fix: handle Qdrant vector count compatibility

.github/workflows/ci.yml

@@ -97,10 +97,24 @@ jobs:
       - name: Build Explorer frontend
         working-directory: explorer
         run: npm run build
-      - name: Install core package and base dependencies
+      - name: Install Explorer backend test dependencies
         run: |
-          # Verify that core semantica installs cleanly with only its base dependencies
-          # (no optional extras) and that core imports and lazy missing-dependency hints work.
+          # Run the deterministic backend path before the all-extras CI
+          # environment is installed.  The Explorer extra supplies the
+          # production API dependencies without importing optional vector
+          # providers such as Pinecone during test collection.
+          #
+          # --no-deps + a separate hash-pinned install (rather than the old
+          # `pip install -e ".[explorer]" pytest==9.1.1`) so every fetched
+          # package is hash-verified (Scorecard Pinned-Dependencies); the
+          # local editable install itself has nothing to hash.
+          # .github/requirements/explorer-extra-py311.txt is
+          # `uv pip compile pyproject.toml --extra explorer --python-version 3.11 --constraint requirements-ci.txt --generate-hashes`
+          # - regenerate it the same way if pyproject.toml's base/explorer
+          # deps change. Resolved specifically for this job's python 3.11
+          # (see the Dockerfile's explorer-extra-py313.txt for why this
+          # can't be shared with python 3.13: audioread needs extra
+          # standard-aifc/standard-sunau hashes only on 3.13+).
           #
           # --no-deps only skips *runtime* dependency resolution - `-e .`
           # still does a PEP 517 build, which by default creates an isolated
@@ -111,30 +125,8 @@ jobs:
           # copies instead of fetching its own.
           pip install -r .github/requirements/pep517-build.txt --require-hashes
           pip install --no-deps --no-build-isolation -e .
-          pip install -r .github/requirements/base-deps.txt --require-hashes
-          pip install -r .github/requirements/pytest-tool.txt --require-hashes
-      - name: Verify core-only package importability and slim behavior
-        run: |
-          python -c "
-          import semantica
-          print('semantica', semantica.__version__, 'core installed and importable')
-          "
-          pytest -q tests/test_issue_1513_slim_core.py
-      - name: Install Explorer backend test dependencies
-        run: |
-          # Run the deterministic backend path before the all-extras CI
-          # environment is installed.  The Explorer extra supplies the
-          # production API dependencies without importing optional vector
-          # providers such as Pinecone during test collection.
-          #
-          # .github/requirements/explorer-extra-py311.txt is
-          # `uv pip compile pyproject.toml --extra explorer --python-version 3.11 --constraint requirements-ci.txt --generate-hashes`
-          # - regenerate it the same way if pyproject.toml's base/explorer
-          # deps change. Resolved specifically for this job's python 3.11
-          # (see the Dockerfile's explorer-extra-py313.txt for why this
-          # can't be shared with python 3.13: audioread needs extra
-          # standard-aifc/standard-sunau hashes only on 3.13+).
           pip install -r .github/requirements/explorer-extra-py311.txt --require-hashes
+          pip install -r .github/requirements/pytest-tool.txt --require-hashes
       - name: Test deterministic Explorer backend path
         run: |
           pytest -q tests/explorer/test_explorer_deterministic_rendering_e2e.py

CHANGELOG.md

@@ -9,32 +9,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-## [0.7.0] - 2026-09-07
-
-### Changed
-
-- **Slim core dependencies: moved ~22 heavy packages to optional extras** (#1513)
-  - Core dependencies in `pyproject.toml` are now reduced to exactly 22 direct packages: `numpy`, `pandas`, `scipy`, `scikit-learn`, `rdflib`, `networkx`, `requests`, `chardet`, `protobuf`, `grpcio`, `pillow`, `pydantic`, `click`, `rich`, `tqdm`, `pyyaml`, `toml`, `python-dotenv`, `loguru`, `structlog`, `httpx`, and `pyarrow`.
-  - Heavy ML/NLP, visualization, document parsing, and ingestion packages moved into granular optional extras:
-    - `models-huggingface`: `torch`, `transformers`
-    - `embeddings-local`: `sentence-transformers`, `fastembed`, `onnxruntime`, `tokenizers`
-    - `nlp-spacy`: `spacy`
-    - `viz`: expanded to include `matplotlib`, `seaborn`, `plotly`, `ipywidgets`, `umap-learn`, alongside `pyvis`, `graphviz`, and `d3blocks`
-    - `media`: `librosa`, `opencv-python`
-    - `vectorstore-faiss`: `faiss-cpu` (also included in `vectorstore-all`)
-    - `documents`: `python-docx`, `openpyxl`, `lxml`, `beautifulsoup4`
-    - `ingest-git`: `GitPython`
-    - `graph-embeddings`: `gensim` (also included in `graph-all`)
-  - Full bundled behavior preserved via `pip install "semantica[all]"`, which includes all optional extras. Pinning `semantica<0.7.0` remains a permanent escape hatch for legacy workflows.
-  - Safe lazy construction across parsers and visualizers:
-    - `DOCXParser`, `ExcelParser`, `HTMLParser`, and `XMLParser` remain constructible without error on `__init__()`. They fail only upon calling `.parse()` with actionable error messages directing users to install `semantica[documents]`.
-    - `XMLParser` automatically falls back to standard library `xml.etree` (`_parse_with_etree`) when `lxml` is not installed, preserving XML parsing capabilities without extra dependencies.
-    - `EmbeddingVisualizer` and `OntologyVisualizer` safely guard `matplotlib` and optional reduction packages, advising `pip install 'semantica[viz]'`.
-    - `RepoIngestor` guards `GitPython` with a clear error pointing to `semantica[ingest-git]`.
-    - `PublicAPIIngestor` guards `lxml` and `_SAFE_XML_PARSER`.
-    - Updated user-facing installation hints across CLI doctor commands, node embeddings (`NodeEmbedder`), vector stores (`FAISSStore`), and model loaders.
-  - Recompiled CI lockfiles (`requirements-ci.txt`, `.github/requirements/explorer-extra-py311.txt`, `.github/requirements/explorer-extra-py313.txt`, and `.github/requirements/base-deps.txt`).
-
 ## [0.6.8] - 2026-09-05
 
 ### Added

CITATION.cff

@@ -7,7 +7,7 @@ authors:
 repository-code: "https://github.com/semantica-agi/semantica"
 url: "https://getsemantica.ai"
 license: MIT
-version: 0.7.0
+version: 0.6.8
 date-released: 2026-09-05
 keywords:
   - knowledge-graph

README.md

@@ -1480,14 +1480,6 @@ app = create_app(session=GraphSession(graph), agent_memory=memory)
 The Memories workspace is shown only when `agent_memory` is provided. Apply
 updates the supplied runtime object; it does not add disk persistence.
 
-## What's New in v0.7.0
-
-**Slim core dependencies: lightweight base install with granular optional extras** — `pip install semantica` now installs only 22 essential core dependencies, moving heavy packages into dedicated optional extras:
-- **Dramatically lighter and faster installation**: Core installation no longer pulls heavy machine learning or visualization packages by default.
-- **Granular extras**: Install only what your workload requires (`documents`, `embeddings-local`, `models-huggingface`, `nlp-spacy`, `viz`, `media`, `vectorstore-faiss`, `graph-embeddings`, `ingest-git`).
-- **Full backward compatibility**: `pip install "semantica[all]"` preserves the full bundled suite, while `semantica<0.7.0` remains a permanent escape hatch.
-- **Lazy parser construction & graceful fallbacks**: Document parsers can be constructed without extras and only raise actionable error hints upon calling `.parse()`; `XMLParser` automatically falls back to Python's standard library `xml.etree`.
-
 ---
 
 ## What's New in v0.6.8
@@ -1526,42 +1518,32 @@ Semantica is designed for environments where AI outputs must be explainable, aud
 ## Installation
 
 ```bash
-pip install semantica             # lightweight core (22 essential dependencies)
-pip install "semantica[all]"      # full bundled behavior with all extras
+pip install semantica           # core
+pip install semantica[all]      # everything
 ```
 
-> **Note for upgrades from <0.7.0**: In Semantica 0.7.0+, heavy machine learning, NLP, visualization, and document dependencies were moved into optional extras to make core installation significantly lighter and faster. If you want the previous bundled installation, install with `pip install "semantica[all]"` or pin `semantica<0.7.0`.
-
 ```bash
-# Granular Extras
-pip install "semantica[documents]"          # Document parsing (docx, openpyxl, lxml, beautifulsoup4)
-pip install "semantica[embeddings-local]"   # Local embeddings (sentence-transformers, fastembed, onnxruntime)
-pip install "semantica[models-huggingface]" # HuggingFace models (transformers, torch)
-pip install "semantica[nlp-spacy]"          # spaCy NLP pipelines (spacy)
-pip install "semantica[viz]"                # Visualization (matplotlib, seaborn, plotly, pyvis, graphviz)
-pip install "semantica[media]"              # Audio & computer vision (librosa, opencv-python)
-pip install "semantica[graph-embeddings]"   # Knowledge graph embeddings (gensim / Node2Vec)
-pip install "semantica[ingest-git]"         # Git repository ingestor (GitPython)
-pip install "semantica[vectorstore-faiss]"  # FAISS vector store
-pip install "semantica[vectorstore-all]"    # All vector stores (Qdrant, Pinecone, Weaviate, FAISS, PgVector, SQLite)
-pip install "semantica[agno]"               # Agno multi-agent integration
-pip install "semantica[crewai]"             # CrewAI integration
-pip install "semantica[langchain]"          # LangChain / LangGraph integration
-pip install "semantica[llm-all]"            # All LLM provider clients
-pip install "semantica[graph-neo4j]"        # Neo4j graph store (LPG)
-pip install "semantica[graph-falkordb]"     # FalkorDB graph store (LPG)
-pip install "semantica[graph-apache-age]"   # Apache AGE graph store (LPG)
-pip install "semantica[graph-amazon-neptune]" # AWS Neptune graph store (LPG)
-pip install "semantica[tripletstore-oxigraph]" # Embedded in-memory/on-disk RDF store
+pip install semantica[agno]                 # Agno multi-agent integration
+pip install semantica[crewai]               # CrewAI integration
+pip install semantica[langchain]            # LangChain / LangGraph integration
+pip install semantica[llm-litellm]          # OpenAI, Anthropic, Gemini, Mistral, Llama, Groq, Cohere, Bedrock, Ollama, DeepSeek, and more
+pip install semantica[graph-neo4j]          # Neo4j graph store (LPG)
+pip install semantica[graph-falkordb]       # FalkorDB graph store (LPG)
+pip install semantica[graph-apache-age]     # Apache AGE graph store (LPG)
+pip install semantica[graph-amazon-neptune] # AWS Neptune graph store (LPG)
+pip install semantica[tripletstore-oxigraph] # Embedded in-memory/on-disk RDF store
 # RDF triple stores (Blazegraph, Apache Jena, Eclipse RDF4J) need no extra:
 # semantica.triplet_store talks SPARQL over HTTP using the core `requests` dependency
-pip install "semantica[db-snowflake]"       # Snowflake
-pip install "semantica[db-databricks]"      # Databricks (SDK + SQL connector)
-pip install "semantica[ingest-sap]"         # SAP OData
-pip install "semantica[ingest-parquet]"     # Parquet / PyArrow
-pip install "semantica[ingest-arrow]"       # Apache Arrow, Feather, IPC
-pip install "semantica[watch]"              # Directory file watcher
-pip install "semantica[explorer]"           # Knowledge Explorer dashboard
+pip install semantica[vectorstore-qdrant]   # Qdrant vector store
+pip install semantica[vectorstore-pinecone] # Pinecone vector store
+pip install semantica[db-snowflake]         # Snowflake
+pip install semantica[db-databricks]        # Databricks (SDK + SQL connector)
+pip install semantica[ingest-sap]           # SAP OData
+pip install semantica[ingest-parquet]       # Parquet / PyArrow
+pip install semantica[ingest-arrow]        # Apache Arrow, Feather, IPC
+pip install semantica[viz]                  # HTML interactive visualization
+pip install semantica[watch]                # Directory file watcher
+pip install semantica[explorer]             # Knowledge Explorer dashboard
 ```
 
 For production deployments, use Docker or Kubernetes rather than a local `pip install`. Set `SEMANTICA_API_KEY`, configure a persistent LPG graph store (Neo4j / FalkorDB / Apache AGE / AWS Neptune) and/or RDF triple store (Blazegraph / Apache Jena / Eclipse RDF4J), and point the vector store at a hosted backend (Qdrant / Pinecone). See [ARCHITECTURE.md](ARCHITECTURE.md) for the full deployment topology.

