Learning More" icon="graduation-cap" href="learning-more">
    Configuration reference, performance guide, and troubleshooting.
  </Card>
  <Card title="Pipeline Reference" icon="gear" href="reference/pipeline">
    Pipeline orchestration, workers, and retry policies.
  </Card>
  <Card title="Core Reference" icon="network-wired" href="reference/core">
    Framework lifecycle, plugin registry, and configuration.
  </Card>
 </CardGroup>
@@ -109,6 +109,47 @@ nav a,
  transition: color 0.15s ease !important;
 }
 /* ============================================================
   BULLET POINTS — cursor-animated hover (premium feel)
   ============================================================ */
 ul > li,
 ol > li {
  position: relative;
  transition:
    background-color 0.18s ease,
    box-shadow 0.18s ease,
    color 0.15s ease;
  border-radius: 4px;
  cursor: default;
 }
 ul > li:hover,
 ol > li:hover {
  background-color: rgba(16, 185, 129, 0.06);
  box-shadow: inset 3px 0 0 #10B981;
  color: rgba(255, 255, 255, 0.95);
 }
 /* Animate the bullet marker green on hover */
 ul > li:hover::marker,
 ol > li:hover::marker {
  color: #10B981;
 }
 /* Slide-in left accent bar for nested lists */
 ul > li > ul > li:hover,
 ol > li > ul > li:hover {
  background-color: rgba(16, 185, 129, 0.04);
  box-shadow: inset 2px 0 0 rgba(16, 185, 129, 0.6);
 }
 /* Strong text inside list items — subtle green tint on parent hover */
 ul > li:hover > strong,
 ol > li:hover > strong {
  color: #10B981;
  transition: color 0.15s ease;
 }
 /* ============================================================
   HIDE THEME TOGGLE (moon / sun emoji button)
   ============================================================ */
@@ -49,11 +49,5 @@ Published research using Semantica? [Let us know](https://github.com/semantica-a
 ## See Also
-<CardGroup cols={2}>
+- [License](project-license) — MIT License details.
-  <Card title="License" icon="file-contract" href="project-license">
+- [Community](community) — Connect with the Semantica community.
    MIT License details.
  </Card>
  <Card title="Community" icon="users" href="community">
    Connect with the Semantica community.
  </Card>
 </CardGroup>
@@ -49,23 +49,11 @@ python -c "import semantica; print(semantica.__version__)"
 ## When to Use Each Command
-<CardGroup cols={2}>
+- **semantica** — The general-purpose CLI. Use it for one-off pipeline runs, entity extraction, and graph operations from a shell script or CI job.
-  <Card title="semantica" icon="terminal">
+- **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.
-    The general-purpose CLI. Use it for one-off pipeline runs, entity extraction, and graph operations from a shell script or CI job.
+- **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.
-  </Card>
+- **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).
-  <Card title="semantica-server" icon="server">
+- **semantica-mcp** — Runs the MCP server over stdio. Configure it in your MCP client's settings file to expose all 12 tools and 3 resources to Claude Desktop, Cursor, Windsurf, or any MCP-aware client. See [MCP Server](reference/mcp_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.
  </Card>
  <Card title="semantica-worker" icon="gears">
    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.
  </Card>
  <Card title="semantica-explorer" icon="map">
    Launches the browser dashboard. Requires `pip install semantica[explorer]`. Use this to explore a saved knowledge graph interactively. See [Explorer Setup](explorer-setup).
  </Card>
  <Card title="semantica-mcp" icon="plug">
    Runs the MCP server over stdio. Configure it in your MCP client's settings file to expose all 12 tools and 3 resources to Claude Desktop, Cursor, Windsurf, or any MCP-aware client. See [MCP Server](reference/mcp_server).
  </Card>
 </CardGroup>
 ## Usage Examples
@@ -240,17 +228,7 @@ Install the [Microsoft Visual C++ Redistributable](https://aka.ms/vs/17/release/
 ## Next Steps
-<CardGroup cols={2}>
+- [Explorer Setup](explorer-setup) — Build a graph, save it, and launch the browser dashboard.
-  <Card title="Explorer Setup" icon="map" href="explorer-setup">
+- [MCP Server](reference/mcp_server) — All 12 tools and 3 resources exposed over the MCP protocol.
-    Build a graph, save it, and launch the browser dashboard.
+- [Installation](installation) — Virtual environments, optional extras, and platform-specific notes.
-  </Card>
+- [Quickstart](quickstart) — End-to-end pipeline walkthrough with working code.
  <Card title="MCP Server" icon="plug" href="reference/mcp_server">
    All 12 tools and 3 resources exposed over the MCP protocol.
  </Card>
  <Card title="Installation" icon="download" href="installation">
    Virtual environments, optional extras, and platform-specific notes.
  </Card>
  <Card title="Quickstart" icon="rocket" href="quickstart">
    End-to-end pipeline walkthrough with working code.
  </Card>
 </CardGroup>
@@ -114,17 +114,7 @@ See [Architecture](architecture#extension-points) for the full extension guide.
 ## How to Contribute
-<CardGroup cols={2}>
+- [Contributing Guide](contributing-guide) — Submit code, documentation, tests, or cookbook notebooks.
-  <Card title="Contributing Guide" icon="code-pull-request" href="contributing-guide">
+- [GitHub Issues](https://github.com/semantica-agi/semantica/issues) — Report bugs, request features, or propose integrations.
-    Submit code, documentation, tests, or cookbook notebooks.
+- [Discord](https://discord.gg/sV34vps5hH) — Share what you're building with the community.
-  </Card>
+- [GitHub Discussions](https://github.com/semantica-agi/semantica/discussions) — Long-form questions, design discussions, and ideas.
  <Card title="GitHub Issues" icon="circle-dot" href="https://github.com/semantica-agi/semantica/issues">
    Report bugs, request features, or propose integrations.
  </Card>
  <Card title="Discord" icon="discord" href="https://discord.gg/sV34vps5hH">
    Share what you're building with the community.
  </Card>
  <Card title="GitHub Discussions" icon="comments" href="https://github.com/semantica-agi/semantica/discussions">
    Long-form questions, design discussions, and ideas.
  </Card>
 </CardGroup>
@@ -9,20 +9,10 @@ Semantica is built in the open, with contributions from researchers, engineers,
 ## Get Help
-<CardGroup cols={2}>
+- [GitHub Issues](https://github.com/semantica-agi/semantica/issues) — File bug reports and feature requests with full context.
-  <Card title="GitHub Issues" icon="circle-dot" href="https://github.com/semantica-agi/semantica/issues">
+- [GitHub Discussions](https://github.com/semantica-agi/semantica/discussions) — Ask questions, share ideas, and discuss design decisions.
-    File bug reports and feature requests with full context.
+- [Pull Requests](https://github.com/semantica-agi/semantica/pulls) — Browse open contributions and submit your own.
-  </Card>
+- [Security Issues](https://github.com/semantica-agi/semantica/security/advisories/new) — Report vulnerabilities privately: never in public issues.
  <Card title="GitHub Discussions" icon="comments" href="https://github.com/semantica-agi/semantica/discussions">
    Ask questions, share ideas, and discuss design decisions.
  </Card>
  <Card title="Pull Requests" icon="code-pull-request" href="https://github.com/semantica-agi/semantica/pulls">
    Browse open contributions and submit your own.
  </Card>
  <Card title="Security Issues" icon="shield" href="https://github.com/semantica-agi/semantica/security/advisories/new">
    Report vulnerabilities privately: never in public issues.
  </Card>
 </CardGroup>
 ## Community Guidelines
@@ -78,17 +68,7 @@ See the [Contributing Guide](contributing-guide) for the full development workfl
 ## See Also
-<CardGroup cols={2}>
+- [Contributing Guide](contributing-guide) — Step-by-step guide for submitting PRs and setting up your dev environment.
-  <Card title="Contributing Guide" icon="code-pull-request" href="contributing-guide">
+- [Community Projects](community-projects) — Projects and integrations built by the community.
-    Step-by-step guide for submitting PRs and setting up your dev environment.
+- [FAQ](faq) — Common questions answered.
-  </Card>
+- [Governance](governance) — How the project is run and decisions are made.
  <Card title="Community Projects" icon="people-group" href="community-projects">
    Projects and integrations built by the community.
  </Card>
  <Card title="FAQ" icon="circle-question" href="faq">
    Common questions answered.
  </Card>
  <Card title="Governance" icon="scale-balanced" href="governance">
    How the project is run and decisions are made.
  </Card>
 </CardGroup>
@@ -12,17 +12,9 @@ Semantica transforms unstructured data: documents, web pages, reports, databases
 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**.
-<CardGroup cols={3}>
+- **Context Layer** — Knowledge graphs, GraphRAG retrieval, semantic embeddings, and temporal intelligence ground every LLM response in structured, queryable facts.
-  <Card title="Context Layer" icon="diagram-project">
+- **Accountability Layer** — Provenance tracking, decision intelligence, conflict detection, and W3C PROV-O compliance make every claim in your AI stack auditable and explainable.
-    Knowledge graphs, GraphRAG retrieval, semantic embeddings, and temporal intelligence ground every LLM response in structured, queryable facts.
+- **Extension Layer** — `PluginRegistry` and `MethodRegistry` let you replace or augment any component: ingestors, extractors, reasoning engines, backends: without changing framework code.
  </Card>
  <Card title="Accountability Layer" icon="shield-check">
    Provenance tracking, decision intelligence, conflict detection, and W3C PROV-O compliance make every claim in your AI stack auditable and explainable.
  </Card>
  <Card title="Extension Layer" icon="plug">
    `PluginRegistry` and `MethodRegistry` let you replace or augment any component: ingestors, extractors, reasoning engines, backends: without changing framework code.
  </Card>
 </CardGroup>
 ## Knowledge Graphs
@@ -487,14 +479,6 @@ Semantica is designed for extension. Any component: ingestor, extractor, graph b
  </Accordion>
 </AccordionGroup>
-<CardGroup cols={2}>
+- [Quickstart Tutorial](quickstart) — Build a full pipeline with code.
-  <Card title="Quickstart Tutorial" icon="play" href="quickstart">
+- [Modules Guide](modules) — Every module explained with examples.
-    Build a full pipeline with code.
+- [API Reference](reference/context) — Complete technical reference.
  </Card>
  <Card title="Modules Guide" icon="puzzle-piece" href="modules">
    Every module explained with examples.
  </Card>
  <Card title="API Reference" icon="code" href="reference/context">
    Complete technical reference.
  </Card>
 </CardGroup>
@@ -22,20 +22,10 @@ New to the project? Start with [`good-first-issue`](https://github.com/semantica
 ## Ways to Contribute
-<CardGroup cols={2}>
+- **Code** — Fix bugs, implement features, optimize performance, or add new ingestors, parsers, and exporters using the plugin registry.
-  <Card title="Code" icon="code">
+- **Documentation** — Fix typos, improve clarity, add missing examples, write tutorials, or keep the API reference accurate as modules evolve.
-    Fix bugs, implement features, optimize performance, or add new ingestors, parsers, and exporters using the plugin registry.
+- **Testing** — Add test coverage for untested modules or edge cases, reproduce reported bugs with minimal repros, or improve cross-platform reliability.
-  </Card>
+- **Community** — Answer questions in GitHub Issues and Discussions, review pull requests with constructive feedback, or share Semantica in blog posts and talks.
  <Card title="Documentation" icon="book">
    Fix typos, improve clarity, add missing examples, write tutorials, or keep the API reference accurate as modules evolve.
  </Card>
  <Card title="Testing" icon="flask">
    Add test coverage for untested modules or edge cases, reproduce reported bugs with minimal repros, or improve cross-platform reliability.
  </Card>
  <Card title="Community" icon="users">
    Answer questions in GitHub Issues and Discussions, review pull requests with constructive feedback, or share Semantica in blog posts and talks.
  </Card>
 </CardGroup>
 ## Development Setup
@@ -95,11 +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)
-<CardGroup cols={2}>
+- [Community](community) — Community guidelines and values.
-  <Card title="Community" icon="users" href="community">
+- [Governance](governance) — How decisions are made and the project is run.
    Community guidelines and values.
  </Card>
  <Card title="Governance" icon="scale-balanced" href="governance">
    How decisions are made and the project is run.
  </Card>
 </CardGroup>
@@ -16,131 +16,41 @@ icon: "flask"
 </Note>
-## Featured Recipes
+## Featured Recipe
-<CardGroup cols={2}>
+- **[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*
  <Card title="Your First Knowledge Graph" icon="diagram-project" href="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 · **Difficulty:** Beginner
  </Card>
 </CardGroup>
 ## Core Tutorials
 Essential guides to master the Semantica framework.
-<CardGroup cols={2}>
+- **[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*
-  <Card title="Welcome to Semantica" icon="hands" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/01_Welcome_to_Semantica.ipynb">
+- **[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*
-    An interactive introduction to the framework's core philosophy and all modules.
+- **[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*
-    **Topics:** Framework Overview, Architecture · **Difficulty:** 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*
-  </Card>
+- **[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*
-  <Card title="Data Ingestion" icon="database" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/02_Data_Ingestion.ipynb">
+- **[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*
-    Loading data from files, web, databases, streams, feeds, repositories, email, and MCP.
+- **[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*
-    **Topics:** FileIngestor, WebIngestor, DBIngestor, Streams · **Difficulty:** Beginner
+- **[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*
  </Card>
  <Card title="Document Parsing" icon="file-lines" href="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 · **Difficulty:** Beginner
  </Card>
  <Card title="Data Normalization" icon="broom" href="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 · **Difficulty:** Beginner
  </Card>
  <Card title="Entity Extraction" icon="magnifying-glass" href="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 · **Difficulty:** Beginner
  </Card>
  <Card title="Relation Extraction" icon="arrows-split-up-and-left" href="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 · **Difficulty:** Beginner
  </Card>
  <Card title="Embedding Generation" icon="vector-square" href="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 · **Difficulty:** Intermediate
  </Card>
  <Card title="Vector Store" icon="database" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/13_Vector_Store.ipynb">
    Setting up vector stores for similarity search and retrieval.
    **Difficulty:** Intermediate
  </Card>
  <Card title="Graph Store" icon="server" href="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 · **Difficulty:** Intermediate
  </Card>
  <Card title="Ontology" icon="sitemap" href="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 · **Difficulty:** Intermediate
  </Card>
 </CardGroup>
 ## Advanced Concepts
 Deep dive into advanced features, customization, and complex workflows.
-<CardGroup cols={2}>
+- **[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*
-  <Card title="Advanced Extraction" icon="flask" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/01_Advanced_Extraction.ipynb">
+- **[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*
-    Custom extractors, LLM-based extraction, and complex pattern matching.
+- **[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*
-    **Topics:** Custom Models, Regex, LLMs · **Difficulty:** Advanced
+- **[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*
-  </Card>
+- **[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*
-  <Card title="Advanced Graph Analytics" icon="chart-network" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/02_Advanced_Graph_Analytics.ipynb">
+- **[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*
-    Centrality, community detection, and pathfinding algorithms.