integrations/google_adk/session_service.py

@@ -21,7 +21,6 @@ from typing import Any, List, Optional
 try:
     from google.adk.events import Event
     from google.adk.sessions import BaseSessionService, Session
-
     try:
         from google.adk.sessions import ListSessionsResponse
     except ImportError:
@@ -34,7 +33,7 @@ try:
     except ImportError:
         from google.adk.sessions.base_session_service import GetSessionConfig
     ADK_AVAILABLE = True
-except (ImportError, OSError):
+except (ImportError, ModuleNotFoundError):
     ADK_AVAILABLE = False
     BaseSessionService = object
     Session = Any
@@ -163,10 +162,10 @@ class SemanticaSessionService(BaseSessionService):
         return {}
 
     def _find_session_node(
-        self,
-        app_name: str,
-        user_id: str,
-        session_id: str,
+            self,
+            app_name: str,
+            user_id: str,
+            session_id: str,
     ) -> Optional[Any]:
         """Find a session node by its logical ADK session ID."""
         expected_node_id = self._node_id(app_name, user_id, session_id)
@@ -183,18 +182,18 @@ class SemanticaSessionService(BaseSessionService):
             metadata = node.get("metadata")
 
             if (
-                isinstance(metadata, dict)
-                and str(metadata.get("session_id")) == str(session_id)
-                and str(metadata.get("app_name")) == str(app_name)
-                and str(metadata.get("user_id")) == str(user_id)
+                    isinstance(metadata, dict)
+                    and str(metadata.get("session_id")) == str(session_id)
+                    and str(metadata.get("app_name")) == str(app_name)
+                    and str(metadata.get("user_id")) == str(user_id)
             ):
                 return node
 
         return None
 
     def _find_node_by_id(
-        self,
-        node_id: str,
+            self,
+            node_id: str,
     ) -> Optional[Any]:
         """Find a ContextGraph node by graph node ID."""
         for node in self.graph.find_nodes() or []:
@@ -213,13 +212,13 @@ class SemanticaSessionService(BaseSessionService):
         data = SemanticaSessionService._safe_dict(event)
 
         for field in (
-            "id",
-            "invocation_id",
-            "author",
-            "timestamp",
-            "partial",
-            "turn_complete",
-            "branch",
+                "id",
+                "invocation_id",
+                "author",
+                "timestamp",
+                "partial",
+                "turn_complete",
+                "branch",
         ):
             if field not in data and hasattr(event, field):
                 value = getattr(event, field)
@@ -232,10 +231,10 @@ class SemanticaSessionService(BaseSessionService):
         return data
 
     def _event_nodes(
-        self,
-        app_name: str,
-        user_id: str,
-        session_id: str,
+            self,
+            app_name: str,
+            user_id: str,
+            session_id: str,
     ) -> List[Any]:
         """Return all event nodes connected to a session."""
         session_node_id = self._node_id(app_name, user_id, session_id)
@@ -276,8 +275,8 @@ class SemanticaSessionService(BaseSessionService):
         return str(timestamp)
 
     def _event_from_node(
-        self,
-        node: Any,
+            self,
+            node: Any,
     ) -> Any:
         """
         Reconstruct an ADK Event from its stored metadata.
@@ -290,7 +289,7 @@ class SemanticaSessionService(BaseSessionService):
         if not event_id and graph_node_id:
             graph_node_id = str(graph_node_id)
             if graph_node_id.startswith("adk-event:"):
-                event_id = graph_node_id[len("adk-event:") :]
+                event_id = graph_node_id[len("adk-event:"):]
 
         if event_id:
             properties["id"] = event_id
@@ -311,11 +310,11 @@ class SemanticaSessionService(BaseSessionService):
 
     @staticmethod
     def _session_kwargs(
-        app_name: str,
-        user_id: str,
-        session_id: str,
-        state: Optional[dict],
-        events: Optional[List[Any]],
+            app_name: str,
+            user_id: str,
+            session_id: str,
+            state: Optional[dict],
+            events: Optional[List[Any]],
     ) -> dict:
         """Build kwargs for the ADK Session model."""
         return {
@@ -327,8 +326,8 @@ class SemanticaSessionService(BaseSessionService):
         }
 
     def _session_from_node(
-        self,
-        node: Any,
+            self,
+            node: Any,
     ) -> Session:
         """Reconstruct an ADK Session from a ContextGraph node."""
         properties = self._node_properties(node)
@@ -348,14 +347,14 @@ class SemanticaSessionService(BaseSessionService):
                     # splitting on ':' after the prefix always yields
                     # exactly 3 parts regardless of what characters the
                     # original app_name/user_id/session_id contained.
-                    parts = graph_node_id[len("adk-session:") :].split(":")
+                    parts = graph_node_id[len("adk-session:"):].split(":")
                     if len(parts) == 3:
                         decoded = [urllib.parse.unquote(part) for part in parts]
                         app_name = app_name or decoded[0]
                         user_id = user_id or decoded[1]
                         session_id = decoded[2]
                     else:
-                        session_id = graph_node_id[len("adk-session:") :]
+                        session_id = graph_node_id[len("adk-session:"):]
                 else:
                     session_id = graph_node_id
 
@@ -384,12 +383,12 @@ class SemanticaSessionService(BaseSessionService):
     # ------------------------------------------------------------------
 
     async def create_session(
-        self,
-        *,
-        app_name: str,
-        user_id: str,
-        state: Optional[dict[str, Any]] = None,
-        session_id: Optional[str] = None,
+            self,
+            *,
+            app_name: str,
+            user_id: str,
+            state: Optional[dict[str, Any]] = None,
+            session_id: Optional[str] = None,
     ) -> Session:
         """Create and persist an ADK session."""
         return await asyncio.to_thread(
@@ -397,11 +396,11 @@ class SemanticaSessionService(BaseSessionService):
         )
 
     def _create_session_sync(
-        self,
-        app_name: str,
-        user_id: str,
-        state: Optional[dict[str, Any]],
-        session_id: Optional[str],
+            self,
+            app_name: str,
+            user_id: str,
+            state: Optional[dict[str, Any]],
+            session_id: Optional[str],
     ) -> Session:
         with self._lock:
             session_id = session_id or str(uuid.uuid4())
@@ -431,12 +430,12 @@ class SemanticaSessionService(BaseSessionService):
             )
 
     async def get_session(
-        self,
-        *,
-        app_name: str,
-        user_id: str,
-        session_id: str,
-        config: Optional[GetSessionConfig] = None,
+            self,
+            *,
+            app_name: str,
+            user_id: str,
+            session_id: str,
+            config: Optional[GetSessionConfig] = None,
     ) -> Optional[Session]:
         """Retrieve an ADK session from ContextGraph."""
         return await asyncio.to_thread(
@@ -444,11 +443,11 @@ class SemanticaSessionService(BaseSessionService):
         )
 
     def _get_session_sync(
-        self,
-        app_name: str,
-        user_id: str,
-        session_id: str,
-        config: Optional[GetSessionConfig],
+            self,
+            app_name: str,
+            user_id: str,
+            session_id: str,
+            config: Optional[GetSessionConfig],
     ) -> Optional[Session]:
         with self._lock:
             node = self._find_session_node(app_name, user_id, session_id)
@@ -469,7 +468,7 @@ class SemanticaSessionService(BaseSessionService):
         # trims the already-built Session object.
         if config:
             if config.num_recent_events:
-                session.events = session.events[-config.num_recent_events :]
+                session.events = session.events[-config.num_recent_events:]
             if config.after_timestamp:
                 i = len(session.events) - 1
                 while i >= 0:
@@ -477,14 +476,14 @@ class SemanticaSessionService(BaseSessionService):
                         break
                     i -= 1
                 if i >= 0:
-                    session.events = session.events[i + 1 :]
+                    session.events = session.events[i + 1:]
 
         return session
 
     async def append_event(
-        self,
-        session: Session,
-        event: Event,
+            self,
+            session: Session,
+            event: Event,
     ) -> Event:
         """Persist an ADK event and associate it with a session."""
         # ADK's own base implementation is a no-op for partial/streaming
@@ -511,13 +510,8 @@ class SemanticaSessionService(BaseSessionService):
 
             # Verify cross-tenant security
             properties = self._node_properties(session_node)
-            if (
-                properties.get("app_name") != app_name
-                or properties.get("user_id") != user_id
-            ):
-                raise ValueError(
-                    "Cross-tenant session write denied: app_name or user_id mismatch."
-                )
+            if properties.get("app_name") != app_name or properties.get("user_id") != user_id:
+                raise ValueError("Cross-tenant session write denied: app_name or user_id mismatch.")
 
             # Apply ADK in-memory event and state delta semantics. This
             # runs inside asyncio.to_thread's worker thread, which has no
@@ -559,11 +553,11 @@ class SemanticaSessionService(BaseSessionService):
             )
 
     async def delete_session(
-        self,
-        *,
-        app_name: str,
-        user_id: str,
-        session_id: str,
+            self,
+            *,
+            app_name: str,
+            user_id: str,
+            session_id: str,
     ) -> None:
         """Delete a session and all of its graph-backed events."""
         await asyncio.to_thread(
@@ -571,10 +565,10 @@ class SemanticaSessionService(BaseSessionService):
         )
 
     def _delete_session_sync(
-        self,
-        app_name: str,
-        user_id: str,
-        session_id: str,
+            self,
+            app_name: str,
+            user_id: str,
+            session_id: str,
     ) -> None:
         with self._lock:
             session_node = self._find_session_node(app_name, user_id, session_id)
@@ -596,9 +590,9 @@ class SemanticaSessionService(BaseSessionService):
                     continue
 
                 if (
-                    edge.get("source") == session_node_id
-                    and edge.get("type") == "HAS_EVENT"
-                    and edge.get("target")
+                        edge.get("source") == session_node_id
+                        and edge.get("type") == "HAS_EVENT"
+                        and edge.get("target")
                 ):
                     event_node_ids.append(str(edge["target"]))
 
@@ -608,18 +602,18 @@ class SemanticaSessionService(BaseSessionService):
             self.graph.purge_node(session_node_id)
 
     async def list_sessions(
-        self,
-        *,
-        app_name: str,
-        user_id: Optional[str] = None,
+            self,
+            *,
+            app_name: str,
+            user_id: Optional[str] = None,
     ) -> ListSessionsResponse:
         """List sessions for an app, optionally scoped to one user."""
         return await asyncio.to_thread(self._list_sessions_sync, app_name, user_id)
 
     def _list_sessions_sync(
-        self,
-        app_name: str,
-        user_id: Optional[str],
+            self,
+            app_name: str,
+            user_id: Optional[str],
     ) -> ListSessionsResponse:
         with self._lock:
             sessions: List[Session] = []
@@ -649,4 +643,4 @@ class SemanticaSessionService(BaseSessionService):
 __all__ = [
     "ADK_AVAILABLE",
     "SemanticaSessionService",
-]
+]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "semantica"
-version = "0.7.0"
+version = "0.6.8"
 description = "Graph-Native Infrastructure for Context and Accountable AI Systems: context graphs, decision intelligence, full provenance tracking, and explainable reasoning engines — every AI decision traceable, every output auditable."
 readme = "README.md"
 license = { text = "MIT" }
@@ -52,13 +52,30 @@ dependencies = [
   # last 3.9-compatible release line; 3.10+ is left unconstrained.
   "scikit-learn>=1.6.1,<1.7.0; python_version < '3.10'",
   "scikit-learn>=1.7.2; python_version >= '3.10'",
+  "umap-learn>=0.5.12",
+  # thinc (spacy's core dep) dropped Python 3.9 wheels at 8.3.10, and later
+  # spacy patch releases (3.8.8+) require thinc>=8.3.9-only-on-3.10+ ranges,
+  # which forces a source build that fails outright on 3.9 (see Install
+  # Matrix run history). Capping both keeps 3.9 on the last wheel-compatible
+  # pair; 3.10+ is left unconstrained to always get the latest spacy/thinc.
+  "spacy>=3.4.0,<3.8.8; python_version < '3.10'",
+  "spacy>=3.4.0; python_version >= '3.10'",
+  "thinc<8.3.5; python_version < '3.10'",
+  "transformers>=4.20.0",
+  "torch>=1.13.1",
+  "sentence-transformers>=2.2.0",
   "rdflib>=6.2.0",
   "networkx>=2.8.0",
+  "matplotlib>=3.9.4",
+  "seaborn>=0.13.2",
+  "plotly>=6.8.0",
+  "ipywidgets>=8.0.0",
   # requests dropped Python 3.9 support at 2.33.0 (requires_python >=3.10),
   # so an unqualified >=2.34.2 floor is unsatisfiable on 3.9. Cap 3.9 to the
   # last 3.9-compatible release; 3.10+ is left unconstrained.
   "requests>=2.32.5,<2.33.0; python_version < '3.10'",
   "requests>=2.34.2; python_version >= '3.10'",
+  "GitPython>=3.1.58",
   # chardet dropped Python 3.9 support at 6.0.0 (requires_python >=3.10), so
   # an unqualified >=7.4.3 floor is unsatisfiable on 3.9. Cap 3.9 to the last
   # 3.9-compatible release; 3.10+ is left unconstrained.
@@ -70,11 +87,26 @@ dependencies = [
   # 3.9-compatible release; 3.10+ is left unconstrained.
   "grpcio>=1.80.0,<1.81.0; python_version < '3.10'",
   "grpcio>=1.81.1; python_version >= '3.10'",
+  "beautifulsoup4>=4.15.0",
+  "lxml>=6.1.1",
+  "python-docx>=1.2.0",
+  "openpyxl>=3.1.5",
   # pillow dropped Python 3.9 support at 12.0.0 (requires_python >=3.10), so
   # an unqualified >=12.2.0 floor is unsatisfiable on 3.9. Cap 3.9 to the last
   # 3.9-compatible release; 3.10+ is left unconstrained.
   "pillow>=11.3.0,<12.0.0; python_version < '3.10'",
   "pillow>=12.2.0; python_version >= '3.10'",
+  "librosa>=0.9.0",
+  "opencv-python>=4.13.0.92",
+  "faiss-cpu>=1.7.0",
+  "fastembed>=0.2.0",
+  # onnxruntime stopped shipping cp39 wheels at 1.20.0 (its PyPI metadata
+  # still claims requires_python >=3.9, but no matching wheel exists), so an
+  # unqualified >=1.20.1 floor is unsatisfiable on 3.9. Cap 3.9 to the last
+  # release with a cp39 wheel; 3.10+ is left unconstrained.
+  "onnxruntime>=1.19.2,<1.20.0; python_version < '3.10'",
+  "onnxruntime>=1.20.1; python_version >= '3.10'",
+  "tokenizers>=0.15.0",
   "pydantic>=2.13.4",
   # click dropped Python 3.9 support at 8.2.0 (requires_python >=3.10), so an
   # unqualified >=8.4.2 floor is unsatisfiable on 3.9. Cap 3.9 to the last
@@ -88,6 +120,7 @@ dependencies = [
   "python-dotenv>=1.2.1",
   "loguru>=0.7.3",
   "structlog>=22.1.0",
+  "gensim>=4.4.0",
   "httpx<0.29.0",
   "pyarrow>=14.0.0"
 ]
@@ -119,12 +152,6 @@ llm-all = [
 ]
 
 # ---- Document Parsing ----
-documents = [
-  "python-docx>=1.2.0",
-  "openpyxl>=3.1.5",
-  "lxml>=6.1.1",
-  "beautifulsoup4>=4.15.0"
-]
 parse-docling = ["docling>=2.107.0"]
 