+- **[Pipeline Orchestration](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/07_Pipeline_Orchestration.ipynb)** — Building robust, automated data processing pipelines. Topics: Workflows, Automation, Error Handling · *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*
-    **Topics:** PageRank, Louvain, Shortest Path · **Difficulty:** 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*
  </Card>
  <Card title="Advanced Context Engineering" icon="brain" href="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 · **Difficulty:** Advanced
  </Card>
  <Card title="Complete Visualization Suite" icon="chart-bar" href="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 · **Difficulty:** Intermediate
  </Card>
  <Card title="Conflict Resolution" icon="scale-balanced" href="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 · **Difficulty:** Advanced
  </Card>
  <Card title="Multi-Format Export" icon="file-export" href="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 · **Difficulty:** Intermediate
  </Card>
  <Card title="Multi-Source Integration" icon="code-merge" href="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 · **Difficulty:** Advanced
  </Card>
  <Card title="Pipeline Orchestration" icon="gear" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/07_Pipeline_Orchestration.ipynb">
    Building robust, automated data processing pipelines.
    **Topics:** Workflows, Automation, Error Handling · **Difficulty:** Advanced
  </Card>
  <Card title="Reasoning and Inference" icon="brain" href="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 · **Difficulty:** Advanced
  </Card>
  <Card title="Temporal Knowledge Graphs" icon="clock" href="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 · **Difficulty:** Advanced
  </Card>
 </CardGroup>
 ## How to Run
@@ -264,17 +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.
-<CardGroup cols={2}>
+- [Explorer Reference](reference/explorer) — Every REST endpoint, WebSocket events, analytics, and all supported flags.
-  <Card title="Explorer Reference" icon="book-open" href="reference/explorer">
+- [CLI Setup](cli-setup) — All five Semantica executables and when to use each one.
-    Every REST endpoint, WebSocket events, analytics, and all supported flags.
+- [Context Module](reference/context) — Full documentation for ContextGraph: build, query, save, and load.
-  </Card>
+- [Quickstart](quickstart) — End-to-end pipeline: ingest → extract → build graph → export.
  <Card title="CLI Setup" icon="terminal" href="cli-setup">
    All five Semantica executables and when to use each one.
  </Card>
  <Card title="Context Module" icon="brain" href="reference/context">
    Full documentation for ContextGraph: build, query, save, and load.
  </Card>
  <Card title="Quickstart" icon="rocket" href="quickstart">
    End-to-end pipeline: ingest → extract → build graph → export.
  </Card>
 </CardGroup>
@@ -338,14 +338,6 @@ set PYTHONIOENCODING=utf-8
 ## Support
-<CardGroup cols={3}>
+- [Discord](https://discord.gg/sV34vps5hH) — Community chat and live support.
-  <Card title="Discord" icon="discord" href="https://discord.gg/sV34vps5hH">
+- [GitHub Issues](https://github.com/semantica-agi/semantica/issues) — Bug reports and feature requests.
-    Community chat and live support.
+- [Contributing](contributing-guide) — Help improve Semantica.
  </Card>
  <Card title="GitHub Issues" icon="github" href="https://github.com/semantica-agi/semantica/issues">
    Bug reports and feature requests.
  </Card>
  <Card title="Contributing" icon="code-pull-request" href="contributing-guide">
    Help improve Semantica.
  </Card>
 </CardGroup>
@@ -10,20 +10,10 @@ icon: "rocket"
 ## What You Can Build
-<CardGroup cols={2}>
+- **GraphRAG Systems** — Ground LLM responses in traceable, structured knowledge. Every claim links back to a source node.
-  <Card title="GraphRAG Systems" icon="diagram-project">
+- **Accountable AI Agents** — Agents with structured decision history, causal chains, and precedent search. Every choice is recorded and auditable.
-    Ground LLM responses in traceable, structured knowledge. Every claim links back to a source node.
+- **Production Knowledge Graphs** — Build, validate, and maintain enterprise-grade semantic knowledge bases from multi-source data.
-  </Card>
+- **Compliance-Ready AI** — W3C PROV-O provenance on every fact. HIPAA, SOX, GDPR, FDA 21 CFR Part 11 infrastructure built in.
  <Card title="Accountable AI Agents" icon="robot">
    Agents with structured decision history, causal chains, and precedent search. Every choice is recorded and auditable.
  </Card>
  <Card title="Production Knowledge Graphs" icon="sitemap">
    Build, validate, and maintain enterprise-grade semantic knowledge bases from multi-source data.
  </Card>
  <Card title="Compliance-Ready AI" icon="shield-check">
    W3C PROV-O provenance on every fact. HIPAA, SOX, GDPR, FDA 21 CFR Part 11 infrastructure built in.
  </Card>
 </CardGroup>
 ## Setup in 3 Steps
@@ -204,32 +194,12 @@ icon: "rocket"
 Semantica uses a modular, layered architecture: import only what you need.
-<CardGroup cols={3}>
+- **[Input Layer](reference/ingest)** — Load and prepare data from any source. Modules: `ingest`, `parse`, `split`, `normalize`
-  <Card title="Input Layer" icon="database" href="reference/ingest">
+- **[Semantic Layer](reference/semantic_extract)** — Extract meaning from raw text. Modules: `semantic_extract`, `kg`, `ontology`, `reasoning`
-    Load and prepare data from any source.
+- **[Storage Layer](reference/vector_store)** — Persist knowledge for retrieval. Modules: `embeddings`, `vector_store`, `graph_store`, `triplet_store`
-    **Modules:** `ingest`, `parse`, `split`, `normalize`
+- **[Quality Layer](reference/deduplication)** — Validate and deduplicate. Modules: `deduplication`, `conflicts`
-  </Card>
+- **[Context Layer](reference/context)** — Track decisions and lineage. Modules: `context`, `provenance`, `change_management`
-  <Card title="Semantic Layer" icon="microchip" href="reference/semantic_extract">
+- **[Output Layer](reference/export)** — Deliver results downstream. Modules: `export`, `visualization`, `pipeline`, `explorer`
    Extract meaning from raw text.
    **Modules:** `semantic_extract`, `kg`, `ontology`, `reasoning`
  </Card>
  <Card title="Storage Layer" icon="hard-drive" href="reference/vector_store">
    Persist knowledge for retrieval.
    **Modules:** `embeddings`, `vector_store`, `graph_store`, `triplet_store`
  </Card>
  <Card title="Quality Layer" icon="check-circle" href="reference/deduplication">
    Validate and deduplicate.
    **Modules:** `deduplication`, `conflicts`
  </Card>
  <Card title="Context Layer" icon="brain" href="reference/context">
    Track decisions and lineage.
    **Modules:** `context`, `provenance`, `change_management`
  </Card>
  <Card title="Output Layer" icon="share-nodes" href="reference/export">
    Deliver results downstream.
    **Modules:** `export`, `visualization`, `pipeline`, `explorer`
  </Card>
 </CardGroup>
 ## "Which module do I need?" Quick Reference
@@ -252,32 +222,14 @@ Semantica uses a modular, layered architecture: import only what you need.
 ## Next Steps
-<CardGroup cols={2}>
+- [Core Concepts](concepts) — Knowledge graphs, ontologies, and reasoning explained in depth.
-  <Card title="Core Concepts" icon="book-open" href="concepts">
+- [Quickstart Tutorial](quickstart) — Full 6-step pipeline walkthrough with working code.
-    Knowledge graphs, ontologies, and reasoning explained in depth.
+- [Module Reference](modules) — Every module, class, and common chain explained.
-  </Card>
+- [API Reference](reference/context) — Complete module documentation for every class and method.
  <Card title="Quickstart Tutorial" icon="play" href="quickstart">
    Full 6-step pipeline walkthrough with working code.
  </Card>
  <Card title="Module Reference" icon="puzzle-piece" href="modules">
    Every module, class, and common chain explained.
  </Card>
  <Card title="API Reference" icon="code" href="reference/context">
    Complete module documentation for every class and method.
  </Card>
 </CardGroup>
 ## Help
-<CardGroup cols={3}>
+- [Discord](https://discord.gg/sV34vps5hH) — Ask questions, share projects, get community support.
-  <Card title="Discord" icon="discord" href="https://discord.gg/sV34vps5hH">
+- [GitHub Issues](https://github.com/semantica-agi/semantica/issues) — Report bugs or request features.
-    Ask questions, share projects, get community support.
+- [FAQ](faq) — Common questions answered.
  </Card>
  <Card title="GitHub Issues" icon="github" href="https://github.com/semantica-agi/semantica/issues">
    Report bugs or request features.
  </Card>
  <Card title="FAQ" icon="circle-question" href="faq">
    Common questions answered.
  </Card>
 </CardGroup>
@@ -214,17 +214,7 @@ A vulnerability in XML parsers that allows attackers to read arbitrary files or
 ## See Also
-<CardGroup cols={2}>
+- [Core Concepts](concepts) — Deeper explanation of key ideas with code examples.
-  <Card title="Core Concepts" icon="lightbulb" href="concepts">
+- [Getting Started](getting-started) — First working examples: no prior graph experience required.
-    Deeper explanation of key ideas with code examples.
+- [Modules Guide](modules) — All 27 modules explained with code and pipeline chains.
-  </Card>
+- [API Reference](reference/context) — Complete technical reference for every class and method.
  <Card title="Getting Started" icon="play" href="getting-started">
    First working examples: no prior graph experience required.
  </Card>
  <Card title="Modules Guide" icon="cubes" href="modules">
    All 27 modules explained with code and pipeline chains.
  </Card>
  <Card title="API Reference" icon="code" href="reference/context">
    Complete technical reference for every class and method.
  </Card>
 </CardGroup>
@@ -9,17 +9,9 @@ icon: "scale-balanced"
 ## Roles
-<CardGroup cols={3}>
+- **Maintainers** — Hawksight AI team: review and merge PRs, manage releases and code quality, set project direction and community standards.
-  <Card title="Maintainers" icon="shield-halved">
+- **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).
-    Hawksight AI team: review and merge PRs, manage releases and code quality, set project direction and community standards.
+- **Community Members** — Use Semantica, provide feedback, share use cases, and participate in GitHub Discussions and Discord.
  </Card>
  <Card title="Contributors" icon="code-pull-request">
    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).
  </Card>
  <Card title="Community Members" icon="users">
    Use Semantica, provide feedback, share use cases, and participate in GitHub Discussions and Discord.
  </Card>
 </CardGroup>
 ## Decision Process
@@ -73,23 +65,11 @@ Semantica follows **Semantic Versioning** (`MAJOR.MINOR.PATCH`):
 ## Project Goals
-<CardGroup cols={3}>
+- **Usability** — Easy to use and understand: sensible defaults, clear documentation, minimal ceremony.
-  <Card title="Usability" icon="hand-pointer">
+- **Reliability** — Production-ready quality: tested across Python versions, platforms, and real-world workloads.
-    Easy to use and understand: sensible defaults, clear documentation, minimal ceremony.
+- **Performance** — Efficient and scalable: from single-machine notebooks to enterprise graph databases.
-  </Card>
+- **Extensibility** — Easy to extend with plugins and custom modules via the `PluginRegistry` pattern.
-  <Card title="Reliability" icon="circle-check">
+- **Community** — Welcoming and inclusive: all backgrounds and experience levels contribute and are recognized.
    Production-ready quality: tested across Python versions, platforms, and real-world workloads.
  </Card>
  <Card title="Performance" icon="bolt">
    Efficient and scalable: from single-machine notebooks to enterprise graph databases.
  </Card>
  <Card title="Extensibility" icon="puzzle-piece">
    Easy to extend with plugins and custom modules via the `PluginRegistry` pattern.
  </Card>
  <Card title="Community" icon="heart">
    Welcoming and inclusive: all backgrounds and experience levels contribute and are recognized.
  </Card>
 </CardGroup>
 ## License
@@ -99,11 +79,5 @@ MIT License: see [LICENSE](https://github.com/semantica-agi/semantica/blob/main/
 ## See Also
-<CardGroup cols={2}>
+- [Contributing](contributing-guide) — How to submit changes.
-  <Card title="Contributing" icon="code-pull-request" href="contributing-guide">
+- [Community](community) — Community guidelines and channels.
    How to submit changes.
  </Card>
  <Card title="Community" icon="users" href="community">
    Community guidelines and channels.
  </Card>
 </CardGroup>
@@ -4,7 +4,7 @@ description: "The Accountability and Context Layer for AI: Context Graphs · Dec
 ---
 <Info>
-  **v0.5.0 is live**: Ontology Hub, Distance Intelligence, SHACL Studio, Parquet & XML ingestion, 12 security fixes. [What's new →](#whats-new)
+  **v0.5.0 is live** — Ontology Hub, Distance Intelligence, SHACL Studio, Parquet & XML ingestion, 12 security fixes. <a href="#whats-new" style={{color:"#10B981",fontWeight:600,textDecoration:"none"}}>What's new →</a>
 </Info>
 Your AI agent just made a decision. Now someone needs to explain it.
@@ -15,58 +15,42 @@ If your stack can't answer those questions with a traceable record, you have a g
 **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.
-<CardGroup cols={4}>
+<div style={{display:"flex",flexWrap:"wrap",gap:"3rem",margin:"2rem 0",padding:"1.5rem 2rem",borderRadius:"10px",border:"1px solid rgba(16,185,129,0.2)",background:"rgba(16,185,129,0.03)"}}>
-  <Card title="1,000+ Tests" icon="circle-check">
+  <div><div style={{fontSize:"1.75rem",fontWeight:700,color:"#10B981",lineHeight:1.1}}>1,000+</div><div style={{fontSize:"0.8rem",color:"rgba(255,255,255,0.5)",marginTop:"4px"}}>passing tests</div></div>
-    Production-hardened with a full regression suite
+  <div><div style={{fontSize:"1.75rem",fontWeight:700,color:"#10B981",lineHeight:1.1}}>25+</div><div style={{fontSize:"0.8rem",color:"rgba(255,255,255,0.5)",marginTop:"4px"}}>modules</div></div>
-  </Card>
+  <div><div style={{fontSize:"1.75rem",fontWeight:700,color:"#10B981",lineHeight:1.1}}>12</div><div style={{fontSize:"0.8rem",color:"rgba(255,255,255,0.5)",marginTop:"4px"}}>LLM providers</div></div>
-  <Card title="25+ Modules" icon="puzzle-piece">
+  <div><div style={{fontSize:"1.75rem",fontWeight:700,color:"#10B981",lineHeight:1.1}}>MIT</div><div style={{fontSize:"0.8rem",color:"rgba(255,255,255,0.5)",marginTop:"4px"}}>open source</div></div>
-    Every capability independently importable
+</div>
  </Card>
  <Card title="12 LLM Providers" icon="microchip">
    OpenAI, Anthropic, Ollama, Groq, and more
  </Card>
  <Card title="MIT Licensed" icon="code-branch">
    Open source, no vendor lock-in, fully forkable
  </Card>
 </CardGroup>
 ## 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:
-<CardGroup cols={2}>
+**No memory structure** — agents store embeddings, not meaning
-  <Card title="No memory structure" icon="brain">
+- No way to ask *why* a fact was recalled
-    Agents store embeddings, not meaning.
+- No link from a recalled fact back to its source document
-    - No way to ask *why* a fact was recalled
+- Context is a black box that resets on every run
-    - 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
-  </Card>
+- No history to hand to a regulator or auditor
-  <Card title="No decision trail" icon="clock-rotate-left">
+- No way to replay or reproduce a past decision
-    Agents act continuously but record nothing.
+- Debugging means re-running, not reviewing
-    - No history to hand to a regulator or auditor
+
-    - No way to replay or reproduce a past decision
+**No provenance** — outputs can't be traced to source facts
-    - Debugging means re-running, not reviewing
+- In healthcare, finance, and legal: this is a hard compliance blocker
-  </Card>
+- No lineage from inference back to the original document
-  <Card title="No provenance" icon="link-slash">
+- Impossible to demonstrate what the agent actually relied on
-    Outputs can't be traced to source facts.
+
-    - In healthcare, finance, and legal: this is a hard compliance blocker
+**No reasoning transparency** — black-box answers with no explanation
-    - No lineage from inference back to the original document
+- Impossible to validate the reasoning path
-    - Impossible to demonstrate what the agent actually relied on
+- Impossible to contest a specific conclusion
-  </Card>
+- No basis for improving or correcting future behavior
-  <Card title="No reasoning transparency" icon="eye-slash">
+
-    Black-box answers with no explanation.
+**No conflict detection** — contradictory facts silently coexist in vector stores
-    - Impossible to validate the reasoning path
+- No detection when two sources disagree
-    - Impossible to contest a specific conclusion
+- Outputs become inconsistent and unpredictable over time
-    - No basis for improving or correcting future behavior
+- Silent failures compound as the knowledge base grows
  </Card>
  <Card title="No conflict detection" icon="triangle-exclamation">
    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
  </Card>
 </CardGroup>
 <Note>
  These aren't edge cases. They're why enterprise AI pilots stall: and why your compliance team keeps saying *not yet*.
@@ -77,50 +61,41 @@ Powerful agents aren't automatically trustworthy ones. Five structural blind spo
 Semantica gives every agent the infrastructure it needs to be accountable. Drop it into your existing setup in minutes:
-<CardGroup cols={2}>
+**Context Graphs** — a structured, queryable graph of everything your agent knows, decides, and reasons about
-  <Card title="Context Graphs" icon="diagram-project">
+- Persistent across agent runs: no context loss between sessions
-    A structured, queryable graph of everything your agent knows, decides, and reasons about.
+- Queryable with SPARQL and full graph algorithms
-    - Persistent across agent runs: no context loss between sessions
+- Temporal model with `valid_from` / `valid_until` on nodes and edges
-    - Queryable with SPARQL and full graph algorithms
+- Point-in-time snapshots of the full knowledge state
-    - 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
-  </Card>
+- `record_decision()` captures full lifecycle and causal chain
-  <Card title="Decision Intelligence" icon="check-circle">
+- Hybrid precedent search over past decisions for consistency
-    Every decision is a first-class object in your system.
+- `analyze_decision_impact()` shows downstream consequences
-    - `record_decision()` captures full lifecycle and causal chain
+- Causal chain visualization from trigger to outcome
-    - Hybrid precedent search over past decisions for consistency
+
-    - `analyze_decision_impact()` shows downstream consequences
+**Full Provenance** — every fact links to its source document and ingestion event
-    - Causal chain visualization from trigger to outcome
+- W3C PROV-O compliant lineage across all modules
-  </Card>
+- Full traceability from raw input to final inference
-  <Card title="Full Provenance" icon="shield-check">
+- `recorded_at` stamping with OWL-Time export
-    Every fact links to its source document and ingestion event.
+- Audit-ready for HIPAA, SOX, GDPR, FDA 21 CFR Part 11
-    - W3C PROV-O compliant lineage across all modules
+
-    - Full traceability from raw input to final inference
+**Reasoning Engines** — explainable reasoning paths, not black boxes
-    - `recorded_at` stamping with OWL-Time export
+- Forward chaining, Rete, deductive, abductive
-    - Audit-ready for HIPAA, SOX, GDPR, FDA 21 CFR Part 11
+- SPARQL query-based inference over RDF graphs
-  </Card>
+- Datalog with recursive Horn clause rules
-  <Card title="Reasoning Engines" icon="microchip">
+- Every conclusion backed by a traceable derivation path
-    Explainable reasoning paths: not black boxes.
+
-    - Forward chaining, Rete, deductive, abductive
+**Temporal Intelligence** — your graph knows not just *what*, but *when*
-    - SPARQL query-based inference over RDF graphs
+- Allen interval algebra: all 13 temporal relations
-    - Datalog with recursive Horn clause rules
+- Point-in-time queries over historical graph states
-    - Every conclusion backed by a traceable derivation path
+- Temporal provenance stamping on every fact
-  </Card>
+- OWL-Time export for standards-compliant archiving
-  <Card title="Temporal Intelligence" icon="clock">
+
-    Your graph knows not just *what*: but *when*.
+**Ontology Hub** — full ontology lifecycle in the browser
-    - Allen interval algebra: all 13 temporal relations
+- Visual editor for schema design and editing
-    - Point-in-time queries over historical graph states
+- SHACL Studio for constraint authoring and validation
-    - Temporal provenance stamping on every fact
+- Alignment authoring across multiple ontologies
-    - OWL-Time export for standards-compliant archiving
+- Health dashboard and version control built in
  </Card>
  <Card title="Ontology Hub" icon="sitemap">
    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
  </Card>
 </CardGroup>
 <Tip>
  Works alongside any LLM provider and any agent framework: add it to an existing stack without changing your architecture.
@@ -217,61 +192,50 @@ decision_id = context.record_decision(
 </CodeGroup>
-<CardGroup cols={3}>
+- [Full Quickstart](quickstart) — Step-by-step pipeline walkthrough
-  <Card title="Full Quickstart" icon="rocket" href="quickstart">
+- [Cookbook](cookbook) — 40+ real-world Jupyter notebooks
-    Step-by-step pipeline walkthrough
+- [Join Discord](https://discord.gg/sV34vps5hH) — Community chat and support
  </Card>
  <Card title="Cookbook" icon="flask" href="cookbook">
    40+ real-world Jupyter notebooks
  </Card>
  <Card title="Join Discord" icon="discord" href="https://discord.gg/sV34vps5hH">
    Community chat and support
  </Card>
 </CardGroup>
 ## Built for Where Mistakes Have Consequences
 Semantica was designed for domains where every decision must be explainable and every fact must be traceable:
-<CardGroup cols={2}>
+**Healthcare & Life Sciences**
-  <Card title="Healthcare & Life Sciences" icon="heart-pulse">
+- Clinical decision support with full audit trails
-    - Clinical decision support with full audit trails
+- Drug interaction and contraindication graphs
-    - Drug interaction and contraindication graphs
+- Patient safety event tracking and root-cause analysis
-    - Patient safety event tracking and root-cause analysis
+- HIPAA-compliant provenance chains out of the box
-    - HIPAA-compliant provenance chains out of the box
+
-  </Card>
+**Finance & Risk**
-  <Card title="Finance & Risk" icon="chart-line">
+- Fraud detection knowledge graphs
-    - Fraud detection knowledge graphs
+- Risk assessment trails built to survive an audit
-    - Risk assessment trails built to survive an audit
+- SOX, GDPR, and MiFID II compliance infrastructure
-    - SOX, GDPR, and MiFID II compliance infrastructure
+- Model decision lineage for regulatory reporting
-    - Model decision lineage for regulatory reporting
+
-  </Card>
+**Legal & Compliance**
-  <Card title="Legal & Compliance" icon="scale-balanced">
+- Evidence-backed research with every cited fact provenance-linked
-    - Evidence-backed research with every cited fact provenance-linked
+- Contract analysis with traceable clause extraction
-    - Contract analysis with traceable clause extraction
+- Regulatory change tracking across jurisdictions
-    - Regulatory change tracking across jurisdictions
+- Full reasoning paths ready for court-admissible documentation
-    - Full reasoning paths ready for court-admissible documentation
+
-  </Card>
+**Cybersecurity**
-  <Card title="Cybersecurity" icon="shield">
+- Threat attribution graphs linking actors, TTPs, and indicators
-    - Threat attribution graphs linking actors, TTPs, and indicators
+- Incident response timelines with full event provenance
-    - Incident response timelines with full event provenance
+- Security audit trails across the complete kill chain
-    - Security audit trails across the complete kill chain
+- MITRE ATT&CK-aligned knowledge graph integration
-    - MITRE ATT&CK-aligned knowledge graph integration
+
-  </Card>
+**Government & Defense**
-  <Card title="Government & Defense" icon="building-columns">
+- Policy decision trails from brief to outcome
-    - Policy decision trails from brief to outcome
+- Classified information handling with provenance chains
-    - Classified information handling with provenance chains
+- Chain-of-custody scrutiny for intelligence reporting
-    - Chain-of-custody scrutiny for intelligence reporting
+- Air-gapped deployment with local LLM support
-    - Air-gapped deployment with local LLM support
+
-  </Card>
+**Critical Infrastructure**
-  <Card title="Critical Infrastructure" icon="bolt">
+- Power grid state tracking with temporal intelligence
-    - Power grid state tracking with temporal intelligence
+- Transportation safety event graphs
-    - Transportation safety event graphs
+- Emergency response coordination with decision audit trails
-    - Emergency response coordination with decision audit trails
+- Consequence modeling for high-stakes operational decisions
    - Consequence modeling for high-stakes operational decisions
  </Card>
 </CardGroup>
 ## Start Here
@@ -305,23 +269,11 @@ Semantica was designed for domains where every decision must be explainable and
  </Step>
 </Steps>
-<CardGroup cols={2}>
+- [Installation](installation) — Get Semantica installed in under a minute
-  <Card title="Installation" icon="download" href="installation">
+- [Quickstart](quickstart) — Build a complete knowledge graph pipeline in 5 minutes
-    Get Semantica installed in under a minute
+- [Core Concepts](concepts) — The mental model behind the API
-  </Card>
+- [API Reference](reference/context) — Exact module, class, and method details
-  <Card title="Quickstart" icon="rocket" href="quickstart">
+- [Cookbook](cookbook) — Domain notebooks for real-world use cases
    Build a complete knowledge graph pipeline in 5 minutes
  </Card>
  <Card title="Core Concepts" icon="book-open" href="concepts">
    The mental model behind the API
  </Card>
  <Card title="API Reference" icon="rectangle-terminal" href="reference/context">
    Exact module, class, and method details
  </Card>
  <Card title="Cookbook" icon="flask" href="cookbook">
    Domain notebooks for real-world use cases
  </Card>
 </CardGroup>
 ## What's New
@@ -332,15 +284,13 @@ Semantica was designed for domains where every decision must be explainable and
 Released **May 11, 2026**
-| Area | Highlights |
+- **Ontology Hub** — Visual editor, SHACL Studio, alignment authoring, health dashboard, version control: full ontology lifecycle in the browser
-| :------ | :------------ |
+- **Distance Intelligence** — Semantic neighborhoods, N×N distance matrices, ego-mode visualization, distance band classification, embedding cache optimization
-| **Ontology Hub** | Visual editor, SHACL Studio, alignment authoring, health dashboard, version control: full ontology lifecycle in the browser |
+- **Parquet Ingestion** — `ParquetIngestor` with PyArrow: single file, partitioned directories, Hive-style discovery, selective column reading
-| **Distance Intelligence** | Semantic neighborhoods, N×N distance matrices, ego-mode visualization, distance band classification, embedding cache optimization |
+- **XML Ingestion** — `XMLIngestor` with XXE-safe lxml backend, XSD/DTD validation, namespace handling, directory scanning
-| **Parquet Ingestion** | `ParquetIngestor` with PyArrow: single file, partitioned directories, Hive-style discovery, selective column reading |
+- **Graph Explorer** — Landing page redesign, bidirectional path finding, indexed search (0.004ms on 118k nodes)
-| **XML Ingestion** | `XMLIngestor` with XXE-safe lxml backend, XSD/DTD validation, namespace handling, directory scanning |
+- **Security** — 12 vulnerability fixes: eval injection, pickle deserialization, SQL injection, XXE, SSRF, ReDoS, path traversal
-| **Graph Explorer** | Landing page redesign, bidirectional path finding, indexed search (0.004ms on 118k nodes) |
+- **Bug Fixes** — NER LLM silent fallback on enterprise gateways, ConflictDetector duplicate definition, Windows `[all]` install, cp1252 crash
 | **Security** | 12 vulnerability fixes: eval injection, pickle deserialization, SQL injection, XXE, SSRF, ReDoS, path traversal |
 | **Bug Fixes** | NER LLM silent fallback on enterprise gateways, ConflictDetector duplicate definition, Windows `[all]` install, cp1252 crash |
 ```bash
 pip install semantica==0.5.0
@@ -350,13 +300,11 @@ pip install semantica==0.5.0
 <Accordion title="v0.4.0: Temporal Intelligence & Knowledge Explorer" icon="clock">
-| Area | Highlights |
+- **Temporal Intelligence** — 6-PR system: temporal data model, point-in-time queries, Allen interval algebra (all 13 relations), OWL-Time export
-| :------ | :------------ |
+- **Knowledge Explorer API** — Full FastAPI backend: 99 tests, 12 export formats, WebSocket progress, thread-safe sessions, audit trail
-| **Temporal Intelligence** | 6-PR system: temporal data model, point-in-time queries, Allen interval algebra (all 13 relations), OWL-Time export |
+- **Ontology Foundations** — SHACL generation/validation, SKOS vocabulary, ontology alignment API, diff & migration tooling
-| **Knowledge Explorer API** | Full FastAPI backend: 99 tests, 12 export formats, WebSocket progress, thread-safe sessions, audit trail |
+- **Datalog Reasoning** — Pure-Python bottom-up semi-naive fixpoint, recursive Horn clause rules, guaranteed termination
-| **Ontology Foundations** | SHACL generation/validation, SKOS vocabulary, ontology alignment API, diff & migration tooling |
+- **Agno Integration** — 5 components: graph-backed memory, multi-hop GraphRAG, decision toolkit, KG toolkit, shared team context; 110 tests
 | **Datalog Reasoning** | Pure-Python bottom-up semi-naive fixpoint, recursive Horn clause rules, guaranteed termination |
 | **Agno Integration** | 5 components: graph-backed memory, multi-hop GraphRAG, decision toolkit, KG toolkit, shared team context; 110 tests |
 </Accordion>
@@ -483,26 +431,20 @@ pip install semantica==0.5.0
 ## Why Semantica?
-<CardGroup cols={3}>
+**Open Source, MIT** — No vendor lock-in. No paywalled features.
-  <Card title="Open Source, MIT" icon="code-branch">
+- Full source available on GitHub
-    No vendor lock-in. No paywalled features.
+- Every line auditable by your security team
-    - Full source available on GitHub
+- Fork, extend, and self-host with no restrictions
-    - Every line auditable by your security team
+- No telemetry, no usage reporting
-    - Fork, extend, and self-host with no restrictions
+
-    - No telemetry, no usage reporting
+**Production Ready** — Built for teams that can't afford surprises.
-  </Card>
+- 1,000+ passing tests with full regression coverage
-  <Card title="Production Ready" icon="circle-check">
+- `PipelineValidator` catches configuration errors at startup
-    Built for teams that can't afford surprises.
+- `FailureHandler` with exponential backoff and dead-letter queues
-    - 1,000+ passing tests with full regression coverage
+- 12 security vulnerabilities fixed in v0.5.0
-    - `PipelineValidator` catches configuration errors at startup
+
-    - `FailureHandler` with exponential backoff and dead-letter queues
+**Modular by Design** — Import only what you need.