 # ---- SHACL Validation ----
@@ -138,7 +165,6 @@ db-salesforce = ["simple-salesforce>=1.12.0"]
 ingest-parquet = ["pyarrow>=24.0.0"]
 ingest-arrow = ["pyarrow>=24.0.0"]
 ingest-sap = ["requests>=2.28.0"]
-ingest-git = ["GitPython>=3.1.58"]
 
 db-all = [
   "semantica[db-snowflake,db-databricks,db-salesforce,db-arrow]"
@@ -149,35 +175,22 @@ models-huggingface = [
   "transformers>=4.20.0",
   "torch>=1.13.1"
 ]
-embeddings-local = [
-  "sentence-transformers>=2.2.0",
-  "fastembed>=0.2.0",
-  "onnxruntime>=1.19.2,<1.20.0; python_version < '3.10'",
-  "onnxruntime>=1.20.1; python_version >= '3.10'",
-  "tokenizers>=0.15.0"
-]
-nlp-spacy = [
-  "spacy>=3.4.0,<3.8.8; python_version < '3.10'",
-  "spacy>=3.4.0; python_version >= '3.10'"
-]
 
 # ---- Graph Backends ----
 graph-neo4j = ["neo4j>=5.0.0"]
 graph-falkordb = ["falkordb>=1.0.0", "redis>=4.3.0"]
 graph-amazon-neptune = ["boto3>=1.24.0", "neo4j>=5.0.0"]
 graph-apache-age = ["psycopg2-binary>=2.9.0"]
-graph-embeddings = ["gensim>=4.4.0"]
 
 graph-all = [
-  "semantica[graph-neo4j,graph-falkordb,graph-amazon-neptune,graph-apache-age,graph-embeddings]"
+  "semantica[graph-neo4j,graph-falkordb,graph-amazon-neptune,graph-apache-age]"
 ]
 
 # ---- Triplet Store Backends ----
 tripletstore-oxigraph = ["pyoxigraph>=0.5.0"]
 
 # ---- Vector Store Backends ----
-vectorstore-faiss = ["faiss-cpu>=1.7.0"]
-vectorstore-qdrant = ["qdrant-client>=1.0.0"]
+vectorstore-qdrant = ["qdrant-client>=1.10.0"]
 vectorstore-weaviate = ["weaviate-client>=4.0.0"]
 vectorstore-pinecone = ["pinecone>=3.0.0"]
 vectorstore-milvus = ["pymilvus>=2.0.0"]
@@ -185,7 +198,7 @@ vectorstore-pgvector = ["psycopg[binary,pool]>=3.0.0", "pgvector>=0.2.0"]
 vectorstore-sqlite = ["sqlite-vec>=0.1.1"]
 
 vectorstore-all = [
-  "semantica[vectorstore-qdrant,vectorstore-weaviate,vectorstore-pinecone,vectorstore-milvus,vectorstore-pgvector,vectorstore-sqlite,vectorstore-faiss]"
+  "semantica[vectorstore-qdrant,vectorstore-weaviate,vectorstore-pinecone,vectorstore-milvus,vectorstore-pgvector,vectorstore-sqlite]"
 ]
 
 # ---- Infra / Queues / Workers ----
@@ -217,18 +230,7 @@ monitoring = [
 viz = [
   "pyvis>=0.3.0",
   "graphviz>=0.21",
-  "d3blocks>=1.0.0",
-  "matplotlib>=3.9.4",
-  "seaborn>=0.13.2",
-  "plotly>=6.8.0",
-  "ipywidgets>=8.0.0",
-  "umap-learn>=0.5.12"
-]
-
-# ---- Media ----
-media = [
-  "librosa>=0.9.0",
-  "opencv-python>=4.13.0.92"
+  "d3blocks>=1.0.0"
 ]
 
 # ---- GPU ----
@@ -292,7 +294,8 @@ explorer-lite = [
 # (CVE-2026-45829) with no fixed release — including it here would fail the CI
 # dependency-audit/security gates.  Install it explicitly via ``semantica[crewai]``.
 all = [
-  "semantica[dev,viz,media,infra,cloud,monitoring,watch,llm-all,models-huggingface,embeddings-local,nlp-spacy,documents,ingest-git,graph-embeddings,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,explorer,agno,langchain,google-adk]"
+  "semantica[dev,viz,infra,cloud,monitoring,watch,llm-all,models-huggingface,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,explorer]",
+  "semantica[dev,viz,infra,cloud,monitoring,watch,llm-all,models-huggingface,split-all,graph-all,tripletstore-oxigraph,vectorstore-all,parse-docling,ingest-parquet,ingest-arrow,shacl,agno,langchain,google-adk]"
 ]
 
 # ---------------- ENTRYPOINTS ----------------

requirements-ci.txt

@@ -181,7 +181,6 @@ anyio==4.14.2 \
     #   jupyter-server
     #   langsmith
     #   openai
-    #   pinecone
     #   starlette
     #   watchfiles
 argon2-cffi==25.1.0 \

semantica/__init__.py

@@ -10,7 +10,7 @@ Main exports:
     - Config: Configuration management
 """
 
-__version__ = "0.7.0"
+__version__ = "0.6.8"
 __author__ = "Semantica Contributors"
 __license__ = "MIT"
 

semantica/cli.py

@@ -880,18 +880,10 @@ def doctor(cli_ctx: CLIContext, local_json: bool, deep_embeddings: bool) -> None
         def _embedding_backend(method: str) -> str:
             if method == "sentence_transformers":
                 import sentence_transformers  # noqa: F401
-                try:
-                    ver = importlib.metadata.version("sentence-transformers")
-                except Exception:
-                    ver = getattr(sentence_transformers, "__version__", "installed")
-                note = f"importable ({ver})"
+                note = f"importable ({importlib.metadata.version('sentence-transformers')})"
             else:
                 import fastembed  # noqa: F401
-                try:
-                    ver = importlib.metadata.version("fastembed")
-                except Exception:
-                    ver = getattr(fastembed, "__version__", "installed")
-                note = f"importable ({ver})"
+                note = f"importable ({importlib.metadata.version('fastembed')})"
             if not deep:
                 return note
             try:
@@ -912,12 +904,12 @@ def doctor(cli_ctx: CLIContext, local_json: bool, deep_embeddings: bool) -> None
         checks.append(_check(
             "Embeddings (sentence-transformers)",
             lambda: _embedding_backend("sentence_transformers"),
-            hint="pip install 'semantica[embeddings-local]'",
+            hint="pip install sentence-transformers",
         ))
         checks.append(_check(
             "Embeddings (fastembed)",
             lambda: _embedding_backend("fastembed"),
-            hint="pip install 'semantica[embeddings-local]'",
+            hint="pip install fastembed",
         ))
 
         # LLM provider keys

semantica/embeddings/provider_stores.py

@@ -212,7 +212,7 @@ class FastEmbedStore(ProviderStore):
             self.logger.info(f"Loaded FastEmbed model: {self.model_name}")
         except (ImportError, OSError):
             self.logger.warning(
-                "fastembed not available. Install with: pip install 'semantica[embeddings-local]'"
+                "fastembed not available. Install with: pip install fastembed"
             )
         except Exception as e:
             self.logger.warning(f"Failed to load FastEmbed model: {e}")

semantica/embeddings/text_embedder.py

@@ -35,7 +35,6 @@ try:
 
     SENTENCE_TRANSFORMERS_AVAILABLE = True
 except (ImportError, OSError):
-    SentenceTransformer = None
     SENTENCE_TRANSFORMERS_AVAILABLE = False
 
 try:
@@ -43,7 +42,6 @@ try:
 
     FASTEMBED_AVAILABLE = True
 except (ImportError, OSError):
-    TextEmbedding = None
     FASTEMBED_AVAILABLE = False
 
 
@@ -158,7 +156,7 @@ class TextEmbedder:
             else:
                 self.logger.warning(
                     "fastembed not available. "
-                    "Install with: pip install 'semantica[embeddings-local]'. "
+                    "Install with: pip install fastembed. "
                     "Using fallback embedding method."
                 )
         else:
@@ -180,7 +178,7 @@ class TextEmbedder:
             else:
                 self.logger.warning(
                     "sentence-transformers not available. "
-                    "Install with: pip install 'semantica[embeddings-local]'. "
+                    "Install with: pip install sentence-transformers. "
                     "Using fallback embedding method."
                 )
         

semantica/export/vector_exporter.py

@@ -421,7 +421,7 @@ class VectorExporter:
             import numpy as np
         except (ImportError, OSError):
             raise ImportError(
-                "FAISS not installed. Install with: pip install 'semantica[vectorstore-faiss]' (or 'semantica[gpu]' for CUDA)"
+                "FAISS not installed. Install with: pip install faiss-cpu or faiss-gpu"
             )
 
         # Extract vectors and IDs

semantica/ingest/__init__.py

@@ -133,11 +133,7 @@ import importlib
 from typing import TYPE_CHECKING, Any, Dict, Tuple
 
 if TYPE_CHECKING:
-    from .salesforce_ingestor import (
-        SalesforceConnector,
-        SalesforceData,
-        SalesforceIngestor,
-    )
+    from .salesforce_ingestor import SalesforceConnector, SalesforceData, SalesforceIngestor
 
 from .config import IngestConfig, ingest_config
 from .file_ingestor import (
@@ -252,42 +248,32 @@ _LAZY_EXPORTS: Dict[str, Tuple[str, str]] = {
 _OPTIONAL_DEPENDENCY_MESSAGES = {
     ".repo_ingestor": (
         "Repository ingestion requires optional dependency 'GitPython'. "
-        "Install it before importing RepoIngestor or using ingest_repository(). "
-        "Install it with: pip install 'semantica[ingest-git]'"
+        "Install it before importing RepoIngestor or using ingest_repository()."
     ),
     ".web_ingestor": (
         "Web ingestion requires optional dependency 'beautifulsoup4'. "
-        "Install it before importing WebIngestor or using ingest_web(). "
-        "Install it with: pip install 'semantica[documents]'"
+        "Install it before importing WebIngestor or using ingest_web()."
     ),
     ".feed_ingestor": (
         "Feed ingestion requires optional dependency 'beautifulsoup4'. "
-        "Install it before importing FeedIngestor or using ingest_feed(). "
-        "Install it with: pip install 'semantica[documents]'"
+        "Install it before importing FeedIngestor or using ingest_feed()."
     ),
     ".email_ingestor": (
         "Email ingestion requires optional dependency 'beautifulsoup4'. "
-        "Install it before importing EmailIngestor or using ingest_email(). "
-        "Install it with: pip install 'semantica[documents]'"
-    ),
-    ".xml_ingestor": (
-        "XML ingestion requires optional dependency 'lxml'. "
-        "Install it before importing XMLIngestor or using ingest_xml(). "
-        "Install it with: pip install 'semantica[documents]'"
+        "Install it before importing EmailIngestor or using ingest_email()."
     ),
     ".parquet_ingestor": (
         "Parquet ingestion requires optional dependency 'pyarrow'. "
-        "Install it before importing ParquetIngestor or using ingest_parquet(). "
-        "Install it with: pip install 'semantica[ingest-parquet]'"
+        "Install it before importing ParquetIngestor or using ingest_parquet()."
     ),
     ".arrow_ingestor": (
         "Arrow ingestion requires optional dependency 'pyarrow'. "
-        "Install it before importing ArrowIngestor or using ingest_arrow(). "
-        "Install it with: pip install 'semantica[ingest-arrow]'"
+        "Install it before importing ArrowIngestor or using ingest_arrow()."
     ),
     ".salesforce_ingestor": (
         "Salesforce ingestion requires optional dependency 'simple-salesforce'. "
-        "Install it with: pip install 'semantica[db-salesforce]'"
+        "Install it with: pip install \"semantica[db-salesforce]\" "
+        "or: pip install simple-salesforce>=1.12.0"
     ),
 }
 
@@ -300,55 +286,13 @@ def __getattr__(name: str) -> Any:
     module_name, attr_name = _LAZY_EXPORTS[name]
     try:
         module = importlib.import_module(module_name, __name__)
-    except (ImportError, OSError) as exc:
+    except ModuleNotFoundError as exc:
         message = _OPTIONAL_DEPENDENCY_MESSAGES.get(module_name)
         missing_name = getattr(exc, "name", None)
-        if message and (
-            missing_name is None
-            or any(
-                pkg in missing_name
-                for pkg in ("git", "bs4", "pyarrow", "simple_salesforce", "lxml")
-            )
-        ):
+        if message and missing_name in {"git", "bs4", "pyarrow", "simple_salesforce"}:
             raise ImportError(message) from exc
         raise
 
-    # Guard against backends whose modules imported cleanly with dependencies
-    # set to None; ensure probe imports (e.g. try: from semantica.ingest import ...)
-    # fail at import time rather than postponing failure to construction time.
-    if module_name == ".repo_ingestor" and name in {"RepoIngestor"}:
-        if getattr(module, "git", None) is None:
-            message = _OPTIONAL_DEPENDENCY_MESSAGES.get(module_name)
-            if message:
-                raise ImportError(message)
-
-    if module_name == ".xml_ingestor" and name in {"XMLIngestor"}:
-        if getattr(module, "etree", None) is None:
-            message = _OPTIONAL_DEPENDENCY_MESSAGES.get(module_name)
-            if message:
-                raise ImportError(message)
-
-    if module_name == ".parquet_ingestor" and name in {"ParquetIngestor"}:
-        if not getattr(module, "PARQUET_AVAILABLE", True):
-            message = _OPTIONAL_DEPENDENCY_MESSAGES.get(module_name)
-            if message:
-                raise ImportError(message)
-
-    if module_name == ".arrow_ingestor" and name in {"ArrowIngestor"}:
-        if not getattr(module, "ARROW_AVAILABLE", True):
-            message = _OPTIONAL_DEPENDENCY_MESSAGES.get(module_name)
-            if message:
-                raise ImportError(message)
-
-    if module_name == ".salesforce_ingestor" and name in {
-        "SalesforceIngestor",
-        "SalesforceConnector",
-    }:
-        if not getattr(module, "SALESFORCE_AVAILABLE", True):
-            message = _OPTIONAL_DEPENDENCY_MESSAGES.get(module_name)
-            if message:
-                raise ImportError(message)
-
     value = getattr(module, attr_name)
     globals()[name] = value
     return value

semantica/ingest/methods.py

@@ -193,7 +193,6 @@ def _is_scp_like_repo_source(source: str) -> bool:
     """Return True for scp-like SSH remotes (``user@host:path``)."""
     return bool(_SCP_LIKE_REPO_URL_RE.match(source.strip()))
 
-
 if TYPE_CHECKING:
     from .api_ingestor import APIData
     from .arrow_ingestor import ArrowData
@@ -253,12 +252,7 @@ def ingest_file(
     if custom_method and custom_method != ingest_file:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -324,18 +318,21 @@ def ingest_parquet(
     if custom_method and custom_method != ingest_parquet:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
 
     try:
-        from .parquet_ingestor import ParquetIngestor
+        try:
+            from .parquet_ingestor import ParquetIngestor
+        except ModuleNotFoundError as exc:
+            if _is_missing_dependency(exc, "pyarrow"):
+                raise _missing_optional_dependency(
+                    "Parquet ingestion",
+                    "pyarrow",
+                ) from exc
+            raise
 
         config = ingest_config.get_method_config("parquet")
         config.update(kwargs)
@@ -400,18 +397,21 @@ def ingest_arrow(
     if custom_method and custom_method != ingest_arrow:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
 
     try:
-        from .arrow_ingestor import ArrowIngestor
+        try:
+            from .arrow_ingestor import ArrowIngestor
+        except ModuleNotFoundError as exc:
+            if _is_missing_dependency(exc, "pyarrow"):
+                raise _missing_optional_dependency(
+                    "Arrow ingestion",
+                    "pyarrow",
+                ) from exc
+            raise
 
         config = ingest_config.get_method_config("arrow")
         config.update(kwargs)
@@ -481,12 +481,7 @@ def ingest_xml(
     if custom_method and custom_method != ingest_xml:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -496,10 +491,7 @@ def ingest_xml(
 
         config = ingest_config.get_method_config("xml")
         config.update(kwargs)
-        try:
-            ingestor = XMLIngestor(**config)
-        except ImportError as exc:
-            raise _missing_optional_dependency("XML ingestion", "lxml") from exc
+        ingestor = XMLIngestor(**config)
 
         def _run_single(
             path: Union[str, Path],
@@ -519,8 +511,6 @@ def ingest_xml(
 
         return _run_single(source_path)
 
-    except ConfigurationError:
-        raise
     except Exception as e:
         logger.error(f"Failed to ingest XML: {e}")
         raise
@@ -555,12 +545,7 @@ def ingest_web(
     if custom_method and custom_method != ingest_web:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -650,12 +635,7 @@ def ingest_public_api(
     if custom_method and custom_method != ingest_public_api:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -742,12 +722,7 @@ def ingest_feed(
     if custom_method and custom_method != ingest_feed:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -816,12 +791,7 @@ def ingest_stream(
     if custom_method and custom_method != ingest_stream:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -898,29 +868,26 @@ def ingest_repository(
     if custom_method and custom_method != ingest_repository:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
 
     try:
-        from .repo_ingestor import RepoIngestor
+        try:
+            from .repo_ingestor import RepoIngestor
+        except ModuleNotFoundError as exc:
+            if _is_missing_dependency(exc, "git"):
+                raise _missing_optional_dependency(
+                    "Repository ingestion", "GitPython"
+                ) from exc
+            raise
 
         # Get config
         config = ingest_config.get_method_config("repo")
         config.update(kwargs)
 
-        try:
-            ingestor = RepoIngestor(**config)
-        except ImportError as exc:
-            raise _missing_optional_dependency(
-                "Repository ingestion", "GitPython"
-            ) from exc
+        ingestor = RepoIngestor(**config)
 
         if method == "clone" or (
             isinstance(source, str)
@@ -973,12 +940,7 @@ def ingest_email(
     if custom_method and custom_method != ingest_email:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -1057,12 +1019,7 @@ def ingest_ontology(
     if custom_method and custom_method != ingest_ontology:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -1128,12 +1085,7 @@ def ingest_database(
         if custom_method and custom_method != ingest_database:
             fallback = kwargs.pop("fallback_on_custom_error", False)
             result = call_custom_method(
-                logger,
-                method,
-                custom_method,
-                source,
-                fallback_on_custom_error=fallback,
-                **kwargs,
+                logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
             )
             if result is not CUSTOM_METHOD_FELL_BACK:
                 return result
@@ -1281,122 +1233,105 @@ def ingest_salesforce(
     if custom_method and custom_method != ingest_salesforce:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source,
+            fallback_on_custom_error=fallback, **kwargs,
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
 
     try:
         from .salesforce_ingestor import SalesforceIngestor
-
-        # Unpack credential dict (if given); everything else stays in kwargs.
-        creds: Dict[str, Any] = {}
-        if source is not None:
-            if not isinstance(source, dict):
-                raise ProcessingError(
-                    "ingest_salesforce() source must be a credential dict or None. "
-                    "Pass sobject_name / soql as keyword arguments."
-                )
-            creds = dict(source)
-
-        # Merge any ingest_config method config under "salesforce".
-        # get_method_config() now returns a copy, so this dict is safe to mutate.
-        # We build the final connector config in order of increasing priority:
-        #   1. base method config (lowest — global defaults set by operator)
-        #   2. per-call credential dict supplied via `source`
-        #   3. per-call connector params supplied as kwargs
-        # Credentials are extracted from kwargs and removed so they don't also
-        # flow into the ingest method call (which doesn't understand them).
-        _CONNECTOR_PARAMS = frozenset(
-            {
-                "username",
-                "password",
-                "security_token",
-                "domain",
-                "instance_url",
-                "session_id",
-                "api_version",
-            }
-        )
-        connector_kwargs = {k: v for k, v in kwargs.items() if k in _CONNECTOR_PARAMS}
-        for k in _CONNECTOR_PARAMS:
-            kwargs.pop(k, None)
-
-        # Build a fresh per-call config dict — never mutate the global store.
-        config: Dict[str, Any] = {
-            **ingest_config.get_method_config("salesforce"),  # base (already a copy)
-            **creds,  # source dict credentials
-            **connector_kwargs,  # kwarg credentials
-        }
-
-        try:
-            ingestor = SalesforceIngestor(**config)
-        except ImportError as exc:
+    except ModuleNotFoundError as exc:
+        if _is_missing_dependency(exc, "simple_salesforce"):
             raise _missing_optional_dependency(
                 "Salesforce ingestion", "simple-salesforce"
             ) from exc
+        raise
 
-        if method == "sobject":
-            sobject_name = kwargs.pop("sobject_name", None)
-            if not sobject_name:
-                raise ProcessingError(
-                    "ingest_salesforce() with method='sobject' requires "
-                    "sobject_name keyword argument."
-                )
-            return ingestor.ingest_sobject(sobject_name, **kwargs)
-
-        elif method == "query":
-            soql = kwargs.pop("soql", None)
-            if not soql:
-                raise ProcessingError(
-                    "ingest_salesforce() with method='query' requires "
-                    "soql keyword argument."
-                )
-            return ingestor.ingest_query(soql, **kwargs)
-
-        elif method == "list_sobjects":
-            return ingestor.list_sobjects()
-
-        elif method == "schema":
-            sobject_name = kwargs.pop("sobject_name", None)
-            if not sobject_name:
-                raise ProcessingError(
-                    "ingest_salesforce() with method='schema' requires "
-                    "sobject_name keyword argument."
-                )
-            return ingestor.get_sobject_schema(sobject_name)
-
-        elif method == "documents":
-            sobject_name = kwargs.pop("sobject_name", None)
-            if not sobject_name:
-                raise ProcessingError(
-                    "ingest_salesforce() with method='documents' requires "
-                    "sobject_name keyword argument."
-                )
-            id_field = kwargs.pop("id_field", "Id")
-            text_fields = kwargs.pop("text_fields", None)
-            data = ingestor.ingest_sobject(sobject_name, **kwargs)
-            return ingestor.export_as_documents(
-                data, id_field=id_field, text_fields=text_fields
-            )
-
-        else:
+    # Unpack credential dict (if given); everything else stays in kwargs.
+    creds: Dict[str, Any] = {}
+    if source is not None:
+        if not isinstance(source, dict):
             raise ProcessingError(
-                f"Unknown ingest_salesforce method: {method!r}. "
-                "Valid methods: 'sobject', 'query', 'list_sobjects', 'schema', "
-                "'documents'."
+                "ingest_salesforce() source must be a credential dict or None. "
+                "Pass sobject_name / soql as keyword arguments."
             )
+        creds = dict(source)
 
-    except ConfigurationError:
-        raise
-    except Exception as e:
-        logger.error(f"Failed to ingest salesforce: {e}")
-        raise
+    # Merge any ingest_config method config under "salesforce".
+    # get_method_config() now returns a copy, so this dict is safe to mutate.
+    # We build the final connector config in order of increasing priority:
+    #   1. base method config (lowest — global defaults set by operator)
+    #   2. per-call credential dict supplied via `source`
+    #   3. per-call connector params supplied as kwargs
+    # Credentials are extracted from kwargs and removed so they don't also
+    # flow into the ingest method call (which doesn't understand them).
+    _CONNECTOR_PARAMS = frozenset({
+        "username", "password", "security_token", "domain",
+        "instance_url", "session_id", "api_version",
+    })
+    connector_kwargs = {k: v for k, v in kwargs.items() if k in _CONNECTOR_PARAMS}
+    for k in _CONNECTOR_PARAMS:
+        kwargs.pop(k, None)
+
+    # Build a fresh per-call config dict — never mutate the global store.
+    config: Dict[str, Any] = {
+        **ingest_config.get_method_config("salesforce"),  # base (already a copy)
+        **creds,                                           # source dict credentials
+        **connector_kwargs,                                # kwarg credentials
+    }
+
+    ingestor = SalesforceIngestor(**config)
+
+    if method == "sobject":
+        sobject_name = kwargs.pop("sobject_name", None)
+        if not sobject_name:
+            raise ProcessingError(
+                "ingest_salesforce() with method='sobject' requires "
+                "sobject_name keyword argument."
+            )
+        return ingestor.ingest_sobject(sobject_name, **kwargs)
+
+    elif method == "query":
+        soql = kwargs.pop("soql", None)
+        if not soql:
+            raise ProcessingError(
+                "ingest_salesforce() with method='query' requires "
+                "soql keyword argument."
+            )
+        return ingestor.ingest_query(soql, **kwargs)
+
+    elif method == "list_sobjects":
+        return ingestor.list_sobjects()
+
+    elif method == "schema":
+        sobject_name = kwargs.pop("sobject_name", None)
+        if not sobject_name:
+            raise ProcessingError(
+                "ingest_salesforce() with method='schema' requires "
+                "sobject_name keyword argument."
+            )
+        return ingestor.get_sobject_schema(sobject_name)
+
+    elif method == "documents":
+        sobject_name = kwargs.pop("sobject_name", None)
+        if not sobject_name:
+            raise ProcessingError(
+                "ingest_salesforce() with method='documents' requires "
+                "sobject_name keyword argument."
+            )
+        id_field = kwargs.pop("id_field", "Id")
+        text_fields = kwargs.pop("text_fields", None)
+        data = ingestor.ingest_sobject(sobject_name, **kwargs)
+        return ingestor.export_as_documents(data, id_field=id_field,
+                                            text_fields=text_fields)
+
+    else:
+        raise ProcessingError(
+            f"Unknown ingest_salesforce method: {method!r}. "
+            "Valid methods: 'sobject', 'query', 'list_sobjects', 'schema', "
+            "'documents'."
+        )
 
 
 def ingest_mcp(
@@ -1464,12 +1399,7 @@ def ingest_mcp(
     if custom_method and custom_method != ingest_mcp:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            source,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, source, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -1708,9 +1638,8 @@ def ingest(
     elif source_type == "mcp":
         return {"data": ingest_mcp(sources, method=method or "resources", **kwargs)}
     elif source_type == "salesforce":
-        return {
-            "data": ingest_salesforce(sources, method=method or "sobject", **kwargs)
-        }
+        return {"data": ingest_salesforce(sources,
+                                          method=method or "sobject", **kwargs)}
     else:
         raise ProcessingError(f"Unknown source type: {source_type}")
 

semantica/ingest/public_api_ingestor.py

@@ -28,29 +28,12 @@ from typing import Any, Dict, List, Optional, Tuple
 from urllib.parse import parse_qs, urlparse
 
 import requests
-
-try:
-    from lxml import etree as lxml_etree
-
-    _SAFE_XML_PARSER = lxml_etree.XMLParser(
-        resolve_entities=False,
-        no_network=True,
-        recover=False,
-        huge_tree=False,
-        load_dtd=False,
-        remove_comments=True,
-        remove_pis=True,
-    )
-    _LXML_SYNTAX_ERRORS: Tuple[type, ...] = (lxml_etree.XMLSyntaxError,)
-except (ImportError, OSError):
-    lxml_etree = None
-    _SAFE_XML_PARSER = None
-    _LXML_SYNTAX_ERRORS = ()
+from lxml import etree as lxml_etree
 
 try:
     from defusedxml import ElementTree as safe_xml_etree
     from defusedxml.common import DefusedXmlException
-except (ImportError, OSError):  # pragma: no cover - fallback for minimal installs
+except ModuleNotFoundError:  # pragma: no cover - fallback for minimal installs
     safe_xml_etree = None
 
     class DefusedXmlException(Exception):
@@ -88,6 +71,14 @@ AUTH_PARAM_NAMES = {
     "subscription-key",
 }
 
+_SAFE_XML_PARSER = lxml_etree.XMLParser(
+    resolve_entities=False,
+    no_network=True,
+    recover=False,
+    huge_tree=False,
+    load_dtd=False,
+)
+
 