-    - 12 security vulnerabilities fixed in v0.5.0
+- Use `NERExtractor` without a graph store
-  </Card>
+- Use `ContextGraph` without vector storage
-  <Card title="Modular by Design" icon="puzzle-piece">
+- Every component independently swappable and testable
-    Import only what you need.
+- No framework lock-in: works with any agent stack
    - 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
  </Card>
 </CardGroup>
@@ -183,14 +183,6 @@ Install the [Microsoft Visual C++ Redistributable](https://aka.ms/vs/17/release/
 ## Next Steps
-<CardGroup cols={3}>
+- [Getting Started](getting-started) — Understand what Semantica does before you build.
-  <Card title="Getting Started" icon="rocket" href="getting-started">
+- [Build the Pipeline](quickstart) — Follow the end-to-end workflow with code.
-    Understand what Semantica does before you build.
+- [Browse Examples](cookbook) — See notebook examples organized by use case.
  </Card>
  <Card title="Build the Pipeline" icon="play" href="quickstart">
    Follow the end-to-end workflow with code.
  </Card>
  <Card title="Browse Examples" icon="flask" href="cookbook">
    See notebook examples organized by use case.
  </Card>
 </CardGroup>
@@ -24,23 +24,11 @@ pip install "semantica[agno,graph-neo4j,vectorstore-pgvector]"
 ## Components at a Glance
-<CardGroup cols={2}>
+- **AgnoContextStore** — `AgentMemory(db=…)`: Replaces Agno's flat storage with hybrid vector + context graph memory. Adds decision tracking and precedent search to any agent.
-  <Card title="AgnoContextStore" icon="database">
+- **AgnoKnowledgeGraph** — `Agent(knowledge=…)`: Documents flow through the full Semantica extraction pipeline into a queryable `ContextGraph` with multi-hop GraphRAG.
-    `AgentMemory(db=…)`: Replaces Agno's flat storage with hybrid vector + context graph memory. Adds decision tracking and precedent search to any agent.
+- **AgnoDecisionKit** — `Agent(tools=[…])`: 6 decision intelligence tools: record decisions, find precedents, trace causal chains, analyze impact, check policies, summarize history.
-  </Card>
+- **AgnoKGToolkit** — `Agent(tools=[…])`: 7 KG construction tools: extract entities, extract relations, add to graph, query graph, find related, infer facts, export subgraph.
-  <Card title="AgnoKnowledgeGraph" icon="diagram-project">
+- **AgnoSharedContext** — Team-level: A single `ContextGraph` shared across all agents. Each agent gets a role-scoped view via `bind_agent()`. Writes are tagged by role.
    `Agent(knowledge=…)`: Documents flow through the full Semantica extraction pipeline into a queryable `ContextGraph` with multi-hop GraphRAG.
  </Card>
  <Card title="AgnoDecisionKit" icon="list-check">
    `Agent(tools=[…])`: 6 decision intelligence tools: record decisions, find precedents, trace causal chains, analyze impact, check policies, summarize history.
  </Card>
  <Card title="AgnoKGToolkit" icon="wrench">
    `Agent(tools=[…])`: 7 KG construction tools: extract entities, extract relations, add to graph, query graph, find related, infer facts, export subgraph.
  </Card>
  <Card title="AgnoSharedContext" icon="users">
    Team-level: A single `ContextGraph` shared across all agents. Each agent gets a role-scoped view via `bind_agent()`. Writes are tagged by role.
  </Card>
 </CardGroup>
 ## Component Details
@@ -233,17 +221,7 @@ All five classes are usable without `agno` installed: they carry the full Semant
 ## See Also
-<CardGroup cols={2}>
+- [Context Module](../reference/context) — AgentContext and ContextGraph backing the integration.
-  <Card title="Context Module" icon="brain" href="../reference/context">
+- [Knowledge Graph](../reference/kg) — KG construction used by AgnoKnowledgeGraph.
-    AgentContext and ContextGraph backing the integration.
+- [LLMs](../reference/llms) — Configure LLM providers for Agno agents.
-  </Card>
+- [Vector Store](../reference/vector_store) — Vector backend for AgnoContextStore.
  <Card title="Knowledge Graph" icon="diagram-project" href="../reference/kg">
    KG construction used by AgnoKnowledgeGraph.
  </Card>
  <Card title="LLMs" icon="microchip" href="../reference/llms">
    Configure LLM providers for Agno agents.
  </Card>
  <Card title="Vector Store" icon="vector-square" href="../reference/vector_store">
    Vector backend for AgnoContextStore.
  </Card>
 </CardGroup>
@@ -11,20 +11,10 @@ icon: "file-lines"
 Docling is integrated into Semantica's `parse` module via the **`DoclingParser`**. Documents pass through Docling's **layout engine**, then feed directly into Semantica's extraction and KG pipeline.
-<CardGroup cols={2}>
+- **Multi-format** — PDF, DOCX, PPTX, HTML, and more.
-  <Card title="Multi-format" icon="file">
+- **Table Extraction** — High-fidelity table parsing with header detection.
-    PDF, DOCX, PPTX, HTML, and more.
+- **OCR Support** — Built-in OCR for scanned documents.
-  </Card>
+- **Markdown Export** — Clean Markdown output optimized for LLM consumption.
  <Card title="Table Extraction" icon="table">
    High-fidelity table parsing with header detection.
  </Card>
  <Card title="OCR Support" icon="eye">
    Built-in OCR for scanned documents.
  </Card>
  <Card title="Markdown Export" icon="markdown">
    Clean Markdown output optimized for LLM consumption.
  </Card>
 </CardGroup>
 ## Installation
@@ -100,17 +90,7 @@ print(f"Pages: {result.get('total_pages')}")
 ## See Also
-<CardGroup cols={2}>
+- [Parse Module](../reference/parse) — Full DocumentParser and DoclingParser reference.
-  <Card title="Parse Module" icon="file-lines" href="../reference/parse">
+- [Ingest Module](../reference/ingest) — Loading documents before parsing.
-    Full DocumentParser and DoclingParser reference.
+- [Semantic Extract](../reference/semantic_extract) — NER and relation extraction on parsed text.
-  </Card>
+- [Pipeline](../reference/pipeline) — Using DoclingParser in a full pipeline.
  <Card title="Ingest Module" icon="file-import" href="../reference/ingest">
    Loading documents before parsing.
  </Card>
  <Card title="Semantic Extract" icon="magnifying-glass" href="../reference/semantic_extract">
    NER and relation extraction on parsed text.
  </Card>
  <Card title="Pipeline" icon="gear" href="../reference/pipeline">
    Using DoclingParser in a full pipeline.
  </Card>
 </CardGroup>
@@ -171,17 +171,7 @@ if not connector.test_connection():
 ## See Also
-<CardGroup cols={2}>
+- [Ingest Module](../reference/ingest) — Full SnowflakeIngestor and all other ingestors.
-  <Card title="Ingest Module" icon="database" href="../reference/ingest">
+- [Pipeline](../reference/pipeline) — Use Snowflake ingestion as a pipeline step.
-    Full SnowflakeIngestor and all other ingestors.
+- [Installation](../installation) — All optional dependency extras.
-  </Card>
+- [Knowledge Graph](../reference/kg) — Build a KG from ingested Snowflake data.
  <Card title="Pipeline" icon="gear" href="../reference/pipeline">
    Use Snowflake ingestion as a pipeline step.
  </Card>
  <Card title="Installation" icon="download" href="../installation">
    All optional dependency extras.
  </Card>
  <Card title="Knowledge Graph" icon="diagram-project" href="../reference/kg">
    Build a KG from ingested Snowflake data.
  </Card>
 </CardGroup>
@@ -9,20 +9,9 @@ Whether you're running your first pipeline or deploying Semantica in production,
 ## Learning Paths
-<CardGroup cols={3}>
+- **Beginner (1–2 hrs)** — New to Semantica and knowledge graphs. [Start with Installation →](installation)
-  <Card title="Beginner (1–2 hrs)" icon="seedling">
+- **Intermediate (4–6 hrs)** — Comfortable with basics, building real applications. [Start with Modules →](modules)
-    New to Semantica and knowledge graphs.
+- **Advanced (8+ hrs)** — Enterprise deployments, customization, and extension. [Start with Architecture →](architecture)
    [Start with Installation →](installation)
  </Card>
  <Card title="Intermediate (4–6 hrs)" icon="compass">
    Comfortable with basics, building real applications.
    [Start with Modules →](modules)
  </Card>
  <Card title="Advanced (8+ hrs)" icon="rocket">
    Enterprise deployments, customization, and extension.
    [Start with Architecture →](architecture)
  </Card>
 </CardGroup>
 <Tabs>
  <Tab title="Beginner (1–2 hrs)">
@@ -247,14 +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
-<CardGroup cols={2}>
+- [Cookbook](cookbook) — Interactive Jupyter notebooks from beginner to advanced.
-  <Card title="Cookbook" icon="flask" href="cookbook">
+- [FAQ](faq) — Common questions answered.
-    Interactive Jupyter notebooks from beginner to advanced.
+- [API Reference](reference/core) — Complete technical documentation.
  </Card>
  <Card title="FAQ" icon="circle-question" href="faq">
    Common questions answered.
  </Card>
  <Card title="API Reference" icon="code" href="reference/core">
    Complete technical documentation.
  </Card>
 </CardGroup>
@@ -12,26 +12,12 @@ Semantica is organized into **27 modules** across six logical layers. Each modul
 ## Architecture Overview
-<CardGroup cols={3}>
+- **Input Layer** — Data ingestion and preparation. Modules: `ingest`, `parse`, `split`, `normalize`
-  <Card title="Input Layer" icon="database">
+- **Core Processing** — Intelligence and understanding. Modules: `semantic_extract`, `kg`, `ontology`, `reasoning`
-    Data ingestion and preparation. **Modules:** Ingest, Parse, Split, Normalize
+- **Storage** — Persistent data storage. Modules: `embeddings`, `vector_store`, `graph_store`, `triplet_store`
-  </Card>
+- **Quality Assurance** — Data quality and consistency. Modules: `deduplication`, `conflicts`
-  <Card title="Core Processing" icon="microchip">
+- **Context & Memory** — Agent memory and decision tracking. Modules: `context`, `provenance`, `change_management`
-    Intelligence and understanding. **Modules:** Semantic Extract, KG, Ontology, Reasoning
+- **Output & Orchestration** — Export, visualization, and workflows. Modules: `export`, `visualization`, `pipeline`, `explorer`
  </Card>
  <Card title="Storage" icon="hard-drive">
    Persistent data storage. **Modules:** Embeddings, Vector Store, Graph Store, Triplet Store
  </Card>
  <Card title="Quality Assurance" icon="check-circle">
    Data quality and consistency. **Modules:** Deduplication, Conflicts
  </Card>
  <Card title="Context & Memory" icon="brain">
    Agent memory and decision tracking. **Modules:** Context, Provenance, Change Management
  </Card>
  <Card title="Output & Orchestration" icon="share-nodes">
    Export, visualization, and workflows. **Modules:** Export, Visualization, Pipeline, Explorer
  </Card>
 </CardGroup>
 ## Input Layer
@@ -712,14 +698,6 @@ versioner.create_snapshot(kg, "2024-Q1", author="user@example.com", description=
 | [core](reference/core) | Base classes & registry | `Semantica`, `ConfigManager`, `PluginRegistry`, `LifecycleManager` |
 | [utils](reference/utils) | Shared utilities | `helpers`, `validators` |
-<CardGroup cols={2}>
+- [Getting Started](getting-started) — Your first knowledge graph in 5 minutes.
-  <Card title="Getting Started" icon="rocket" href="getting-started">
+- [Cookbook](cookbook) — 40+ domain notebooks with real-world examples.
-    Your first knowledge graph in 5 minutes.
+- [API Reference](reference/context) — Full technical documentation.
  </Card>
  <Card title="Cookbook" icon="flask" href="cookbook">
    40+ domain notebooks with real-world examples.
  </Card>
  <Card title="API Reference" icon="code" href="reference/context">
    Full technical documentation.
  </Card>
 </CardGroup>
@@ -76,11 +76,5 @@ By contributing to Semantica, you agree that your contributions will be licensed
 ## See Also
-<CardGroup cols={2}>
+- [Contributing](contributing-guide) — How to contribute to the project.
-  <Card title="Contributing" icon="code-pull-request" href="contributing-guide">
+- [Citation](citation) — How to cite Semantica in research.
    How to contribute to the project.
  </Card>
  <Card title="Citation" icon="quote-left" href="citation">
    How to cite Semantica in research.
  </Card>
 </CardGroup>
@@ -5,7 +5,7 @@ icon: "rocket"
 ---
 <Info>
-  **v0.5.0**: Ontology Hub, Distance Intelligence, Parquet & XML ingestion, 12 security fixes. [What's new →](index#whats-new)
+  **v0.5.0** — Ontology Hub, Distance Intelligence, Parquet & XML ingestion, 12 security fixes. <a href="index#whats-new" 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.
@@ -420,17 +420,7 @@ pip install --upgrade semantica
 ## Next Steps
-<CardGroup cols={2}>
+- [Core Concepts](concepts) — Knowledge graphs, ontologies, reasoning engines: the mental model behind Semantica.
-  <Card title="Core Concepts" icon="book-open" href="concepts">
+- [Module Reference](modules) — Every module explained with key classes and common chains.
-    Knowledge graphs, ontologies, reasoning engines: the mental model behind Semantica.
+- [API Reference](reference/context) — Complete documentation for every module, class, and parameter.
-  </Card>
+- [Cookbook](cookbook) — 40+ interactive Jupyter notebooks with real-world datasets.
  <Card title="Module Reference" icon="puzzle-piece" href="modules">
    Every module explained with key classes and common chains.
  </Card>
  <Card title="API Reference" icon="rectangle-terminal" href="reference/context">
    Complete documentation for every module, class, and parameter.
  </Card>
  <Card title="Cookbook" icon="flask" href="cookbook">
    40+ interactive Jupyter notebooks with real-world datasets.
  </Card>
 </CardGroup>
@@ -30,26 +30,12 @@ icon: "clock-rotate-left"
 ## What You Get
-<CardGroup cols={2}>
+- **TemporalVersionManager** — Snapshot, diff, rollback, and per-entity audit trail for knowledge graphs.
-  <Card title="TemporalVersionManager" icon="code-branch">
+- **OntologyVersionManager** — Version control for OWL ontologies with diff and schema migration support.
-    Snapshot, diff, rollback, and per-entity audit trail for knowledge graphs.
+- **VersionStorage** — Pluggable backends: `InMemoryVersionStorage` for tests, `SQLiteVersionStorage` for production.
-  </Card>
+- **Integrity Verification** — SHA-256 checksums on every snapshot to detect any unauthorised modification.
-  <Card title="OntologyVersionManager" icon="sitemap">
+- **ChangeLogEntry** — Internal metadata validated on every snapshot: ISO 8601 timestamp, email author, and description (max 500 chars).
-    Version control for OWL ontologies with diff and schema migration support.
+- **Version History** — Full tamper-evident version history via `list_versions()` and `diff()` for regulatory review.