 @dataclass
 class PublicAPIExample:
@@ -452,9 +443,7 @@ class PublicAPIIngestor(RESTIngestor):
             APIData: Normalized public API response and metadata
         """
         self._validate_endpoint(endpoint)
-        self._validate_no_auth_request(
-            headers=headers, params=params, options=options, endpoint=endpoint
-        )
+        self._validate_no_auth_request(headers=headers, params=params, options=options, endpoint=endpoint)
 
         tracking_id = self.progress_tracker.start_tracking(
             file=endpoint,
@@ -615,9 +604,7 @@ class PublicAPIIngestor(RESTIngestor):
         for endpoint in endpoints:
             try:
                 results.append(
-                    self.ingest_public_api(
-                        endpoint, method=method, **copy.deepcopy(options)
-                    )
+                    self.ingest_public_api(endpoint, method=method, **copy.deepcopy(options))
                 )
             except Exception as exc:
                 self.logger.warning(f"Failed to fetch public API {endpoint}: {exc}")
@@ -743,7 +730,7 @@ class PublicAPIIngestor(RESTIngestor):
             raise ProcessingError(
                 f"Failed to parse {detected_format.upper()} public API response"
             ) from exc
-        except (DefusedXmlException, *_LXML_SYNTAX_ERRORS) as exc:
+        except (DefusedXmlException, lxml_etree.XMLSyntaxError) as exc:
             raise ProcessingError("Failed to parse XML public API response") from exc
 
     def _detect_response_format(
@@ -783,40 +770,15 @@ class PublicAPIIngestor(RESTIngestor):
     def _parse_xml(self, xml_text: str) -> Dict[str, Any]:
         if safe_xml_etree is not None:
             root = safe_xml_etree.fromstring(xml_text)
-        elif lxml_etree is not None and _SAFE_XML_PARSER is not None:
+        else:
             root = lxml_etree.fromstring(
                 xml_text.encode("utf-8"),
                 parser=_SAFE_XML_PARSER,
             )
-            for elem in root.iter():
-                if (
-                    elem.tag is lxml_etree.Comment
-                    or elem.tag is lxml_etree.PI
-                    or getattr(elem.tag, "__name__", "")
-                    in ("Comment", "ProcessingInstruction", "PI")
-                ):
-                    continue
-                if callable(elem.tag) or not isinstance(elem.tag, str):
-                    raise ProcessingError("Failed to parse XML public API response")
-        else:
-            raise ProcessingError(
-                "XML parsing requires 'defusedxml' or 'lxml'. "
-                "Install it with: pip install 'semantica[documents]'"
-            )
         return self._element_to_dict(root)
 
     def _element_to_dict(self, element: Any) -> Dict[str, Any]:
-        children = [
-            self._element_to_dict(child)
-            for child in list(element)
-            if not (
-                callable(child.tag)
-                or (
-                    lxml_etree is not None
-                    and (child.tag is lxml_etree.Comment or child.tag is lxml_etree.PI)
-                )
-            )
-        ]
+        children = [self._element_to_dict(child) for child in list(element)]
         return {
             "tag": self._strip_namespace(element.tag),
             "attributes": {
@@ -827,9 +789,7 @@ class PublicAPIIngestor(RESTIngestor):
             "children": children,
         }
 
-    def _strip_namespace(self, value: Any) -> str:
-        if not isinstance(value, str):
-            return str(value)
+    def _strip_namespace(self, value: str) -> str:
         if value.startswith("{") and "}" in value:
             return value.split("}", 1)[1]
         return value

semantica/ingest/repo_ingestor.py

@@ -29,8 +29,6 @@ Author: Semantica Contributors
 License: MIT
 """
 
-from __future__ import annotations
-
 import ipaddress
 import os
 import re
@@ -46,10 +44,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Set, Tuple, Union
 from urllib.parse import urlparse
 
-try:
-    import git
-except (ImportError, OSError):
-    git = None
+import git
 
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
@@ -62,7 +57,9 @@ ALLOWED_CLONE_OPTIONS: Set[str] = {"depth", "branch", "single_branch", "no_tags"
 ALLOWED_REPO_URL_SCHEMES = frozenset({"https", "http", "git", "ssh"})
 # SCP-like SSH remotes: user@host:path/to/repo.git (no scheme)
 _SCP_LIKE_REPO_URL_RE = re.compile(r"^[^@\s]+@[^:\s]+:.+$")
-_ENV_VAR_TOKEN_RE = re.compile(r"\$(\{[A-Za-z_][A-Za-z0-9_]*\}|[A-Za-z_][A-Za-z0-9_]*)")
+_ENV_VAR_TOKEN_RE = re.compile(
+    r"\$(\{[A-Za-z_][A-Za-z0-9_]*\}|[A-Za-z_][A-Za-z0-9_]*)"
+)
 # Short-lived DNS cache for host validation. This reduces repeated lookups but
 # does not eliminate DNS-rebinding / TOCTOU races between validate and clone —
 # network egress controls remain recommended.
@@ -528,11 +525,6 @@ class RepoIngestor:
             **kwargs: Additional configuration parameters (merged into config)
         """
         self.logger = get_logger("repo_ingestor")
-        if git is None:
-            raise ImportError(
-                "GitPython is required for repository ingestion. "
-                "Install it with: pip install 'semantica[ingest-git]'"
-            )
         self.config = config or {}
         self.config.update(kwargs)
 
@@ -598,7 +590,10 @@ class RepoIngestor:
         networks). Those addresses are not SSRF-sensitive.
         """
         return bool(
-            ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_unspecified
+            ip.is_private
+            or ip.is_loopback
+            or ip.is_link_local
+            or ip.is_unspecified
         )
 
     @staticmethod
@@ -625,7 +620,9 @@ class RepoIngestor:
         # or hanging lookup for one host cannot stall cache access for
         # concurrent lookups of other hosts.
         try:
-            addrinfos = socket.getaddrinfo(host, None, type=socket.SOCK_STREAM)
+            addrinfos = socket.getaddrinfo(
+                host, None, type=socket.SOCK_STREAM
+            )
         except socket.gaierror as exc:
             raise ValidationError(
                 f"Cannot resolve repository host {host!r}: {exc}"
@@ -798,7 +795,9 @@ class RepoIngestor:
                 f"Allowed schemes: {sorted(ALLOWED_REPO_URL_SCHEMES)}"
             )
         if not parsed.netloc or not host:
-            raise ValidationError(f"Repository URL must include a host: {repo_url}")
+            raise ValidationError(
+                f"Repository URL must include a host: {repo_url}"
+            )
 
         RepoIngestor._validate_repo_host(host)
 
@@ -813,7 +812,9 @@ class RepoIngestor:
             "include_extensions",
             "max_depth",
         }
-        candidate = {k: v for k, v in options.items() if k not in non_git_options}
+        candidate = {
+            k: v for k, v in options.items() if k not in non_git_options
+        }
         unsafe = set(candidate) - ALLOWED_CLONE_OPTIONS
         if unsafe:
             raise ValidationError(
@@ -892,7 +893,9 @@ class RepoIngestor:
             if "include_extensions" in options:
                 # Normalize extensions to include dot prefix
                 exts = options["include_extensions"]
-                normalized_exts = [e if e.startswith(".") else f".{e}" for e in exts]
+                normalized_exts = [
+                    e if e.startswith(".") else f".{e}" for e in exts
+                ]
                 file_filters["extensions"] = normalized_exts
 
             # Process code files
@@ -1059,14 +1062,14 @@ class RepoIngestor:
         return code_files
 
     def get_repository_info(
-        self, repo_url: str, repo: Optional[Any] = None
+        self, repo_url: str, repo: Optional[git.Repo] = None
     ) -> Dict[str, Any]:
         """
         Get repository metadata and information.
 
         Args:
             repo_url: Repository URL
-            repo: Git repository object (git.Repo, optional)
+            repo: Git repository object (optional)
 
         Returns:
             dict: Repository information
@@ -1108,7 +1111,6 @@ class RepoIngestor:
     def cleanup(self):
         """Cleanup temporary repository files."""
         if self.temp_dir and os.path.exists(self.temp_dir):
-
             def onexc(func, path, exc_info):
                 """
                 Error handler for shutil.rmtree.
@@ -1121,7 +1123,6 @@ class RepoIngestor:
                 Usage : shutil.rmtree(path, onerror=onexc)
                 """
                 import stat
-
                 if not os.access(path, os.W_OK):
                     # Is the error an access error ?
                     os.chmod(path, stat.S_IWUSR)

semantica/ingest/xml_ingestor.py

@@ -24,10 +24,7 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple, Union
 
-try:
-    from lxml import etree
-except (ImportError, OSError):
-    etree = None
+from lxml import etree
 
 from ..utils.constants import FILE_SIZE_LIMITS
 from ..utils.exceptions import ProcessingError, ValidationError
@@ -75,11 +72,6 @@ class XMLIngestor:
             **kwargs: Additional configuration values
         """
         self.logger = get_logger("xml_ingestor")
-        if etree is None:
-            raise ImportError(
-                "lxml is required for XMLIngestor. "
-                "Install it with: pip install 'semantica[documents]'"
-            )
         self.config = config or {}
         self.config.update(kwargs)
         self.progress_tracker = get_progress_tracker()
@@ -792,8 +784,8 @@ class XMLIngestor:
         first_error = errors[0] if errors else "No detailed validation error available."
         return f"{prefix} for {source}: {first_error}"
 
-    def _format_xml_error(self, exc: Any) -> str:
-        if hasattr(exc, "error_log") and exc.error_log:
+    def _format_xml_error(self, exc: etree.XMLSyntaxError) -> str:
+        if exc.error_log:
             return str(exc.error_log.last_error)
         return str(exc)
 

semantica/kg/node_embeddings.py

@@ -141,7 +141,7 @@ class NodeEmbedder:
 
         if method == "node2vec" and not GENSIM_AVAILABLE:
             raise ImportError(
-                "gensim is required for Node2Vec. Install with: pip install 'semantica[graph-embeddings]'"
+                "gensim is required for Node2Vec. Install with: pip install gensim"
             )
     
     def compute_embeddings(

semantica/parse/docx_parser.py

@@ -32,20 +32,12 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
-try:
-    from docx import Document
-    from docx.document import Document as DocxDocument
-    from docx.oxml.table import CT_Tbl
-    from docx.oxml.text.paragraph import CT_P
-    from docx.table import Table
-    from docx.text.paragraph import Paragraph
-except (ImportError, OSError):
-    Document = None
-    DocxDocument = None
-    CT_Tbl = None
-    CT_P = None
-    Table = None
-    Paragraph = None
+from docx import Document
+from docx.document import Document as DocxDocument
+from docx.oxml.table import CT_Tbl
+from docx.oxml.text.paragraph import CT_P
+from docx.table import Table
+from docx.text.paragraph import Paragraph
 
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
@@ -92,9 +84,7 @@ class DOCXParser:
         self.config = config
         self.progress_tracker = get_progress_tracker()
 
-    def parse(
-        self, file_path: Union[str, Path], pipeline_id: Optional[str] = None, **options
-    ) -> Dict[str, Any]:
+    def parse(self, file_path: Union[str, Path], pipeline_id: Optional[str] = None, **options) -> Dict[str, Any]:
         """
         Parse DOCX document.
 
@@ -109,12 +99,6 @@ class DOCXParser:
         Returns:
             dict: Parsed document data
         """
-        if Document is None:
-            raise ProcessingError(
-                "python-docx is required to parse DOCX files. "
-                "Install it with: pip install 'semantica[documents]'"
-            )
-
         file_path = Path(file_path)
 
         # Track DOCX parsing

semantica/parse/excel_parser.py

@@ -33,11 +33,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
 import pandas as pd
-
-try:
-    from openpyxl import load_workbook
-except (ImportError, OSError):
-    load_workbook = None
+from openpyxl import load_workbook
 
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
@@ -96,12 +92,6 @@ class ExcelParser:
         Returns:
             ExcelData or ExcelSheet: Parsed Excel data
         """
-        if load_workbook is None:
-            raise ProcessingError(
-                "openpyxl is required to parse Excel files. "
-                "Install it with: pip install 'semantica[documents]'"
-            )
-
         file_path = Path(file_path)
 
         # Track Excel parsing

semantica/parse/html_parser.py

@@ -33,10 +33,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 from urllib.parse import urljoin
 
-try:
-    from bs4 import BeautifulSoup
-except (ImportError, OSError):
-    BeautifulSoup = None
+from bs4 import BeautifulSoup
 
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
@@ -116,12 +113,6 @@ class HTMLParser:
         Returns:
             HTMLData: Parsed HTML data
         """
-        if BeautifulSoup is None:
-            raise ProcessingError(
-                "beautifulsoup4 is required to parse HTML files. "
-                "Install it with: pip install 'semantica[documents]'"
-            )
-
         # Track HTML parsing
         file_path = None
         if isinstance(html_content, Path) or (

semantica/parse/methods.py

@@ -123,6 +123,7 @@ Example Usage:
 from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Union
 
+from ..utils.exceptions import ConfigurationError, ProcessingError
 from ..utils.logging import get_logger
 from ..utils.custom_methods import CUSTOM_METHOD_FELL_BACK, call_custom_method
 from .code_parser import CodeParser
@@ -177,16 +178,10 @@ def parse_document(
         >>> text = parse_document("document.pdf", method="default", extract_text=True)
     """
     custom_method = method_registry.get("document", method)
-    if custom_method and custom_method != parse_document:
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            file_type,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, file_type, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -253,8 +248,7 @@ def parse_document_docling(
 