  </Card>
  <Card title="VersionStorage" icon="database">
    Pluggable backends: `InMemoryVersionStorage` for tests, `SQLiteVersionStorage` for production.
  </Card>
  <Card title="Integrity Verification" icon="shield-check">
    SHA-256 checksums on every snapshot to detect any unauthorised modification.
  </Card>
  <Card title="ChangeLogEntry" icon="list-check">
    Internal metadata validated on every snapshot: ISO 8601 timestamp, email author, and description (max 500 chars).
  </Card>
  <Card title="Version History" icon="file-shield">
    Full tamper-evident version history via `list_versions()` and `diff()` for regulatory review.
  </Card>
 </CardGroup>
 ## Typical Workflow
@@ -364,17 +350,7 @@ for record in history:
  </Accordion>
 </AccordionGroup>
-<CardGroup cols={2}>
+- [Provenance](provenance) — W3C PROV-O lineage tracking.
-  <Card title="Provenance" icon="link" href="provenance">
+- [Knowledge Graph](kg) — The graph being versioned.
-    W3C PROV-O lineage tracking.
+- [Export](export) — Export versioned snapshots.
-  </Card>
+- [Conflicts](conflicts) — Detect conflicts introduced between versions.
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    The graph being versioned.
  </Card>
  <Card title="Export" icon="file-export" href="export">
    Export versioned snapshots.
  </Card>
  <Card title="Conflicts" icon="triangle-exclamation" href="conflicts">
    Detect conflicts introduced between versions.
  </Card>
 </CardGroup>
@@ -45,26 +45,12 @@ Semantica's conflict detection makes disagreements explicit and actionable:
 ## What You Get
-<CardGroup cols={2}>
+- **ConflictDetector** — Value, type, and relationship conflict detection across entity and relationship lists.
-  <Card title="ConflictDetector" icon="magnifying-glass">
+- **ConflictResolver** — 7 resolution strategies including voting, credibility-weighted, and temporal preference.
-    Value, type, and relationship conflict detection across entity and relationship lists.
+- **SourceTracker** — Track which source each conflicting fact came from, with per-source credibility scores.
-  </Card>
+- **ConflictAnalyzer** — Pattern analysis, severity grouping, source-level statistics, and trend identification.
-  <Card title="ConflictResolver" icon="check">
+- **InvestigationGuideGenerator** — Auto-generate step-by-step investigation checklists for human and expert review.
-    7 resolution strategies including voting, credibility-weighted, and temporal preference.
+- **Convenience Functions** — `detect_conflicts()` and `resolve_conflicts()` for one-call workflows.
  </Card>
  <Card title="SourceTracker" icon="link">
    Track which source each conflicting fact came from, with per-source credibility scores.
  </Card>
  <Card title="ConflictAnalyzer" icon="chart-line">
    Pattern analysis, severity grouping, source-level statistics, and trend identification.
  </Card>
  <Card title="InvestigationGuideGenerator" icon="list-check">
    Auto-generate step-by-step investigation checklists for human and expert review.
  </Card>
  <Card title="Convenience Functions" icon="bolt">
    `detect_conflicts()` and `resolve_conflicts()` for one-call workflows.
  </Card>
 </CardGroup>
 ## Quick Start
@@ -464,17 +450,7 @@ class InvestigationStep:
  </Accordion>
 </AccordionGroup>
-<CardGroup cols={2}>
+- [Deduplication](deduplication) — Resolve duplicate entities before conflict detection.
-  <Card title="Deduplication" icon="copy" href="deduplication">
+- [Ontology](ontology) — Logical conflicts use SHACL shapes and ontology axioms.
-    Resolve duplicate entities before conflict detection.
+- [Provenance](provenance) — Track which source each conflicting fact came from.
-  </Card>
+- [Knowledge Graph](kg) — The graph being checked for conflicts.
  <Card title="Ontology" icon="sitemap" href="ontology">
    Logical conflicts use SHACL shapes and ontology axioms.
  </Card>
  <Card title="Provenance" icon="link" href="provenance">
    Track which source each conflicting fact came from.
  </Card>
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    The graph being checked for conflicts.
  </Card>
 </CardGroup>
@@ -29,48 +29,30 @@ icon: "brain"
 ## What You Get
-<CardGroup cols={2}>
+- **AgentContext** — Memory, decision tracking, and graph-backed retrieval behind one API
-  <Card title="AgentContext" icon="brain">
+  - Conversation history and checkpoint diffing
-    - Memory, decision tracking, and graph-backed retrieval behind one API
+  - Persist and restore full context state to disk
-    - Conversation history and checkpoint diffing
+- **ContextGraph** — Thread-safe in-memory knowledge graph
-    - Persist and restore full context state to disk
+  - PageRank, centrality, community detection, temporal validity
-  </Card>
+  - Cross-graph navigation and link traversal
-  <Card title="ContextGraph" icon="diagram-project">
+- **AgentMemory** — Embedding-backed memory with retention policy
-    - Thread-safe in-memory knowledge graph
+  - LRU eviction at configurable `max_memory_size`
-    - PageRank, centrality, community detection, temporal validity
+  - Per-conversation history isolation
-    - Cross-graph navigation and link traversal
+- **DecisionRecorder** — Records decisions with causal chains and confidence scores
-  </Card>
+  - Temporal validity windows (`valid_from` / `valid_until`)
-  <Card title="AgentMemory" icon="database">
+  - Cross-system context capture on every decision
-    - Embedding-backed memory with retention policy
+- **PolicyEngine** — Versioned policy storage in the knowledge graph
-    - LRU eviction at configurable `max_memory_size`
+  - Compliance checking against recorded decisions
-    - Per-conversation history isolation
+  - Policy exception tracking with approver audit trail
-  </Card>
+- **EntityLinker** — Maps entity text to stable URIs
-  <Card title="DecisionRecorder" icon="list-check">
+  - Creates typed links between entity IDs
-    - Records decisions with causal chains and confidence scores
+  - Prevents "Apple", "Apple Inc.", "AAPL" becoming separate nodes
-    - Temporal validity windows (`valid_from` / `valid_until`)
+- **ContextRetriever** — Fuses vector similarity, graph traversal, and agent memory
-    - Cross-system context capture on every decision
+  - Richer context than pure vector search
-  </Card>
+  - Configurable `hybrid_alpha` and expansion hops
-  <Card title="PolicyEngine" icon="shield-check">
+- **CausalChainAnalyzer** — Traces upstream causes and downstream effects of any decision
-    - Versioned policy storage in the knowledge graph
+  - Explainability paths with relationship types
-    - Compliance checking against recorded decisions
+  - Configurable depth and direction
    - Policy exception tracking with approver audit trail
  </Card>
  <Card title="EntityLinker" icon="link">
    - Maps entity text to stable URIs
    - Creates typed links between entity IDs
    - Prevents "Apple", "Apple Inc.", "AAPL" becoming separate nodes
  </Card>
  <Card title="ContextRetriever" icon="magnifying-glass">
    - Fuses vector similarity, graph traversal, and agent memory
    - Richer context than pure vector search
    - Configurable `hybrid_alpha` and expansion hops
  </Card>
  <Card title="CausalChainAnalyzer" icon="arrow-trend-up">
    - Traces upstream causes and downstream effects of any decision
    - Explainability paths with relationship types
    - Configurable depth and direction
  </Card>
 </CardGroup>
 ## Quick Start
@@ -889,26 +871,10 @@ class EntityLink:
  </Tab>
 </Tabs>
-<CardGroup cols={2}>
+- [Vector Store](vector_store) — Embedding storage backend for memory retrieval.
-  <Card title="Vector Store" icon="database" href="vector_store">
+- [Knowledge Graph](kg) — Graph algorithms and analytics used inside ContextGraph.
-    Embedding storage backend for memory retrieval.
+- [Reasoning](reasoning) — Logical inference layered on top of context.
-  </Card>
+- [Provenance](provenance) — W3C PROV-O lineage for every stored fact.
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    Graph algorithms and analytics used inside ContextGraph.
  </Card>
  <Card title="Reasoning" icon="microchip" href="reasoning">
    Logical inference layered on top of context.
  </Card>
  <Card title="Provenance" icon="link" href="provenance">
    W3C PROV-O lineage for every stored fact.
  </Card>
 </CardGroup>
-<CardGroup cols={2}>
+- [Context Module](https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/19_Context_Module.ipynb) — Memory and decision tracking · Intermediate
-  <Card title="Context Module" icon="book-open" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/introduction/19_Context_Module.ipynb">
+- [Advanced Context Engineering](https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb) — Production FAISS + Neo4j setup · Advanced
    Memory and decision tracking · Intermediate
  </Card>
  <Card title="Advanced Context Engineering" icon="flask" href="https://github.com/semantica-agi/semantica/blob/main/cookbook/advanced/11_Advanced_Context_Engineering.ipynb">
    Production FAISS + Neo4j setup · Advanced
  </Card>
 </CardGroup>
@@ -18,20 +18,10 @@ icon: "gear"
 ## What You Get
-<CardGroup cols={2}>
+- **Semantica** — High-level orchestrator: coordinates the full KG construction pipeline from a single `config.yaml`. Entry point for application-level deployments.
-  <Card title="Semantica" icon="arrows-turn-to-dots">
+- **ConfigManager** — YAML config with deep-merge, `SEMANTICA_` env var overrides, and dot-notation nested key access. Keeps secrets out of source files.
-    High-level orchestrator: coordinates the full KG construction pipeline from a single `config.yaml`. Entry point for application-level deployments.
+- **LifecycleManager** — Ordered startup/shutdown hooks, health monitoring, and a 6-state machine. Essential for long-running services like FastAPI apps.
-  </Card>
+- **PluginRegistry** — Register custom ingestors, parsers, exporters, or any component. Load them by name at runtime: no imports required.
  <Card title="ConfigManager" icon="sliders">
    YAML config with deep-merge, `SEMANTICA_` env var overrides, and dot-notation nested key access. Keeps secrets out of source files.
  </Card>
  <Card title="LifecycleManager" icon="circle-play">
    Ordered startup/shutdown hooks, health monitoring, and a 6-state machine. Essential for long-running services like FastAPI apps.
  </Card>
  <Card title="PluginRegistry" icon="plug">
    Register custom ingestors, parsers, exporters, or any component. Load them by name at runtime: no imports required.
  </Card>
 </CardGroup>
 ## Exported Classes
@@ -236,17 +226,7 @@ result = build_knowledge_base(sources=["doc.pdf"], method="fast")
  Use `Semantica` and `LifecycleManager` only when building a long-running application (e.g. a FastAPI service) that needs ordered startup, health checks, and graceful shutdown. For scripts and notebooks, use individual modules directly.
 </Tip>
-<CardGroup cols={2}>
+- [Pipeline](pipeline) — Pipeline execution and step orchestration.
-  <Card title="Pipeline" icon="arrows-turn-to-dots" href="pipeline">
+- [Utils](utils) — Shared utilities used by Core internally.
-    Pipeline execution and step orchestration.
+- [Getting Started](../getting-started) — Learn the basics before using Core.
-  </Card>
+- [LLMs](llms) — Configure LLM providers via ConfigManager.
  <Card title="Utils" icon="wrench" href="utils">
    Shared utilities used by Core internally.
  </Card>
  <Card title="Getting Started" icon="play" href="../getting-started">
    Learn the basics before using Core.
  </Card>
  <Card title="LLMs" icon="microchip" href="llms">
    Configure LLM providers via ConfigManager.
  </Card>
 </CardGroup>
@@ -30,26 +30,12 @@ icon: "copy"
 ## What You Get
-<CardGroup cols={2}>
+- **DuplicateDetector** — Pairwise, batch, incremental, and group detection modes. Returns scored candidates with reasons.
-  <Card title="DuplicateDetector" icon="copy">
+- **EntityMerger** — Five merge strategies: keep first, last, most complete, highest confidence, or merge all fields.
-    Pairwise, batch, incremental, and group detection modes. Returns scored candidates with reasons.
+- **SimilarityCalculator** — Multi-factor scoring across string edit distance, property overlap, relationship overlap, and embeddings.
-  </Card>
+- **ClusterBuilder** — Union-Find and hierarchical clustering for batch deduplication at scale: handles 100k+ entity sets.
-  <Card title="EntityMerger" icon="code-merge">
+- **MergeStrategyManager** — Per-property merge rules with conflict resolution priorities. Apply different strategies to different fields.
-    Five merge strategies: keep first, last, most complete, highest confidence, or merge all fields.
+- **v2 Strategies** — `blocking_v2`, `hybrid_v2`, `semantic_v2`: up to 7× faster than v1 for large entity sets.
  </Card>
  <Card title="SimilarityCalculator" icon="equals">
    Multi-factor scoring across string edit distance, property overlap, relationship overlap, and embeddings.
  </Card>
  <Card title="ClusterBuilder" icon="diagram-project">
    Union-Find and hierarchical clustering for batch deduplication at scale: handles 100k+ entity sets.
  </Card>
  <Card title="MergeStrategyManager" icon="sliders">
    Per-property merge rules with conflict resolution priorities. Apply different strategies to different fields.
  </Card>
  <Card title="v2 Strategies" icon="bolt">
    `blocking_v2`, `hybrid_v2`, `semantic_v2`: up to 7× faster than v1 for large entity sets.
  </Card>
 </CardGroup>
 ## Getting Started
@@ -451,17 +437,7 @@ result = calculate_similarity(entity_a, entity_b, method="drug_name")
  </Tab>
 </Tabs>
-<CardGroup cols={2}>
+- [Conflicts](conflicts) — Detect value conflicts between non-duplicate entities.
-  <Card title="Conflicts" icon="triangle-exclamation" href="conflicts">
+- [Knowledge Graph](kg) — GraphBuilder uses deduplication during construction.
-    Detect value conflicts between non-duplicate entities.
+- [Normalize](normalize) — Normalize entity names before deduplication.
-  </Card>
+- [Provenance](provenance) — Track merged entity lineage.
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    GraphBuilder uses deduplication during construction.
  </Card>
  <Card title="Normalize" icon="broom" href="normalize">
    Normalize entity names before deduplication.
  </Card>
  <Card title="Provenance" icon="link" href="provenance">
    Track merged entity lineage.
  </Card>
 </CardGroup>
@@ -41,26 +41,12 @@ Semantica uses embeddings for:
 ## What You Get
-<CardGroup cols={2}>
+- **EmbeddingGenerator** — Main entry point: provider-agnostic, handles batching automatically across all backends.
-  <Card title="EmbeddingGenerator" icon="vector-square">
+- **TextEmbedder** — Text-specific with automatic batching and progress tracking. Default method is FastEmbed.
-    Main entry point: provider-agnostic, handles batching automatically across all backends.
+- **GraphEmbeddingManager** — Node and edge embeddings for graph databases: Neo4j, NetworkX, FalkorDB.
-  </Card>
+- **VectorEmbeddingManager** — Prepare, normalize, and format embeddings for FAISS, Weaviate, Qdrant, and Milvus.
-  <Card title="TextEmbedder" icon="text-size">
+- **Provider Stores** — `OpenAIStore`, `BGEStore`, `FastEmbedStore`, and `ProviderStoreFactory`.
-    Text-specific with automatic batching and progress tracking. Default method is FastEmbed.
+- **Pooling Strategies** — Mean, Max, CLS, Attention, and Hierarchical: control token-to-vector aggregation.
  </Card>
  <Card title="GraphEmbeddingManager" icon="diagram-project">
    Node and edge embeddings for graph databases: Neo4j, NetworkX, FalkorDB.
  </Card>
  <Card title="VectorEmbeddingManager" icon="database">
    Prepare, normalize, and format embeddings for FAISS, Weaviate, Qdrant, and Milvus.
  </Card>
  <Card title="Provider Stores" icon="plug">
    `OpenAIStore`, `BGEStore`, `FastEmbedStore`, and `ProviderStoreFactory`.
  </Card>
  <Card title="Pooling Strategies" icon="layer-group">
    Mean, Max, CLS, Attention, and Hierarchical: control token-to-vector aggregation.
  </Card>
 </CardGroup>
 ## Provider Setup
@@ -633,17 +619,7 @@ providers = check_available_providers()
 # → {"sentence_transformers": True, "fastembed": True, "openai": False}
 ```
-<CardGroup cols={2}>
+- [Vector Store](vector_store) — Store and search the generated embeddings.
-  <Card title="Vector Store" icon="database" href="vector_store">
+- [Split](split) — Chunk text before embedding for better retrieval quality.
-    Store and search the generated embeddings.
+- [KG Module](kg) — Distance Intelligence uses graph embeddings for semantic neighbourhoods.
-  </Card>
+- [Deduplication](deduplication) — Semantic deduplication uses embedding distance for entity resolution.
  <Card title="Split" icon="scissors" href="split">
    Chunk text before embedding for better retrieval quality.
  </Card>
  <Card title="KG Module" icon="diagram-project" href="kg">
    Distance Intelligence uses graph embeddings for semantic neighbourhoods.
  </Card>
  <Card title="Deduplication" icon="copy" href="deduplication">
    Semantic deduplication uses embedding distance for entity resolution.
  </Card>
 </CardGroup>
@@ -58,17 +58,7 @@ print("Relation coverage: ", report["relation_completeness"]["relation_coverage"
 | `suggestions` | `List[str]` | Improvement suggestions |
 | `metrics` | `dict` | Detailed sub-metrics |
-<CardGroup cols={2}>
+- [Semantic Extract](semantic_extract) — Extraction module.
-  <Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
+- [Knowledge Graph](kg) — Graph quality assessment.
-    Extraction module.
+- [Pipeline](pipeline) — Pipeline performance metrics.
-  </Card>
+- [Ontology Evaluator](ontology) — Available now for ontology quality metrics.
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    Graph quality assessment.
  </Card>
  <Card title="Pipeline" icon="gear" href="pipeline">
    Pipeline performance metrics.
  </Card>
  <Card title="Ontology Evaluator" icon="sitemap" href="ontology">
    Available now for ontology quality metrics.
  </Card>
 </CardGroup>
@@ -115,26 +115,12 @@ EXPLORER_CORS_ORIGINS="http://myapp.example.com" \
 ## What You Get
-<CardGroup cols={2}>
+- **Graph Explorer** — Interactive node/edge search, path finding, and neighborhood expansion. Indexed search at 0.004ms on 118k-node graphs.
-  <Card title="Graph Explorer" icon="diagram-project">
+- **Ontology Hub** — SKOS vocabulary management, SHACL shape generation and validation, ontology alignment, health dashboard, and versioning.
-    Interactive node/edge search, path finding, and neighborhood expansion. Indexed search at 0.004ms on 118k-node graphs.
+- **Analytics** — Degree centrality, community detection, connectivity analysis, graph validation, and distance matrices.
-  </Card>
+- **REST API** — All features available as a REST API: fully documented at `/docs`.
-  <Card title="Ontology Hub" icon="sitemap">
+- **WebSocket Updates** — Real-time graph mutation events streamed over WebSocket at `/ws/graph-updates`.
-    SKOS vocabulary management, SHACL shape generation and validation, ontology alignment, health dashboard, and versioning.
+- **CLI Launcher** — `semantica-explorer --graph my_graph.json` for instant local startup.
  </Card>
  <Card title="Analytics" icon="chart-line">
    Degree centrality, community detection, connectivity analysis, graph validation, and distance matrices.
  </Card>
  <Card title="REST API" icon="code">
    All features available as a REST API: fully documented at `/docs`.
  </Card>
  <Card title="WebSocket Updates" icon="bolt">
    Real-time graph mutation events streamed over WebSocket at `/ws/graph-updates`.
  </Card>
  <Card title="CLI Launcher" icon="terminal">
    `semantica-explorer --graph my_graph.json` for instant local startup.
  </Card>
 </CardGroup>
 ## Features
@@ -412,17 +398,7 @@ Semantic neighborhood requires node embeddings stored in node properties (keys `
 **Session state lost after restart**
 Session state is in-memory only. Use `POST /api/export` to save a JSON snapshot before shutting down.
-<CardGroup cols={2}>
+- [Context](context) — Build and save the ContextGraph that Explorer loads.
-  <Card title="Context" icon="brain" href="context">
+- [Ontology](ontology) — Programmatic ontology management and SHACL generation.
-    Build and save the ContextGraph that Explorer loads.
+- [Visualization](visualization) — Programmatic graph rendering without the Explorer server.
-  </Card>
+- [Export](export) — Export to RDF, Parquet, and other formats without launching a server.
  <Card title="Ontology" icon="sitemap" href="ontology">
    Programmatic ontology management and SHACL generation.
  </Card>
  <Card title="Visualization" icon="chart-bar" href="visualization">
    Programmatic graph rendering without the Explorer server.
  </Card>
  <Card title="Export" icon="file-export" href="export">
    Export to RDF, Parquet, and other formats without launching a server.
  </Card>
 </CardGroup>
@@ -381,17 +381,7 @@ The `export_csv` convenience function delegates to `CSVExporter.export()`. For p
  **Match your export format to your consumer.** Neo4j → `cypher`; ArangoDB → `aql`; Gephi/yEd → `graphml` or `gexf`; semantic web tools → `turtle` or `json-ld`; analytics pipelines → `parquet`; zero-copy IPC → `arrow`.
 </Tip>
-<CardGroup cols={2}>
+- [Triplet Store](triplet_store) — Store RDF exports in a SPARQL-queryable backend.
-  <Card title="Triplet Store" icon="table" href="triplet_store">
+- [Ontology](ontology) — Export OWL ontologies.
-    Store RDF exports in a SPARQL-queryable backend.
+- [Provenance](provenance) — Include provenance metadata in RDF exports.
-  </Card>
+- [Pipeline](pipeline) — Add export as a final pipeline step.
  <Card title="Ontology" icon="sitemap" href="ontology">
    Export OWL ontologies.
  </Card>
  <Card title="Provenance" icon="link" href="provenance">
    Include provenance metadata in RDF exports.
  </Card>
  <Card title="Pipeline" icon="gear" href="pipeline">
    Add export as a final pipeline step.
  </Card>
 </CardGroup>
@@ -28,38 +28,24 @@ icon: "server"
 ## What You Get
-<CardGroup cols={2}>
+- **GraphStore** — Unified API across Neo4j, FalkorDB, Apache AGE, Amazon Neptune
-  <Card title="GraphStore" icon="server">
+  - Context manager support for automatic connection cleanup
-    - Unified API across Neo4j, FalkorDB, Apache AGE, Amazon Neptune
+  - `create_nodes()` for bulk loading: faster than individual calls
-    - Context manager support for automatic connection cleanup
+- **QueryEngine** — Parameterized Cypher construction prevents injection attacks
-    - `create_nodes()` for bulk loading: faster than individual calls
+  - Optional in-process result caching with `use_cache=True`
-  </Card>
+  - `clear_cache()` on writes, toggle with `enable_cache()` / `disable_cache()`
-  <Card title="QueryEngine" icon="magnifying-glass">
+- **GraphAnalytics** — Degree centrality ordered by degree DESC
-    - Parameterized Cypher construction prevents injection attacks
+  - Connected component assignment
-    - Optional in-process result caching with `use_cache=True`
+  - Shortest path between nodes, neighbor traversal up to N hops
-    - `clear_cache()` on writes, toggle with `enable_cache()` / `disable_cache()`
+- **Bulk Operations** — `create_nodes(list)`: one round-trip for many nodes
-  </Card>
+  - `create_relationship()` with typed properties
-  <Card title="GraphAnalytics" icon="chart-line">
+  - `delete_node(detach=True)` removes all connected relationships
-    - Degree centrality ordered by degree DESC
+- **Schema Management** — `create_index(label, property_name=)`: makes MATCH queries orders-of-magnitude faster
-    - Connected component assignment
+  - `get_stats()`: node counts, edge counts, type breakdown
-    - Shortest path between nodes, neighbor traversal up to N hops
+  - Create indexes before bulk loading for best performance
-  </Card>
+- **Path Traversal** — `shortest_path()` returns `length`, `nodes`, `relationships`
-  <Card title="Bulk Operations" icon="layer-group">
+  - `get_neighbors()` with direction and depth control
-    - `create_nodes(list)`: one round-trip for many nodes
+  - Cross-backend path traversal via the unified API
    - `create_relationship()` with typed properties
    - `delete_node(detach=True)` removes all connected relationships
  </Card>
  <Card title="Schema Management" icon="table">
    - `create_index(label, property_name=)`: makes MATCH queries orders-of-magnitude faster
    - `get_stats()`: node counts, edge counts, type breakdown
    - Create indexes before bulk loading for best performance
  </Card>
  <Card title="Path Traversal" icon="route">
    - `shortest_path()` returns `length`, `nodes`, `relationships`
    - `get_neighbors()` with direction and depth control
    - Cross-backend path traversal via the unified API
  </Card>
 </CardGroup>
 ## Getting Started
@@ -517,17 +503,7 @@ stats = store.get_stats()
  </Tab>
 </Tabs>
-<CardGroup cols={2}>
+- [KG Module](kg) — Build the graph before persisting it.
-  <Card title="KG Module" icon="diagram-project" href="kg">
+- [Triplet Store](triplet_store) — RDF triple store for semantic web and SPARQL queries.
-    Build the graph before persisting it.
+- [Visualization](visualization) — Visualize graphs stored in any backend.
-  </Card>
+- [Context](context) — AgentContext uses GraphStore for memory retrieval.
  <Card title="Triplet Store" icon="table" href="triplet_store">
    RDF triple store for semantic web and SPARQL queries.
  </Card>
  <Card title="Visualization" icon="chart-bar" href="visualization">
    Visualize graphs stored in any backend.
  </Card>
  <Card title="Context" icon="brain" href="context">
    AgentContext uses GraphStore for memory retrieval.
  </Card>
 </CardGroup>
@@ -625,17 +625,7 @@ from semantica.ingest import ingest_file
 result = ingest_file("source_path", method="my_format")
 ```
-<CardGroup cols={2}>
+- [Parse](parse) — Parse raw sources into structured text and tables.
-  <Card title="Parse" icon="file-lines" href="parse">
+- [Pipeline](pipeline) — Orchestrate ingest as the first pipeline step.
-    Parse raw sources into structured text and tables.
+- [Snowflake Integration](../integrations/snowflake) — Snowflake-specific setup and authentication guide.
-  </Card>
+- [Provenance](provenance) — Track lineage from ingest through to inference.
  <Card title="Pipeline" icon="gear" href="pipeline">
    Orchestrate ingest as the first pipeline step.
  </Card>
  <Card title="Snowflake Integration" icon="snowflake" href="../integrations/snowflake">
    Snowflake-specific setup and authentication guide.
  </Card>
  <Card title="Provenance" icon="link" href="provenance">
    Track lineage from ingest through to inference.
  </Card>
 </CardGroup>
@@ -316,20 +316,10 @@ kg:
    default_validity: infinite
 ```
-<CardGroup cols={2}>
+- [Graph Store](graph_store) — Persist graphs in Neo4j, FalkorDB, or Apache AGE.
-  <Card title="Graph Store" icon="server" href="graph_store">
+- [Semantic Extract](semantic_extract) — Source of entities and relationships fed to GraphBuilder.
-    Persist graphs in Neo4j, FalkorDB, or Apache AGE.
+- [Visualization](visualization) — Visualize knowledge graphs interactively.
-  </Card>
+- [Conflicts](conflicts) — Conflict detection and resolution.
  <Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
    Source of entities and relationships fed to GraphBuilder.
  </Card>
  <Card title="Visualization" icon="chart-bar" href="visualization">
    Visualize knowledge graphs interactively.
  </Card>
  <Card title="Conflicts" icon="triangle-exclamation" href="conflicts">
    Conflict detection and resolution.
  </Card>
 </CardGroup>
 ### Cookbooks
@@ -439,17 +439,7 @@ extractor = NERExtractor(
 )
 ```
-<CardGroup cols={2}>
+- [Semantic Extract](semantic_extract) — Use LLMs for NER and relation extraction.
-  <Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
+- [Agno Integration](../integrations/agno) — LLM providers in Agno multi-agent teams.
-    Use LLMs for NER and relation extraction.
+- [Reasoning](reasoning) — LLM-backed deductive and abductive reasoning.
-  </Card>
+- [Context](context) — GraphRAG uses LLMs for reasoning over knowledge graphs.
  <Card title="Agno Integration" icon="robot" href="../integrations/agno">
    LLM providers in Agno multi-agent teams.
  </Card>
  <Card title="Reasoning" icon="brain" href="reasoning">
    LLM-backed deductive and abductive reasoning.
  </Card>
  <Card title="Context" icon="diagram-project" href="context">
    GraphRAG uses LLMs for reasoning over knowledge graphs.
  </Card>
 </CardGroup>
@@ -40,26 +40,12 @@ python -m semantica.mcp_server
 ## What You Get
-<CardGroup cols={2}>
+- **12 MCP Tools** — Extract entities, extract relations, record decisions, query decisions, find precedents, trace causal chains, add entities, add relationships, run analytics, summarise graph, run reasoning, export graph.
-  <Card title="12 MCP Tools" icon="wrench">
+- **3 Readable Resources** — Live graph JSON (`semantica://graph/summary`), decision list, and schema/version info: readable by any MCP client.
-    Extract entities, extract relations, record decisions, query decisions, find precedents, trace causal chains, add entities, add relationships, run analytics, summarise graph, run reasoning, export graph.
+- **Zero Infrastructure** — Runs over stdio: no server, no port, no Docker required. One config block to activate in any MCP client.
-  </Card>
+- **Persistent Graphs** — Point `SEMANTICA_KG_PATH` at a saved graph file to reload it automatically on every server startup.
-  <Card title="3 Readable Resources" icon="book-open">
+- **Decision Intelligence** — Record decisions, find precedents via hybrid similarity search, and trace causal chains across agent runs.
-    Live graph JSON (`semantica://graph/summary`), decision list, and schema/version info: readable by any MCP client.
+- **REST Alternative** — The [Explorer](explorer) module offers a full HTTP API and browser dashboard if you prefer programmatic access.
  </Card>
  <Card title="Zero Infrastructure" icon="bolt">
    Runs over stdio: no server, no port, no Docker required. One config block to activate in any MCP client.
  </Card>
  <Card title="Persistent Graphs" icon="database">
    Point `SEMANTICA_KG_PATH` at a saved graph file to reload it automatically on every server startup.