 # Register Docling method
 try:
-    from . import docling_parser  # noqa: F401
-
+    from .docling_parser import DoclingParser
     method_registry.register("document", "docling", parse_document_docling)
 except (ImportError, OSError):
     # Docling not available, skip registration
@@ -295,17 +289,10 @@ def parse_web_content(
         >>> html = parse_web_content("page.html", content_type="html", method="default")
     """
     custom_method = method_registry.get("web", method)
-    if custom_method and custom_method != parse_web_content:
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            content,
-            content_type,
-            base_url,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, content, content_type, base_url, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -358,16 +345,10 @@ def parse_structured_data(
         >>> csv_data = parse_structured_data("data.csv", data_format="csv", method="default")
     """
     custom_method = method_registry.get("structured", method)
-    if custom_method and custom_method != parse_structured_data:
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            data,
-            data_format,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, data, data_format, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -411,15 +392,10 @@ def parse_email(
         >>> headers = parse_email("email.eml", method="headers")
     """
     custom_method = method_registry.get("email", method)
-    if custom_method and custom_method != parse_email:
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            email_content,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, email_content, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -466,16 +442,10 @@ def parse_code(
         >>> structure = parse_code("script.py", method="ast")
     """
     custom_method = method_registry.get("code", method)
-    if custom_method and custom_method != parse_code:
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            language,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, language, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -525,16 +495,10 @@ def parse_media(
         >>> video = parse_media("video.mp4", method="default")
     """
     custom_method = method_registry.get("media", method)
-    if custom_method and custom_method != parse_media:
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            media_type,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, media_type, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -577,15 +541,10 @@ def parse_pdf(
         >>> pages = parse_pdf("document.pdf", method="default", pages=[1, 2, 3])
     """
     custom_method = method_registry.get("document", method)
-    if custom_method and custom_method not in (parse_pdf, parse_document):
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -626,15 +585,10 @@ def parse_docx(
         >>> docx = parse_docx("document.docx", method="default")
     """
     custom_method = method_registry.get("document", method)
-    if custom_method and custom_method not in (parse_docx, parse_document):
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -674,15 +628,10 @@ def parse_json(file_path: Union[str, Path], method: str = "default", **kwargs) -
         >>> flattened = parse_json("data.json", method="default", flatten=True)
     """
     custom_method = method_registry.get("structured", method)
-    if custom_method and custom_method not in (parse_json, parse_structured_data):
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -726,16 +675,10 @@ def parse_csv(
         >>> tab_separated = parse_csv("data.tsv", delimiter="\t", method="default")
     """
     custom_method = method_registry.get("structured", method)
-    if custom_method and custom_method not in (parse_csv, parse_structured_data):
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            delimiter,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, delimiter, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -771,15 +714,10 @@ def parse_xml(file_path: Union[str, Path], method: str = "default", **kwargs) ->
         >>> xml_data = parse_xml("data.xml", method="default")
     """
     custom_method = method_registry.get("structured", method)
-    if custom_method and custom_method not in (parse_xml, parse_structured_data):
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result
@@ -824,15 +762,10 @@ def parse_image(
         >>> ocr_text = image.get("ocr_result", {}).get("text", "")
     """
     custom_method = method_registry.get("media", method)
-    if custom_method and custom_method not in (parse_image, parse_media):
+    if custom_method:
         fallback = kwargs.pop("fallback_on_custom_error", False)
         result = call_custom_method(
-            logger,
-            method,
-            custom_method,
-            file_path,
-            fallback_on_custom_error=fallback,
-            **kwargs,
+            logger, method, custom_method, file_path, fallback_on_custom_error=fallback, **kwargs
         )
         if result is not CUSTOM_METHOD_FELL_BACK:
             return result

semantica/parse/web_parser.py

@@ -33,10 +33,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 from urllib.parse import urljoin, urlparse
 
-try:
-    from bs4 import BeautifulSoup
-except (ImportError, OSError):
-    BeautifulSoup = None
+from bs4 import BeautifulSoup
 
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
@@ -190,12 +187,6 @@ class HTMLContentParser(HTMLParser):
         }
 
         # Load HTML for structure extraction
-        if BeautifulSoup is None:
-            raise ProcessingError(
-                "beautifulsoup4 is required for HTML structure extraction. "
-                "Install it with: pip install 'semantica[documents]'"
-            )
-
         if isinstance(html_content, Path) or (
             isinstance(html_content, str) and Path(html_content).exists()
         ):
@@ -252,12 +243,6 @@ class HTMLContentParser(HTMLParser):
         else:
             html_string = html_content
 
-        if BeautifulSoup is None:
-            raise ProcessingError(
-                "beautifulsoup4 is required for HTML cleaning. "
-                "Install it with: pip install 'semantica[documents]'"
-            )
-
         soup = BeautifulSoup(html_string, "html.parser")
 
         # Remove scripts and styles

semantica/parse/xml_parser.py

@@ -34,10 +34,7 @@ from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
-try:
-    from lxml import etree
-except (ImportError, OSError):
-    etree = None
+from lxml import etree
 
 from ..utils.exceptions import ProcessingError, ValidationError
 from ..utils.logging import get_logger
@@ -108,13 +105,7 @@ class XMLParser:
         )
 
         try:
-            explicit_engine = options.get("engine") or self.config.get("engine")
-            engine = explicit_engine or ("lxml" if etree is not None else "etree")
-            if engine == "lxml" and etree is None:
-                raise ProcessingError(
-                    "lxml is required to parse XML with engine='lxml'. "
-                    "Install it with: pip install 'semantica[documents]'"
-                )
+            engine = options.get("engine", "lxml")
 
             # Load XML content
             if file_path_obj:
@@ -156,7 +147,7 @@ class XMLParser:
         self, xml_string: str, source: str, options: Dict[str, Any]
     ) -> XMLData:
         """Parse XML using lxml."""
-        parser = etree.XMLParser(remove_blank_text=True, remove_comments=True)
+        parser = etree.XMLParser(remove_blank_text=True)
         root = etree.fromstring(xml_string.encode("utf-8"), parser)
 
         # Extract namespaces
@@ -197,10 +188,8 @@ class XMLParser:
             metadata={"source": source, "engine": "etree"},
         )
 
-    def _element_to_xml_element(self, element) -> Optional[XMLElement]:
+    def _element_to_xml_element(self, element) -> XMLElement:
         """Convert lxml element to XMLElement."""
-        if not hasattr(element, "tag") or not isinstance(element.tag, str):
-            return None
         tag = element.tag
         if "}" in tag:
             namespace, tag = tag.split("}", 1)
@@ -217,18 +206,12 @@ class XMLParser:
 
         # Process children
         for child in element:
-            child_elem = self._element_to_xml_element(child)
-            if child_elem is not None:
-                xml_elem.children.append(child_elem)
+            xml_elem.children.append(self._element_to_xml_element(child))
 
         return xml_elem
 
-    def _etree_element_to_xml_element(
-        self, element: ET.Element
-    ) -> Optional[XMLElement]:
+    def _etree_element_to_xml_element(self, element: ET.Element) -> XMLElement:
         """Convert ElementTree element to XMLElement."""
-        if not hasattr(element, "tag") or not isinstance(element.tag, str):
-            return None
         tag = element.tag
         if "}" in tag:
             namespace, tag = tag.split("}", 1)
@@ -245,9 +228,7 @@ class XMLParser:
 
         # Process children
         for child in element:
-            child_elem = self._etree_element_to_xml_element(child)
-            if child_elem is not None:
-                xml_elem.children.append(child_elem)
+            xml_elem.children.append(self._etree_element_to_xml_element(child))
 
         return xml_elem
 
@@ -268,30 +249,18 @@ class XMLParser:
         xml_data = self.parse(file_path, **options)
 
         # Use lxml for XPath queries
-        if etree is None:
-            raise ProcessingError(
-                "lxml is required for find_elements (XPath queries). "
-                "Install it with: pip install 'semantica[documents]'"
-            )
-
         xml_string = (
             file_path
             if isinstance(file_path, str) and not Path(file_path).exists()
-            else Path(file_path).read_text(encoding="utf-8")
+            else Path(file_path).read_text()
         )
-        parser = etree.XMLParser(remove_blank_text=True, remove_comments=True)
-        root = etree.fromstring(xml_string.encode("utf-8"), parser=parser)
+        root = etree.fromstring(xml_string.encode("utf-8"))
 
         # Register namespaces for XPath
         namespaces = xml_data.namespaces
         elements = root.xpath(xpath, namespaces=namespaces)
 
-        results = []
-        for elem in elements:
-            xml_elem = self._element_to_xml_element(elem)
-            if xml_elem is not None:
-                results.append(xml_elem)
-        return results
+        return [self._element_to_xml_element(elem) for elem in elements]
 
     def extract_by_tag(
         self, file_path: Union[str, Path], tag_name: str, **options

semantica/semantic_extract/methods.py

@@ -209,11 +209,6 @@ def load_spacy_model(name: str):
     Raises whatever ``spacy.load`` raises (``OSError`` for a missing model), so
     callers keep their existing fallback behavior.
     """
-    if spacy is None:
-        raise ImportError(
-            "spaCy is not installed. Install with: pip install 'semantica[nlp-spacy]'"
-        )
-
     cached = _spacy_model_cache.get(name)
     if cached is not None and cached[0] is spacy:
         return cached[1]

semantica/utils/helpers.py

@@ -38,15 +38,15 @@ Example Usage:
     >>> from semantica.utils import clean_text, normalize_entities
     >>> cleaned = clean_text("  Hello   World  ")
     >>> entities = normalize_entities([{"id": "e1", "text": "John", "type": "PERSON"}])
-    >>>
+    >>> 
     >>> from semantica.utils import hash_data, safe_filename
     >>> data_hash = hash_data({"key": "value"})
     >>> safe_name = safe_filename("my file.txt")
-    >>>
+    >>> 
     >>> from semantica.utils import merge_dicts, get_nested_value
     >>> merged = merge_dicts({"a": 1}, {"b": 2}, deep=True)
     >>> value = get_nested_value(config, "database.host", default="localhost")
-    >>>
+    >>> 
     >>> from semantica.utils import retry_on_error
     >>> @retry_on_error(max_retries=3, delay=1.0)
     ... def fetch_data():
@@ -457,9 +457,7 @@ def chunk_list(items: List[Any], chunk_size: int) -> List[List[Any]]:
     Returns:
         List of chunks
     """
-    return [items[i : i + chunk_size] for i in range(0, len(items), chunk_size)]
-
-
+    return [items[i : i + chunk_size] for i in range(0, len(items), chunk_size)]    
 def flatten_dict(
     d: Dict[str, Any], parent_key: str = "", sep: str = "."
 ) -> Dict[str, Any]:
@@ -558,27 +556,27 @@ def safe_import(
 ) -> Tuple[Any, bool]:
     """
     Safely import an optional module, handling both ImportError and OSError.
-
+    
     This is useful for optional dependencies that may fail to import due to:
     - Missing package (ImportError)
     - DLL loading failures on Windows, e.g., PyTorch (OSError)
-
+    
     Args:
         module_name: Name of the module to import (e.g., "spacy", "docling.document_converter")
         package: Optional package name for relative imports
         default: Default value to return if import fails
         error_message: Optional custom error message for logging
-
+        
     Returns:
         Tuple of (module_or_default, success_flag):
         - If import succeeds: (imported_module, True)
         - If import fails: (default, False)
-
+        
     Example:
         >>> spacy, available = safe_import("spacy")
         >>> if available:
         ...     doc = spacy.load("en_core_web_sm")
-        >>>
+        >>> 
         >>> converter, available = safe_import("docling.document_converter", default=None)
         >>> if available:
         ...     converter = converter()
@@ -589,13 +587,11 @@ def safe_import(
         else:
             module = importlib.import_module(module_name)
         return module, True
-    except (ImportError, OSError) as e:
+    except (ImportError, ModuleNotFoundError, OSError) as e:
         if error_message:
             import sys
-
             if "logging" in sys.modules:
                 from .logging import get_logger
-
                 logger = get_logger("utils.helpers")
                 logger.debug(f"{error_message}: {e}")
         return default, False
@@ -811,13 +807,9 @@ def _is_record(value: Any) -> bool:
     exporters rather than a ``ValidationError`` at the boundary where the
     problem is visible.
     """
-    return (
-        isinstance(value, Mapping)
-        or is_dataclass(value)
-        or (
-            hasattr(value, "__dict__")
-            and not isinstance(value, (types.ModuleType, type))
-        )
+    return isinstance(value, Mapping) or is_dataclass(value) or (
+        hasattr(value, "__dict__")
+        and not isinstance(value, (types.ModuleType, type))
     )
 
 

semantica/vector_store/faiss_store.py

@@ -343,9 +343,7 @@ class FAISSIndex:
         was originally saved.
         """
         if not FAISS_AVAILABLE:
-            raise ProcessingError(
-                "FAISS not available. Install with: pip install 'semantica[vectorstore-faiss]' (or 'semantica[gpu]' for CUDA)"
-            )
+            raise ProcessingError("FAISS not available")
 
         path = Path(path)
         index = faiss.read_index(str(path))
@@ -484,7 +482,7 @@ class FAISSIndexBuilder:
         """
         if not FAISS_AVAILABLE:
             raise ProcessingError(
-                "FAISS is not available. Install it with: pip install 'semantica[vectorstore-faiss]' (or 'semantica[gpu]' for CUDA)"
+                "FAISS is not available. Install it with: pip install faiss-cpu or faiss-gpu"
             )
 
         # Create index based on type
@@ -556,7 +554,7 @@ class FAISSStore:
         # Check FAISS availability
         if not FAISS_AVAILABLE:
             self.logger.warning(
-                "FAISS not available. Install with: pip install 'semantica[vectorstore-faiss]' (or 'semantica[gpu]' for CUDA)"
+                "FAISS not available. Install with: pip install faiss-cpu or faiss-gpu"
             )
 
     def create_index(
@@ -755,9 +753,7 @@ class FAISSStore:
             FAISSIndex instance
         """
         if not FAISS_AVAILABLE:
-            raise ProcessingError(
-                "FAISS not available. Install with: pip install 'semantica[vectorstore-faiss]' (or 'semantica[gpu]' for CUDA)"
-            )
+            raise ProcessingError("FAISS not available")
 
         path = Path(path)
         if path.exists() and not _metadata_path(path).exists():

semantica/vector_store/qdrant_store.py

@@ -153,9 +153,12 @@ class QdrantCollection:
             raise ProcessingError("Qdrant not available")
 
         try:
-            search_results = self.client.search(
+            # qdrant-client >=1.10.0: query_points() supersedes the removed search().
+            # It returns a QueryResponse whose .points attribute is a list of
+            # ScoredPoint objects (id, score, payload, …).
+            response = self.client.query_points(
                 collection_name=self.collection_name,
-                query_vector=query_vector.tolist(),
+                query=query_vector.tolist(),
                 limit=limit,
                 query_filter=query_filter,
                 with_payload=True,
@@ -164,19 +167,19 @@ class QdrantCollection:
             )
 
             results = []
-            for result in search_results:
+            for point in response.points:
                 results.append(
                     {
-                        "id": result.id,
+                        "id": point.id,
                         # See pinecone_store.py PineconeIndex.search_vectors for why
                         # this uses x/(1+|x|) rather than clamping distance-to-zero:
                         # Qdrant's Dot distance metric is unbounded, and the old
                         # clamped formula collapsed every score >= 1.0 to 1.0.
                         "score": (
-                            float(result.score) / (1.0 + abs(float(result.score))) + 1.0
+                            float(point.score) / (1.0 + abs(float(point.score))) + 1.0
                         )
                         / 2.0,
-                        "metadata": result.payload or {},
+                        "metadata": point.payload or {},
                         "vector": None,
                         "distance": None,
                     }
@@ -695,9 +698,31 @@ class QdrantStore:
             collection_info = self.client.get_collection(
                 self.collection.collection_name
             )
+            # vectors_count was removed in qdrant-client 1.16.0.
+            # When it is absent, only infer the total from points_count if we
+            # can confirm the collection uses a single unnamed vector per point
+            # (VectorParams). Named/multi-vector collections (dict of VectorParams)
+            # have an unknown multiplier, so return None rather than a wrong value.
+            # get_collection() accepts externally-created collections without schema
+            # validation, so the schema must be inspected at stats time.
+            vectors_count_fallback: Optional[int]
+            try:
+                vectors_cfg = collection_info.config.params.vectors
+                vectors_count_fallback = (
+                    collection_info.points_count
+                    if QDRANT_AVAILABLE and isinstance(vectors_cfg, VectorParams)
+                    else None
+                )
+            except Exception:
+                vectors_count_fallback = None
+
             return {
                 "points_count": collection_info.points_count,
-                "vectors_count": collection_info.vectors_count,
+                "vectors_count": getattr(
+                    collection_info,
+                    "vectors_count",
+                    vectors_count_fallback,
+                ),
                 "status": str(collection_info.status)
                 if hasattr(collection_info, "status")
                 else "unknown",

semantica/visualization/analytics_visualizer.py

@@ -85,7 +85,7 @@ class AnalyticsVisualizer:
         if px is None or go is None:
             raise ProcessingError(
                 "Plotly is required for analytics visualization. "
-                "Install with: pip install 'semantica[viz]'"
+                "Install with: pip install plotly"
             )
         if np is None:
             raise ProcessingError(

semantica/visualization/embedding_visualizer.py

@@ -1,10 +1,9 @@
 """
 Embedding Visualizer Module
 
-This module provides comprehensive visualization capabilities for vector
-embeddings in the Semantica framework, including 2D/3D dimensionality
-reduction projections, similarity heatmaps, clustering visualizations,
-multi-modal comparisons, and quality metrics analysis.
+This module provides comprehensive visualization capabilities for vector embeddings in the
+Semantica framework, including 2D/3D dimensionality reduction projections, similarity heatmaps,
+clustering visualizations, multi-modal comparisons, and quality metrics analysis.
 