  </Card>
  <Card title="Decision Intelligence" icon="brain">
    Record decisions, find precedents via hybrid similarity search, and trace causal chains across agent runs.
  </Card>
  <Card title="REST Alternative" icon="globe">
    The [Explorer](explorer) module offers a full HTTP API and browser dashboard if you prefer programmatic access.
  </Card>
 </CardGroup>
 ## Installation
@@ -459,17 +445,7 @@ The MCP server exposes three readable resources:
 | `semantica://decisions/list` | All recorded decisions (up to 50) |
 | `semantica://schema/info` | Server version and available tools |
-<CardGroup cols={2}>
+- [Context](context) — The ContextGraph that the MCP server operates on.
-  <Card title="Context" icon="brain" href="context">
+- [Semantic Extract](semantic_extract) — NER and relation extraction powering the MCP tools.
-    The ContextGraph that the MCP server operates on.
+- [Reasoning](reasoning) — Forward-chaining engine behind run_reasoning.
-  </Card>
+- [Agno Integration](../integrations/agno) — Use Semantica inside Agno multi-agent teams.
  <Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
    NER and relation extraction powering the MCP tools.
  </Card>
  <Card title="Reasoning" icon="microchip" href="reasoning">
    Forward-chaining engine behind run_reasoning.
  </Card>
  <Card title="Agno Integration" icon="robot" href="../integrations/agno">
    Use Semantica inside Agno multi-agent teams.
  </Card>
 </CardGroup>
@@ -584,17 +584,7 @@ normalized = normalize_text("Apple Inc.", method="expand_suffixes")
 # → "Apple Incorporated"
 ```
-<CardGroup cols={2}>
+- [Parse](parse) — Parse documents before normalization.
-  <Card title="Parse" icon="file-lines" href="parse">
+- [Split](split) — Chunk normalized text for embedding.
-    Parse documents before normalization.
+- [Deduplication](deduplication) — Resolve duplicate entities after normalization.
-  </Card>
+- [Pipeline](pipeline) — Include normalization as a named pipeline step.
  <Card title="Split" icon="scissors" href="split">
    Chunk normalized text for embedding.
  </Card>
  <Card title="Deduplication" icon="copy" href="deduplication">
    Resolve duplicate entities after normalization.
  </Card>
  <Card title="Pipeline" icon="gear" href="pipeline">
    Include normalization as a named pipeline step.
  </Card>
 </CardGroup>
@@ -286,17 +286,7 @@ ontology_data = ingest_ontology("schema.jsonld")  # JSON-LD
  Ontology versioning (`VersionManager`, `OntologyVersion`) has moved to `semantica.change_management`. Import from there: `from semantica.change_management import VersionManager`.
 </Note>
-<CardGroup cols={2}>
+- [Reasoning](reasoning) — Apply inference rules over ontology axioms.
-  <Card title="Reasoning" icon="microchip" href="reasoning">
+- [Knowledge Graph](kg) — The graph being modeled by the ontology.
-    Apply inference rules over ontology axioms.
+- [Export](export) — Export ontologies as RDF, OWL, or JSON-LD.
-  </Card>
+- [Conflicts](conflicts) — Detect ontology constraint violations.
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    The graph being modeled by the ontology.
  </Card>
  <Card title="Export" icon="file-export" href="export">
    Export ontologies as RDF, OWL, or JSON-LD.
  </Card>
  <Card title="Conflicts" icon="triangle-exclamation" href="conflicts">
    Detect ontology constraint violations.
  </Card>
 </CardGroup>
@@ -297,17 +297,7 @@ for source in sources:
  Docling is an optional dependency. If `docling` is not installed, `DoclingParser` raises an `ImportError` with installation instructions: `pip install docling`. `DocumentParser` is always available and requires no extras.
 </Note>
-<CardGroup cols={2}>
+- [Ingest](ingest) — Load files before parsing.
-  <Card title="Ingest" icon="database" href="ingest">
+- [Split](split) — Chunk parsed text for embedding and extraction.
-    Load files before parsing.
+- [Docling Integration](../integrations/docling) — Full Docling integration setup guide.
-  </Card>
+- [Semantic Extract](semantic_extract) — Extract entities and relations from parsed text.
  <Card title="Split" icon="scissors" href="split">
    Chunk parsed text for embedding and extraction.
  </Card>
  <Card title="Docling Integration" icon="file-pdf" href="../integrations/docling">
    Full Docling integration setup guide.
  </Card>
  <Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
    Extract entities and relations from parsed text.
  </Card>
 </CardGroup>
@@ -29,26 +29,12 @@ icon: "gear"
 You could wire Semantica modules together with plain Python code. Pipelines add:
-<CardGroup cols={2}>
+- **Retry and failure handling** — A single bad document doesn't crash a 10,000-document run.
-  <Card title="Retry and failure handling" icon="arrow-rotate-right">
+- **Parallelism** — Run extraction across multiple workers with one parameter.
-    A single bad document doesn't crash a 10,000-document run.
+- **Progress tracking** — tqdm console bar or WebSocket streaming to Explorer.
-  </Card>
+- **Reproducibility** — Save the exact pipeline configuration to YAML and replay on any machine.
-  <Card title="Parallelism" icon="bolt">
+- **Delta mode** — On re-runs, only process documents that changed since the last run.
-    Run extraction across multiple workers with one parameter.
+- **Validation** — Catch misconfigured steps and dependency cycles before they fail mid-run.
  </Card>
  <Card title="Progress tracking" icon="chart-line">
    tqdm console bar or WebSocket streaming to Explorer.
  </Card>
  <Card title="Reproducibility" icon="floppy-disk">
    Save the exact pipeline configuration to YAML and replay on any machine.
  </Card>
  <Card title="Delta mode" icon="code-compare">
    On re-runs, only process documents that changed since the last run.
  </Card>
  <Card title="Validation" icon="shield-check">
    Catch misconfigured steps and dependency cycles before they fail mid-run.
  </Card>
 </CardGroup>
 <Note>
  Use plain module calls for quick scripts and notebooks. Use pipelines for anything you run repeatedly, at scale, or in production.
@@ -322,48 +308,33 @@ manager = PipelineTemplateManager()
 The `create_pipeline_from_template(name)` method returns a configured `PipelineBuilder`. Call `.build(pipeline_name)` on it to produce a runnable `Pipeline`.
-<CardGroup cols={2}>
+- **document_processing** — **Ingest → Parse → Normalize → Extract → Embed → Build KG** — Complete document processing from ingestion to knowledge graph.
  <Card title="document_processing" icon="diagram-project">
    **Ingest → Parse → Normalize → Extract → Embed → Build KG**
-    Complete document processing from ingestion to knowledge graph.
+  ```python
  builder  = manager.create_pipeline_from_template("document_processing")
  pipeline = builder.build("doc_pipeline")
  ```
-    ```python
+- **rag_pipeline** — **Ingest → Chunk → Embed → Store Vectors** — RAG pipeline for question answering: builds a vector-indexed store.
    builder  = manager.create_pipeline_from_template("document_processing")
    pipeline = builder.build("doc_pipeline")
    ```
  </Card>
  <Card title="rag_pipeline" icon="magnifying-glass">
    **Ingest → Chunk → Embed → Store Vectors**
-    RAG pipeline for question answering: builds a vector-indexed store.
+  ```python
  builder  = manager.create_pipeline_from_template("rag_pipeline")
  pipeline = builder.build("rag_pipeline")
  ```
-    ```python
+- **kg_construction** — **Ingest → Extract Entities → Extract Relations → Dedup → Resolve → Build Graph** — Knowledge graph construction from multiple sources.
    builder  = manager.create_pipeline_from_template("rag_pipeline")
    pipeline = builder.build("rag_pipeline")
    ```
  </Card>
  <Card title="kg_construction" icon="chart-bar">
    **Ingest → Extract Entities → Extract Relations → Dedup → Resolve → Build Graph**
-    Knowledge graph construction from multiple sources.
+  ```python
  builder  = manager.create_pipeline_from_template("kg_construction")
  pipeline = builder.build("kg_pipeline")
  ```
-    ```python
+- **ontology_generation** — **Extract Concepts → Infer Classes → Infer Properties → Generate OWL → Validate** — Ontology generation from extracted data.
    builder  = manager.create_pipeline_from_template("kg_construction")
    pipeline = builder.build("kg_pipeline")
    ```
  </Card>
  <Card title="ontology_generation" icon="shield-check">
    **Extract Concepts → Infer Classes → Infer Properties → Generate OWL → Validate**
-    Ontology generation from extracted data.
+  ```python
-
+  builder  = manager.create_pipeline_from_template("ontology_generation")
-    ```python
+  pipeline = builder.build("ontology_pipeline")
-    builder  = manager.create_pipeline_from_template("ontology_generation")
+  ```
    pipeline = builder.build("ontology_pipeline")
    ```
  </Card>
 </CardGroup>
 <Tip>
  **Use templates from `PipelineTemplateManager` for common patterns.** `create_pipeline_from_template("kg_construction")` wires normalization, deduplication, conflict detection, and graph construction in the correct order: saving you from common mistakes like deduplicating before normalizing.
@@ -583,17 +554,7 @@ StepStatus.SKIPPED    # Skipped due to FailureHandler "skip" strategy
  </Accordion>
 </AccordionGroup>
-<CardGroup cols={2}>
+- [Ingest](ingest) — First step in most pipelines.
-  <Card title="Ingest" icon="database" href="ingest">
+- [Semantic Extract](semantic_extract) — Core extraction step.
-    First step in most pipelines.
+- [Knowledge Graph](kg) — Graph construction step.
-  </Card>
+- [Export](export) — Final output step.
  <Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
    Core extraction step.
  </Card>
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    Graph construction step.
  </Card>
  <Card title="Export" icon="file-export" href="export">
    Final output step.
  </Card>
 </CardGroup>
@@ -517,17 +517,7 @@ Provenance tracking in Semantica produces the following audit artifacts:
  `ProvenanceManager` does not include built-in Turtle or JSON-LD serialization. Use `entry.to_dict()` and `get_lineage()` to retrieve provenance data, then serialize with your preferred RDF library if W3C PROV-O RDF output is required.
 </Note>
-<CardGroup cols={2}>
+- [Change Management](change_management) — Version control and snapshot audit trails.
-  <Card title="Change Management" icon="clock-rotate-left" href="change_management">
+- [Ingest](ingest) — Provenance begins at the ingestion stage.
-    Version control and snapshot audit trails.
+- [Export](export) — Include provenance metadata in RDF exports.
-  </Card>
+- [Context](context) — Decision provenance via AgentContext.
  <Card title="Ingest" icon="database" href="ingest">
    Provenance begins at the ingestion stage.
  </Card>
  <Card title="Export" icon="file-export" href="export">
    Include provenance metadata in RDF exports.
  </Card>
  <Card title="Context" icon="brain" href="context">
    Decision provenance via AgentContext.
  </Card>
 </CardGroup>
@@ -31,26 +31,12 @@ icon: "microchip"
 ## Which Engine Should I Use?
-<CardGroup cols={2}>
+- [Reasoner](#reasoner-forwardbackward-chaining) — IF/THEN rules, forward and backward chaining. **Start here**: covers 90% of use cases. No query language required.
-  <Card title="Reasoner" icon="arrow-right-arrow-left" href="#reasoner-forwardbackward-chaining">
+- [GraphReasoner](#graphreasoner) — Natural language queries over a knowledge graph via LLM. No SPARQL or rules: just ask a question.
-    IF/THEN rules, forward and backward chaining. **Start here**: covers 90% of use cases. No query language required.
+- [DatalogReasoner](#datalogreasoner) — Recursive Horn clause rules with guaranteed termination. Use for complex multi-hop transitive rules.
-  </Card>
+- [ReteEngine](#reteengine) — Rete pattern matching for high-frequency inference. Use when you need to match many facts against many rules simultaneously.
-  <Card title="GraphReasoner" icon="robot" href="#graphreasoner">
+- [SPARQLReasoner](#sparqlreasoner) — SPARQL query expansion and rule-based inference. Use when you're working with RDF/OWL data.
-    Natural language queries over a knowledge graph via LLM. No SPARQL or rules: just ask a question.
+- [TemporalReasoningEngine](#temporalreasoningengine) — All 13 Allen interval algebra relations. Use for time-aware reasoning: overlaps, before/after, during, contains.
  </Card>
  <Card title="DatalogReasoner" icon="code" href="#datalogreasoner">
    Recursive Horn clause rules with guaranteed termination. Use for complex multi-hop transitive rules.
  </Card>
  <Card title="ReteEngine" icon="bolt" href="#reteengine">
    Rete pattern matching for high-frequency inference. Use when you need to match many facts against many rules simultaneously.
  </Card>
  <Card title="SPARQLReasoner" icon="database" href="#sparqlreasoner">
    SPARQL query expansion and rule-based inference. Use when you're working with RDF/OWL data.
  </Card>
  <Card title="TemporalReasoningEngine" icon="clock" href="#temporalreasoningengine">
    All 13 Allen interval algebra relations. Use for time-aware reasoning: overlaps, before/after, during, contains.
  </Card>
 </CardGroup>
 ## Getting Started
@@ -479,17 +465,7 @@ step.confidence     # float
  `GraphReasoner` requires a configured LLM provider. If the provider fails to initialize, `reason()` returns an error string instead of raising. Check `reasoner.provider is not None` before calling if you need to surface failures explicitly.
 </Warning>
-<CardGroup cols={2}>
+- [Knowledge Graph](kg) — The knowledge graph being reasoned over.
-  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
+- [Ontology](ontology) — Ontology axioms and SHACL constraints for logical reasoning.
-    The knowledge graph being reasoned over.
+- [Triplet Store](triplet_store) — RDF backend for SPARQL-based reasoning.
-  </Card>
+- [Context](context) — Reasoning integrated into agent decision intelligence.
  <Card title="Ontology" icon="sitemap" href="ontology">
    Ontology axioms and SHACL constraints for logical reasoning.
  </Card>
  <Card title="Triplet Store" icon="table" href="triplet_store">
    RDF backend for SPARQL-based reasoning.
  </Card>
  <Card title="Context" icon="brain" href="context">
    Reasoning integrated into agent decision intelligence.
  </Card>
 </CardGroup>
@@ -23,26 +23,12 @@ icon: "database"
 ## What You Get
-<CardGroup cols={2}>
+- **SeedDataManager** — Register sources, build a foundation graph, validate quality, and merge with extracted data.
-  <Card title="SeedDataManager" icon="database">
+- **SeedDataSource** — Typed source definition supporting CSV, JSON, SQL, and API with format-specific config.
-    Register sources, build a foundation graph, validate quality, and merge with extracted data.
+- **Foundation Graph** — Build a foundation graph from all registered sources in one pass, ready to merge with extracted data.
-  </Card>
+- **Merge Strategies** — `seed_first`, `extracted_first`, and `merge` with property-level conflict detection.
-  <Card title="SeedDataSource" icon="file-code">
+- **Validation** — Required field checks, ID uniqueness, type consistency, reference integrity, and encoding validation before loading.
-    Typed source definition supporting CSV, JSON, SQL, and API with format-specific config.
+- **Versioning** — Track seed data versions across pipeline runs and diff changes between versions.
  </Card>
  <Card title="Foundation Graph" icon="circle-plus">
    Build a foundation graph from all registered sources in one pass, ready to merge with extracted data.
  </Card>
  <Card title="Merge Strategies" icon="arrows-merge">
    `seed_first`, `extracted_first`, and `merge` with property-level conflict detection.
  </Card>
  <Card title="Validation" icon="shield-check">
    Required field checks, ID uniqueness, type consistency, reference integrity, and encoding validation before loading.
  </Card>
  <Card title="Versioning" icon="clock-rotate-left">
    Track seed data versions across pipeline runs and diff changes between versions.
  </Card>
 </CardGroup>
 <Tip>
  **When to use the Seed Module:** Bootstrapping with structured reference data (taxonomies, user lists, product catalogs), loading immutable facts (ISO country codes, standard ontology terms) that extracted data should not override, ensuring test reproducibility with deterministic datasets, and anchoring entity disambiguation with canonical forms.
@@ -335,17 +321,7 @@ export SEMANTICA_SEED_MERGE_STRATEGY=seed_first
  **Use YAML configuration for production deployments.** Hard-coding source paths in Python scripts makes environment-switching (dev → staging → prod) fragile. Declare sources in `config.yaml` under the `seed:` key and override paths with `SEMANTICA_SEED_DATA_DIR`. This way, the same code runs in every environment.
 </Tip>
-<CardGroup cols={2}>
+- [Ingest](ingest) — Load unstructured data alongside seed data.
-  <Card title="Ingest" icon="file-import" href="ingest">
+- [Knowledge Graph](kg) — The target graph that seed data populates.
-    Load unstructured data alongside seed data.
+- [Deduplication](deduplication) — Handle duplicates during seed-extracted merge.
-  </Card>
+- [Pipeline](pipeline) — Incorporate seed loading as a named pipeline step.
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    The target graph that seed data populates.
  </Card>
  <Card title="Deduplication" icon="copy" href="deduplication">
    Handle duplicates during seed-extracted merge.
  </Card>
  <Card title="Pipeline" icon="gear" href="pipeline">
    Incorporate seed loading as a named pipeline step.
  </Card>
 </CardGroup>
@@ -410,17 +410,7 @@ triplets      = trip.extract(text)
 | `ml` | Fast | Free | High | Limited |
 | `llm` | Medium | API cost | Highest | Yes (schema) |
-<CardGroup cols={2}>
+- [LLM Providers](llms) — Configure which LLM is used for extraction.
-  <Card title="LLM Providers" icon="microchip" href="llms">
+- [Knowledge Graph](kg) — Build graphs from extracted entities and relationships.
-    Configure which LLM is used for extraction.
+- [Parse Module](parse) — Parse documents before extraction.
-  </Card>
+- [Deduplication](deduplication) — Resolve duplicate entities after extraction.
  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
    Build graphs from extracted entities and relationships.
  </Card>
  <Card title="Parse Module" icon="file-lines" href="parse">
    Parse documents before extraction.
  </Card>
  <Card title="Deduplication" icon="copy" href="deduplication">
    Resolve duplicate entities after extraction.
  </Card>
 </CardGroup>
@@ -51,23 +51,11 @@ Semantica's chunking methods are designed to avoid these failure modes.
 ## What You Get
-<CardGroup cols={2}>
+- **TextSplitter** — Unified interface for 11 chunking strategies: swap methods without changing downstream code.
-  <Card title="TextSplitter" icon="scissors">
+- **Semantic Chunking** — Embedding-based topic shift detection: splits only when the topic actually changes.
-    Unified interface for 11 chunking strategies: swap methods without changing downstream code.
+- **Entity-Aware Chunking** — Entity spans never cross chunk boundaries: guaranteed by boundary adjustment.
-  </Card>
+- **Relation-Aware Chunking** — Subject–predicate–object triplets kept within a single chunk for KG pipelines.
-  <Card title="Semantic Chunking" icon="brain">
+- **Chunk Object** — Output dataclass with text, character offsets, optional id, and method-specific metadata.
    Embedding-based topic shift detection: splits only when the topic actually changes.
  </Card>
  <Card title="Entity-Aware Chunking" icon="user">
    Entity spans never cross chunk boundaries: guaranteed by boundary adjustment.
  </Card>
  <Card title="Relation-Aware Chunking" icon="arrows-left-right">
    Subject–predicate–object triplets kept within a single chunk for KG pipelines.
  </Card>
  <Card title="Chunk Object" icon="box">
    Output dataclass with text, character offsets, optional id, and method-specific metadata.
  </Card>
 </CardGroup>
 ## Quick Start
@@ -385,17 +373,7 @@ for chunk in chunks:
 For the full pipeline orchestration API, see the [Pipeline reference](pipeline).
-<CardGroup cols={2}>
+- [Parse](parse) — Parse documents before chunking: produces sections and metadata.
-  <Card title="Parse" icon="file-lines" href="parse">
+- [Embeddings](embeddings) — Embed chunks for vector search and semantic chunking.
-    Parse documents before chunking: produces sections and metadata.
+- [Semantic Extract](semantic_extract) — Extract entities and relations from individual chunks.
-  </Card>
+- [Pipeline](pipeline) — Integrate splitting as a named pipeline step.
  <Card title="Embeddings" icon="vector-square" href="embeddings">
    Embed chunks for vector search and semantic chunking.
  </Card>
  <Card title="Semantic Extract" icon="magnifying-glass" href="semantic_extract">
    Extract entities and relations from individual chunks.
  </Card>
  <Card title="Pipeline" icon="gear" href="pipeline">
    Integrate splitting as a named pipeline step.
  </Card>
 </CardGroup>
@@ -19,26 +19,12 @@ icon: "table"
 ## What You Get
-<CardGroup cols={2}>
+- **TripletStore** — Unified interface across Blazegraph, Apache Jena, and RDF4J: swap backends with one parameter.
-  <Card title="TripletStore" icon="server">
+- **SPARQL** — Full SPARQL SELECT, ASK, CONSTRUCT, and UPDATE query support via `execute_query()`.
-    Unified interface across Blazegraph, Apache Jena, and RDF4J: swap backends with one parameter.
+- **Bulk Loading** — `add_triplets()` batches writes with configurable batch size, retry logic, and progress tracking.
-  </Card>
+- **SKOS Vocabulary** — Built-in helpers: `add_skos_concept()` and `get_skos_concepts()` for controlled vocabulary management.
-  <Card title="SPARQL" icon="magnifying-glass">
+- **Named Graphs** — Blazegraph and RDF4J support named graph scoping via `graph=` on `execute_query()`.
-    Full SPARQL SELECT, ASK, CONSTRUCT, and UPDATE query support via `execute_query()`.
+- **Delta Computation** — `compute_delta(old_graph_uri, new_graph_uri)` returns added and removed triples between two named graph snapshots.
  </Card>
  <Card title="Bulk Loading" icon="layer-group">
    `add_triplets()` batches writes with configurable batch size, retry logic, and progress tracking.
  </Card>
  <Card title="SKOS Vocabulary" icon="diagram-project">
    Built-in helpers: `add_skos_concept()` and `get_skos_concepts()` for controlled vocabulary management.
  </Card>
  <Card title="Named Graphs" icon="folder-tree">
    Blazegraph and RDF4J support named graph scoping via `graph=` on `execute_query()`.
  </Card>
  <Card title="Delta Computation" icon="code-compare">
    `compute_delta(old_graph_uri, new_graph_uri)` returns added and removed triples between two named graph snapshots.
  </Card>
 </CardGroup>
 ## Getting Started
@@ -490,17 +476,7 @@ for row in result.bindings:
    print(row)
 ```
-<CardGroup cols={2}>
+- [Export](export) — Export knowledge graphs to RDF formats.
-  <Card title="Export" icon="file-export" href="export">
+- [Ontology](ontology) — Load OWL ontologies and store as RDF triples.
-    Export knowledge graphs to RDF formats.
+- [Reasoning](reasoning) — SPARQL-based property chain inference.
-  </Card>
+- [Graph Store](graph_store) — Property graph alternative for Cypher queries.
  <Card title="Ontology" icon="sitemap" href="ontology">
    Load OWL ontologies and store as RDF triples.
  </Card>
  <Card title="Reasoning" icon="microchip" href="reasoning">
    SPARQL-based property chain inference.
  </Card>
  <Card title="Graph Store" icon="server" href="graph_store">
    Property graph alternative for Cypher queries.
  </Card>
 </CardGroup>
@@ -36,26 +36,12 @@ Most users won't call utils directly: it's the **shared foundation** for all mod
 ## What You Get
-<CardGroup cols={2}>
+- **Logging** — Structured logging with `@log_execution_time` decorator and quality metrics via environment variables.
-  <Card title="Logging" icon="scroll">
+- **Validation** — `validate_entity` and `validate_config` with a typed `ValidationError` carrying field and value context.
-    Structured logging with `@log_execution_time` decorator and quality metrics via environment variables.
+- **Progress Tracking** — `track_progress` wraps any iterable: auto-detects console vs Jupyter for the right renderer.
-  </Card>
+- **Helper Functions** — `clean_text`, `hash_data`, `safe_filename`, and nested dict utilities used throughout the framework.
-  <Card title="Validation" icon="shield-check">
+- **Exception Hierarchy** — `SemanticaError` → `ValidationError`, `ProcessingError`: typed exceptions for targeted recovery.
-    `validate_entity` and `validate_config` with a typed `ValidationError` carrying field and value context.
+- **File Utilities** — `read_json_file` raises `FileNotFoundError` or `json.JSONDecodeError` on failure: no boilerplate try/except around JSON I/O.
  </Card>
  <Card title="Progress Tracking" icon="bars-progress">
    `track_progress` wraps any iterable: auto-detects console vs Jupyter for the right renderer.
  </Card>
  <Card title="Helper Functions" icon="wrench">
    `clean_text`, `hash_data`, `safe_filename`, and nested dict utilities used throughout the framework.
  </Card>
  <Card title="Exception Hierarchy" icon="triangle-exclamation">
    `SemanticaError` → `ValidationError`, `ProcessingError`: typed exceptions for targeted recovery.
  </Card>
  <Card title="File Utilities" icon="file">
    `read_json_file` raises `FileNotFoundError` or `json.JSONDecodeError` on failure: no boilerplate try/except around JSON I/O.
  </Card>
 </CardGroup>
 ## Logging
@@ -226,11 +212,5 @@ from semantica.utils import read_json_file
 config = read_json_file("config.json")
 ```
-<CardGroup cols={2}>
+- [Core](core) — Framework orchestration that uses Utils internally.
-  <Card title="Core" icon="gear" href="core">
+- [Pipeline](pipeline) — Uses ProgressTracker for per-step tracking.
    Framework orchestration that uses Utils internally.
  </Card>
  <Card title="Pipeline" icon="arrows-turn-to-dots" href="pipeline">
    Uses ProgressTracker for per-step tracking.
  </Card>
 </CardGroup>
@@ -32,38 +32,24 @@ icon: "database"
 ## What You Get
-<CardGroup cols={2}>
+- **VectorStore** — Unified interface across FAISS, Pinecone, Weaviate, Qdrant, Milvus, PgVector
-  <Card title="VectorStore" icon="database">
+  - One-line backend swap: no application code changes
-    - Unified interface across FAISS, Pinecone, Weaviate, Qdrant, Milvus, PgVector
+  - `add_documents()` auto-embeds; `store_vectors()` for pre-computed embeddings
-    - One-line backend swap: no application code changes
+- **HybridSearch** — Dense vector similarity with metadata filtering
-    - `add_documents()` auto-embeds; `store_vectors()` for pre-computed embeddings
+  - RRF or weighted-average fusion strategies
-  </Card>
+  - Multi-source fusion across separate collections
-  <Card title="HybridSearch" icon="magnifying-glass">
+- **MetadataStore** — Rich metadata indexing by field values
-    - Dense vector similarity with metadata filtering
+  - Update metadata fields without re-embedding
-    - RRF or weighted-average fusion strategies
+  - OR and AND query operators
-    - Multi-source fusion across separate collections
+- **NamespaceManager** — Structural per-tenant namespace isolation
-  </Card>
+  - Faster queries (smaller search space per tenant)
-  <Card title="MetadataStore" icon="table">
+  - Safer than metadata-filter-only separation
-    - Rich metadata indexing by field values
+- **Batch Operations** — Bulk add, delete, and metadata updates
-    - Update metadata fields without re-embedding
+  - Parallel embedding with configurable `batch_size` and `workers`
-    - OR and AND query operators
+  - In-place vector updates without full re-indexing
-  </Card>
+- **FAISS Index Types** — flat, ivf, hnsw, and pq index types
-  <Card title="NamespaceManager" icon="folder-tree">
+  - Full configuration control via `FAISSStore.create_index()`
-    - Structural per-tenant namespace isolation
+  - `save()` / `load()` for disk persistence
    - Faster queries (smaller search space per tenant)
    - Safer than metadata-filter-only separation
  </Card>
  <Card title="Batch Operations" icon="layer-group">
    - Bulk add, delete, and metadata updates
    - Parallel embedding with configurable `batch_size` and `workers`
    - In-place vector updates without full re-indexing
  </Card>
  <Card title="FAISS Index Types" icon="chart-scatter">
    - flat, ivf, hnsw, and pq index types
    - Full configuration control via `FAISSStore.create_index()`
    - `save()` / `load()` for disk persistence
  </Card>
 </CardGroup>
 ## Getting Started
@@ -602,17 +588,7 @@ store.create_index(index_type="pq", metric="L2", m=8)
  </Tab>
 </Tabs>
-<CardGroup cols={2}>
+- [Embeddings](embeddings) — Generate the vectors stored here.
-  <Card title="Embeddings" icon="vector-square" href="embeddings">
+- [Context](context) — AgentContext uses VectorStore for memory retrieval.
-    Generate the vectors stored here.
+- [Split](split) — Chunk documents before embedding and storing.
-  </Card>
+- [Ingest](ingest) — Ingest documents before embedding and storing.
  <Card title="Context" icon="brain" href="context">
    AgentContext uses VectorStore for memory retrieval.
  </Card>
  <Card title="Split" icon="scissors" href="split">
    Chunk documents before embedding and storing.
  </Card>
  <Card title="Ingest" icon="download" href="ingest">
    Ingest documents before embedding and storing.
  </Card>
 </CardGroup>
@@ -290,17 +290,7 @@ semantica-explorer --graph my_graph.json
 See the [Explorer reference](explorer) for the full feature set and REST API.
-<CardGroup cols={2}>
+- [Knowledge Graph](kg) — The graph being visualized.
-  <Card title="Knowledge Graph" icon="diagram-project" href="kg">
+- [Ontology](ontology) — Visualize ontology class structure.
-    The graph being visualized.
+- [Embeddings](embeddings) — Generate the embeddings visualized here.
-  </Card>
+- [Explorer](explorer) — Full interactive Knowledge Explorer UI.
  <Card title="Ontology" icon="sitemap" href="ontology">
    Visualize ontology class structure.
  </Card>
  <Card title="Embeddings" icon="vector-square" href="embeddings">
    Generate the embeddings visualized here.
  </Card>
  <Card title="Explorer" icon="globe" href="explorer">
    Full interactive Knowledge Explorer UI.
  </Card>
 </CardGroup>