 Key Features:
     - 2D and 3D dimensionality reduction (UMAP, t-SNE, PCA)
@@ -32,8 +31,9 @@ License: MIT
 """
 
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional, Tuple, Union
 
+import matplotlib.pyplot as plt
 import numpy as np
 
 try:
@@ -45,12 +45,8 @@ except (ImportError, OSError):
     go = None
     make_subplots = None
 
-try:
-    from sklearn.decomposition import PCA
-    from sklearn.manifold import TSNE
-except (ImportError, OSError):
-    PCA = None
-    TSNE = None
+from sklearn.decomposition import PCA
+from sklearn.manifold import TSNE
 
 try:
     import umap
@@ -61,7 +57,7 @@ from ..utils.exceptions import ProcessingError
 from ..utils.logging import get_logger
 from ..utils.progress_tracker import get_progress_tracker
 from .utils.color_schemes import ColorPalette, ColorScheme
-from .utils.export_formats import export_plotly_figure
+from .utils.export_formats import export_matplotlib_figure, export_plotly_figure
 
 
 class EmbeddingVisualizer:
@@ -98,17 +94,12 @@ class EmbeddingVisualizer:
             self.color_scheme = ColorScheme.DEFAULT
         self.point_size = config.get("point_size", 5)
 
-    def _check_dependencies(self, require_sklearn: bool = False):
+    def _check_dependencies(self):
         """Check if dependencies are available."""
         if px is None or go is None:
             raise ProcessingError(
                 "Plotly is required for embedding visualization. "
-                "Install with: pip install 'semantica[viz]'"
-            )
-        if require_sklearn and (PCA is None or TSNE is None):
-            raise ProcessingError(
-                "scikit-learn is required for dimensionality reduction. "
-                "Reinstall scikit-learn or install dependencies."
+                "Install with: pip install plotly"
             )
 
     def visualize_2d_projection(
@@ -159,12 +150,10 @@ class EmbeddingVisualizer:
 
         try:
             self.logger.info(f"Visualizing 2D projection using {method}")
-
+            
             # Step 2: Data Analysis
             n_samples, n_features = embeddings.shape
-            self.logger.info(
-                f"Embedding Analysis: {n_samples} samples, {n_features} dimensions"
-            )
+            self.logger.info(f"Embedding Analysis: {n_samples} samples, {n_features} dimensions")
 
             if embeddings.shape[1] <= 2:
                 # Already 2D or less, use directly
@@ -176,32 +165,28 @@ class EmbeddingVisualizer:
                 self.progress_tracker.update_tracking(
                     tracking_id, message=f"Reducing dimensions using {method}..."
                 )
-                dim_options = dict(options)
-                n_comp = dim_options.pop("n_components", 2)
                 projected = self._reduce_dimensions(
-                    embeddings, method=method, n_components=n_comp, **dim_options
+                    embeddings, method=method, n_components=2, **options
                 )
 
             self.progress_tracker.update_tracking(
                 tracking_id, message="Generating visualization..."
             )
             result = self._visualize_2d_plotly(
-                projected,
-                labels,
-                output,
-                file_path,
+                projected, 
+                labels, 
+                output, 
+                file_path, 
                 color_by=color_by,
                 size_by=size_by,
                 hover_data=hover_data,
-                **options,
+                **options
             )
 
             self.progress_tracker.stop_tracking(
                 tracking_id,
                 status="completed",
-                message=(
-                    f"2D projection visualization generated: {len(projected)} points"
-                ),
+                message=f"2D projection visualization generated: {len(projected)} points",
             )
             return result
         except Exception as e:
@@ -252,10 +237,8 @@ class EmbeddingVisualizer:
                 self.progress_tracker.update_tracking(
                     tracking_id, message=f"Reducing dimensions using {method}..."
                 )
-                dim_options = dict(options)
-                n_comp = dim_options.pop("n_components", 3)
                 projected = self._reduce_dimensions(
-                    embeddings, method=method, n_components=n_comp, **dim_options
+                    embeddings, method=method, n_components=3, **options
                 )
 
             self.progress_tracker.update_tracking(
@@ -268,9 +251,7 @@ class EmbeddingVisualizer:
             self.progress_tracker.stop_tracking(
                 tracking_id,
                 status="completed",
-                message=(
-                    f"3D projection visualization generated: {len(projected)} points"
-                ),
+                message=f"3D projection visualization generated: {len(projected)} points",
             )
             return result
         except Exception as e:
@@ -361,10 +342,7 @@ class EmbeddingVisualizer:
                 self.progress_tracker.stop_tracking(
                     tracking_id,
                     status="completed",
-                    message=(
-                        f"Similarity heatmap generated: "
-                        f"{len(embeddings)}x{len(embeddings)} matrix"
-                    ),
+                    message=f"Similarity heatmap generated: {len(embeddings)}x{len(embeddings)} matrix",
                 )
                 return fig
             elif file_path:
@@ -426,10 +404,8 @@ class EmbeddingVisualizer:
                 self.progress_tracker.update_tracking(
                     tracking_id, message=f"Reducing dimensions using {method}..."
                 )
-                dim_options = dict(options)
-                n_comp = dim_options.pop("n_components", 2)
                 projected = self._reduce_dimensions(
-                    embeddings, method=method, n_components=n_comp, **dim_options
+                    embeddings, method=method, n_components=2, **options
                 )
 
             num_clusters = len(set(cluster_labels))
@@ -469,10 +445,7 @@ class EmbeddingVisualizer:
                 self.progress_tracker.stop_tracking(
                     tracking_id,
                     status="completed",
-                    message=(
-                        f"Clustering visualization generated: "
-                        f"{num_clusters} clusters, {len(embeddings)} points"
-                    ),
+                    message=f"Clustering visualization generated: {num_clusters} clusters, {len(embeddings)} points",
                 )
                 return fig
             elif file_path:
@@ -568,13 +541,8 @@ class EmbeddingVisualizer:
                 self.progress_tracker.update_tracking(
                     tracking_id, message=f"Reducing dimensions using {method}..."
                 )
-                dim_options = dict(options)
-                n_comp = dim_options.pop("n_components", 2)
                 projected = self._reduce_dimensions(
-                    combined_embeddings,
-                    method=method,
-                    n_components=n_comp,
-                    **dim_options,
+                    combined_embeddings, method=method, n_components=2, **options
                 )
 
             # Color by type
@@ -611,10 +579,7 @@ class EmbeddingVisualizer:
                 self.progress_tracker.stop_tracking(
                     tracking_id,
                     status="completed",
-                    message=(
-                        f"Multi-modal comparison generated: "
-                        f"{len(combined_embeddings)} embeddings"
-                    ),
+                    message=f"Multi-modal comparison generated: {len(combined_embeddings)} embeddings",
                 )
                 return fig
             elif file_path:
@@ -633,6 +598,8 @@ class EmbeddingVisualizer:
             )
             raise
 
+
+
     def _reduce_dimensions(
         self,
         embeddings: np.ndarray,
@@ -641,56 +608,39 @@ class EmbeddingVisualizer:
         **options,
     ) -> np.ndarray:
         """Reduce embedding dimensions using specified method."""
-        opts = dict(options)
-        opts.pop("n_components", None)
-
         if method == "pca":
-            if PCA is None:
-                raise ProcessingError(
-                    "scikit-learn is required for dimensionality reduction. "
-                    "Reinstall scikit-learn or install dependencies."
-                )
-            pca = PCA(n_components=n_components, **opts)
+            pca = PCA(n_components=n_components, **options)
             return pca.fit_transform(embeddings)
 
         elif method == "tsne":
-            if TSNE is None:
-                raise ProcessingError(
-                    "scikit-learn is required for dimensionality reduction. "
-                    "Reinstall scikit-learn or install dependencies."
-                )
-            perplexity = opts.pop("perplexity", min(30, len(embeddings) - 1))
-            random_state = opts.pop("random_state", 42)
+            perplexity = options.get("perplexity", min(30, len(embeddings) - 1))
             tsne = TSNE(
                 n_components=n_components,
                 perplexity=perplexity,
-                random_state=random_state,
-                **opts,
+                random_state=42,
+                **options,
             )
             return tsne.fit_transform(embeddings)
 
         elif method == "umap":
             if umap is not None:
-                n_neighbors = opts.pop("n_neighbors", min(15, len(embeddings) - 1))
+                n_neighbors = options.get("n_neighbors", min(15, len(embeddings) - 1))
                 reducer = umap.UMAP(
-                    n_components=n_components, n_neighbors=n_neighbors, **opts
+                    n_components=n_components, n_neighbors=n_neighbors, **options
                 )
                 return reducer.fit_transform(embeddings)
             else:
-                raise ProcessingError(
-                    "UMAP is required for UMAP dimensionality reduction. "
-                    "Install with: pip install 'semantica[viz]'"
+                # Fallback to PCA if UMAP not available
+                self.logger.warning(
+                    "UMAP not available, using PCA. Install with: pip install umap-learn"
                 )
+                pca = PCA(n_components=n_components)
+                return pca.fit_transform(embeddings)
 
         else:
-            if PCA is None:
-                raise ProcessingError(
-                    "scikit-learn is required for dimensionality reduction. "
-                    "Reinstall scikit-learn or install dependencies."
-                )
             # Fallback to PCA
             self.logger.warning(f"Method {method} not available, using PCA")
-            pca = PCA(n_components=n_components, **opts)
+            pca = PCA(n_components=n_components)
             return pca.fit_transform(embeddings)
 
     def _visualize_2d_plotly(

semantica/visualization/kg_visualizer.py

@@ -124,7 +124,7 @@ class KGVisualizer:
         if px is None or go is None:
             raise ProcessingError(
                 "Plotly is required for KG visualization. "
-                "Install with: pip install 'semantica[viz]'"
+                "Install with: pip install plotly"
             )
 
     def _convert_knowledge_graph(self, kg: Any) -> Dict[str, Any]:

semantica/visualization/ontology_visualizer.py

@@ -35,14 +35,8 @@ License: MIT
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 
-try:
-    import matplotlib.patches as mpatches
-    import matplotlib.pyplot as plt
-    from matplotlib.patches import FancyBboxPatch
-except (ImportError, OSError):
-    mpatches = None
-    plt = None
-    FancyBboxPatch = None
+import matplotlib.patches as mpatches
+import matplotlib.pyplot as plt
 
 try:
     import plotly.express as px
@@ -53,6 +47,8 @@ except (ImportError, OSError):
     go = None
     make_subplots = None
 
+from matplotlib.patches import FancyBboxPatch
+
 try:
     import graphviz
 except (ImportError, OSError):
@@ -110,13 +106,13 @@ class OntologyVisualizer:
             if graphviz is None:
                 raise ProcessingError(
                     "Graphviz is required for DOT export. "
-                    "Install with: pip install 'semantica[viz]'"
+                    "Install with: pip install graphviz"
                 )
         else:
-            if go is None:
+            if px is None or go is None:
                 raise ProcessingError(
                     "Plotly is required for ontology visualization. "
-                    "Install with: pip install 'semantica[viz]'"
+                    "Install with: pip install plotly"
                 )
 
     def visualize_hierarchy(
@@ -896,7 +892,7 @@ class OntologyVisualizer:
         """Create Graphviz hierarchy visualization."""
         if graphviz is None:
             raise ProcessingError(
-                "Graphviz not available. Install with: pip install 'semantica[viz]'"
+                "Graphviz not available. Install with: pip install graphviz"
             )
 
         dot = graphviz.Digraph(comment="Ontology Hierarchy")

semantica/visualization/semantic_network_visualizer.py

@@ -74,7 +74,7 @@ class SemanticNetworkVisualizer:
         if px is None or go is None:
             raise ProcessingError(
                 "Plotly is required for semantic network visualization. "
-                "Install with: pip install 'semantica[viz]'"
+                "Install with: pip install plotly"
             )
 
     def visualize_network(

semantica/visualization/temporal_visualizer.py

@@ -83,7 +83,7 @@ class TemporalVisualizer:
         if px is None or go is None:
             raise ProcessingError(
                 "Plotly is required for temporal visualization. "
-                "Install with: pip install 'semantica[viz]'"
+                "Install with: pip install plotly"
             )
 
     def visualize_temporal_dashboard(

tests/ingest/test_optional_imports.py

@@ -141,134 +141,3 @@ else:
     assert "ConfigurationError" in result.stdout
     assert "Parquet ingestion" in result.stdout
     assert "pyarrow" in result.stdout
-
-
-def test_repo_ingestor_probe_fails_without_gitpython() -> None:
-    result = _run_python_with_blocked_modules(
-        """
-try:
-    from semantica.ingest import RepoIngestor
-    has_git = True
-except ImportError:
-    has_git = False
-
-assert not has_git, "Expected RepoIngestor import to fail without GitPython"
-print("RepoIngestor probe passed")
-""",
-        ("git",),
-    )
-
-    assert result.returncode == 0, result.stderr
-    assert "RepoIngestor probe passed" in result.stdout
-
-
-def test_xml_ingestor_probe_fails_without_lxml() -> None:
-    result = _run_python_with_blocked_modules(
-        """
-try:
-    from semantica.ingest import XMLIngestor
-    has_lxml = True
-except ImportError:
-    has_lxml = False
-
-assert not has_lxml, "Expected XMLIngestor import to fail without lxml"
-print("XMLIngestor probe passed")
-""",
-        ("lxml",),
-    )
-
-    assert result.returncode == 0, result.stderr
-    assert "XMLIngestor probe passed" in result.stdout
-
-
-def test_xml_ingestion_reports_missing_lxml_when_used() -> None:
-    result = _run_python_with_blocked_modules(
-        """
-from semantica.ingest import ingest_xml
-
-try:
-    ingest_xml("catalog.xml")
-except Exception as exc:
-    print(type(exc).__name__, exc)
-else:
-    raise SystemExit("expected XML ingestion to fail without lxml")
-""",
-        ("lxml",),
-    )
-
-    assert result.returncode == 0, result.stderr
-    assert "ConfigurationError" in result.stdout
-    assert "XML ingestion" in result.stdout
-    assert "lxml" in result.stdout
-
-
-def test_sibling_imports_succeed_without_optional_backends() -> None:
-    result = _run_python_with_blocked_modules(
-        """
-from semantica.ingest import (
-    CodeExtractor,
-    CodeFile,
-    CommitInfo,
-    GitAnalyzer,
-    XMLIngestionData,
-    SalesforceData,
-)
-print(
-    CodeExtractor.__name__,
-    CodeFile.__name__,
-    CommitInfo.__name__,
-    GitAnalyzer.__name__,
-    XMLIngestionData.__name__,
-    SalesforceData.__name__,
-)
-""",
-        ("git", "lxml", "simple_salesforce"),
-    )
-
-    assert result.returncode == 0, result.stderr
-    assert (
-        "CodeExtractor CodeFile CommitInfo GitAnalyzer XMLIngestionData SalesforceData"
-        in result.stdout
-    )
-
-
-def test_salesforce_ingestor_probe_fails_without_simple_salesforce() -> None:
-    result = _run_python_with_blocked_modules(
-        """
-try:
-    from semantica.ingest import SalesforceIngestor
-    has_salesforce = True
-except ImportError:
-    has_salesforce = False
-
-assert not has_salesforce, (
-    "Expected SalesforceIngestor import to fail without simple-salesforce"
-)
-print("SalesforceIngestor probe passed")
-""",
-        ("simple_salesforce",),
-    )
-
-    assert result.returncode == 0, result.stderr
-    assert "SalesforceIngestor probe passed" in result.stdout
-
-
-def test_salesforce_ingestion_reports_missing_dep_when_used() -> None:
-    result = _run_python_with_blocked_modules(
-        """
-from semantica.ingest import ingest_salesforce
-
-try:
-    ingest_salesforce()
-except Exception as exc:
-    print(type(exc).__name__, exc)
-else:
-    raise SystemExit("expected Salesforce ingestion to fail without simple-salesforce")
-""",
-        ("simple_salesforce",),
-    )
-
-    assert result.returncode == 0, result.stderr
-    assert "ConfigurationError" in result.stdout
-    assert "Salesforce ingestion" in result.stdout
-    assert "simple-salesforce" in result.stdout

tests/semantic_extract/test_temporal_extraction.py

@@ -18,40 +18,29 @@ from datetime import datetime, timezone
 from unittest.mock import MagicMock, patch
 
 # ── Mock optional heavyweight dependencies before any semantica import ──────
-_MOCKED_MODULES = [
-    "spacy",
-    "instructor",
-    "openai",
-    "groq",
-    "sentence_transformers",
-    "transformers",
-]
-_original_modules = {k: sys.modules.get(k) for k in _MOCKED_MODULES}
-
-for k in _MOCKED_MODULES:
-    sys.modules.setdefault(k, MagicMock())
+sys.modules.setdefault("spacy", MagicMock())
+sys.modules.setdefault("instructor", MagicMock())
+_openai_mock = MagicMock()
+sys.modules.setdefault("openai", _openai_mock)
+sys.modules.setdefault("groq", MagicMock())
+sys.modules.setdefault("sentence_transformers", MagicMock())
+sys.modules.setdefault("transformers", MagicMock())
+sys.modules.setdefault("torch", MagicMock())
 
 sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../..")))
 
-from semantica.semantic_extract.methods import extract_relations_llm  # noqa: E402
-
-for _key, _original in _original_modules.items():
-    if _original is None:
-        sys.modules.pop(_key, None)
-    else:
-        sys.modules[_key] = _original
-
-from semantica.semantic_extract.ner_extractor import Entity  # noqa: E402
-from semantica.semantic_extract.schemas import (  # noqa: E402
+from semantica.semantic_extract.methods import extract_relations_llm
+from semantica.semantic_extract.ner_extractor import Entity
+from semantica.semantic_extract.schemas import (
     RelationsResponse,
     RelationsWithTemporalResponse,
 )
-from semantica.kg.temporal_normalizer import TemporalNormalizer  # noqa: E402
-from semantica.utils.exceptions import TemporalAmbiguityWarning  # noqa: E402
+from semantica.kg.temporal_normalizer import TemporalNormalizer
+from semantica.utils.exceptions import TemporalAmbiguityWarning
+
 
 # ── Helpers ─────────────────────────────────────────────────────────────────
 
-
 def _make_entities():
     return [
         Entity(text="Apple", label="ORG", start_char=0, end_char=5),
@@ -67,17 +56,15 @@ def _ref_date():
 # Part 1 – extract_relations_llm() temporal flag
 # ============================================================================
 
-
 class TestTemporalExtractionFlag(unittest.TestCase):
 
     def setUp(self):
         from semantica.semantic_extract.methods import _result_cache
-
         _result_cache.clear()
 
     @patch("semantica.semantic_extract.methods.create_provider")
     def test_extract_temporal_bounds_true_adds_four_fields(self, mock_create):
-        """With extract_temporal_bounds=True all four temporal keys appear."""
+        """With extract_temporal_bounds=True all four temporal keys appear in metadata."""
         mock_prov = MagicMock()
         mock_prov.is_available.return_value = True
         mock_prov.generate_typed.return_value = RelationsWithTemporalResponse(
@@ -145,9 +132,7 @@ class TestTemporalExtractionFlag(unittest.TestCase):
         self.assertNotIn("temporal_source_text", meta)
 
     @patch("semantica.semantic_extract.methods.create_provider")
-    def test_no_temporal_signal_returns_zero_confidence_and_null_dates(
-        self, mock_create
-    ):
+    def test_no_temporal_signal_returns_zero_confidence_and_null_dates(self, mock_create):
         """When LLM returns no temporal signal, confidence=0.0 and dates are null."""
         mock_prov = MagicMock()
         mock_prov.is_available.return_value = True
@@ -212,12 +197,10 @@ class TestTemporalExtractionFlag(unittest.TestCase):
 
     @patch("semantica.semantic_extract.methods.create_provider")
     def test_correct_schema_used_when_temporal_true(self, mock_create):
-        """generate_typed is called with RelationsWithTemporalResponse."""
+        """generate_typed is called with RelationsWithTemporalResponse when flag=True."""
         mock_prov = MagicMock()
         mock_prov.is_available.return_value = True
-        mock_prov.generate_typed.return_value = RelationsWithTemporalResponse(
-            relations=[]
-        )
+        mock_prov.generate_typed.return_value = RelationsWithTemporalResponse(relations=[])
         mock_create.return_value = mock_prov
 
         extract_relations_llm(
@@ -252,7 +235,6 @@ class TestTemporalExtractionFlag(unittest.TestCase):
 # Part 2 – TemporalNormalizer: relative dates
 # ============================================================================
 
-
 class TestTemporalNormalizerRelativeDates(unittest.TestCase):
 
     def setUp(self):
@@ -331,13 +313,10 @@ class TestTemporalNormalizerRelativeDates(unittest.TestCase):
 # Part 3 – TemporalNormalizer: partial / structured dates
 # ============================================================================
 
-
 class TestTemporalNormalizerPartialDates(unittest.TestCase):
 
     def setUp(self):
-        self.tn = TemporalNormalizer(
-            reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc)
-        )
+        self.tn = TemporalNormalizer(reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc))
 
     def test_year_only(self):
         result = self.tn.normalize("2021")
@@ -417,13 +396,10 @@ class TestTemporalNormalizerPartialDates(unittest.TestCase):
 # Part 4 – TemporalNormalizer: ambiguous formats
 # ============================================================================
 
-
 class TestTemporalNormalizerAmbiguity(unittest.TestCase):
 
     def setUp(self):
-        self.tn = TemporalNormalizer(
-            reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc)
-        )
+        self.tn = TemporalNormalizer(reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc))
 
     def test_ambiguous_slash_date_raises_warning_and_returns_none(self):
         with warnings.catch_warnings(record=True) as w:
@@ -456,19 +432,14 @@ class TestTemporalNormalizerAmbiguity(unittest.TestCase):
 # Part 5 – TemporalNormalizer: domain phrase map
 # ============================================================================
 
-
 class TestTemporalNormalizerDomainPhrases(unittest.TestCase):
 
     def setUp(self):
-        self.tn = TemporalNormalizer(
-            reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc)
-        )
+        self.tn = TemporalNormalizer(reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc))
 
     def _assert_recognized(self, phrase):
         result = self.tn.normalize_phrase(phrase)
-        self.assertIsNotNone(
-            result, f"Expected phrase {phrase!r} to be recognized but got None"
-        )
+        self.assertIsNotNone(result, f"Expected phrase {phrase!r} to be recognized but got None")
         return result
 
     # General / Policy
@@ -551,7 +522,6 @@ class TestTemporalNormalizerDomainPhrases(unittest.TestCase):
 # Part 6 – TemporalNormalizer: custom phrase map
 # ============================================================================
 
-
 class TestTemporalNormalizerCustomPhraseMap(unittest.TestCase):
 
     def setUp(self):
@@ -595,12 +565,10 @@ class TestTemporalNormalizerCustomPhraseMap(unittest.TestCase):
 # Part 7 – Full pipeline: extract → normalize → BiTemporalFact
 # ============================================================================
 
-
 class TestFullPipelineTemporalToBiTemporal(unittest.TestCase):
 
     def setUp(self):
         from semantica.semantic_extract.methods import _result_cache
-
         _result_cache.clear()
 
     @patch("semantica.semantic_extract.methods.create_provider")
@@ -652,12 +620,10 @@ class TestFullPipelineTemporalToBiTemporal(unittest.TestCase):
         self.assertEqual(vf[0].day, 1)
 
         # Feed into BiTemporalFact
-        fact = BiTemporalFact.from_relationship(
-            {
-                "valid_from": "2014-05-01T00:00:00Z",
-                "valid_until": None,
-            }
-        )
+        fact = BiTemporalFact.from_relationship({
+            "valid_from": "2014-05-01T00:00:00Z",
+            "valid_until": None,
+        })
         self.assertIsNotNone(fact.valid_from)
         self.assertEqual(fact.valid_from.year, 2014)
         self.assertEqual(fact.valid_from.month, 5)
@@ -694,9 +660,7 @@ class TestFullPipelineTemporalToBiTemporal(unittest.TestCase):
             extract_temporal_bounds=True,
         )
         meta = rels[0].metadata
-        tn = TemporalNormalizer(
-            reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc)
-        )
+        tn = TemporalNormalizer(reference_date=datetime(2025, 3, 25, tzinfo=timezone.utc))
 
         vf = tn.normalize(meta["valid_from"])
         vu = tn.normalize(meta["valid_until"])

tests/test_cli_commands.py

@@ -2302,7 +2302,7 @@ class TestDoctorEmbeddings:
         checks = self._doctor_checks(runner)
         st = checks["Embeddings (sentence-transformers)"]
         assert st["status"] == "fail"
-        assert st["hint"] == "pip install 'semantica[embeddings-local]'"
+        assert st["hint"] == "pip install sentence-transformers"
 
     def test_deep_probe_detects_fallback_active(self, runner, monkeypatch):
         self._with_fake_st(monkeypatch)

tests/test_issue_1513_slim_core.py

@@ -1,454 +0,0 @@
-from pathlib import Path
-from unittest.mock import patch
-import pytest
-
-from semantica.parse.docx_parser import DOCXParser
-from semantica.parse.excel_parser import ExcelParser
-from semantica.parse.html_parser import HTMLParser
-from semantica.parse.xml_parser import XMLParser
-from semantica.utils.exceptions import ProcessingError
-
-
-def _load_toml(file_path: Path) -> dict:
-    """Load and parse a TOML file across Python 3.8-3.14+ without mode mismatches."""
-    content = file_path.read_text(encoding="utf-8")
-    try:
-        import tomllib  # Python 3.11+ standard library
-
-        return tomllib.loads(content)
-    except ImportError:
-        try:
-            import tomli  # Fast PEP 680 compatible parser for Python < 3.11
-
-            return tomli.loads(content)
-        except ImportError:
-            import toml  # Fallback toml parser
-
-            return toml.loads(content)
-
-
-def test_core_dependencies_count():
-    """pyproject.toml must contain exactly 22 unique core dependencies."""
-    repo_root = Path(__file__).resolve().parents[1]
-    data = _load_toml(repo_root / "pyproject.toml")
-    deps = data["project"]["dependencies"]
-    normalized_names = {
-        d.split(";")[0].split(">=")[0].split("<")[0].split("==")[0].strip()
-        for d in deps
-    }
-    expected_22 = {
-        "numpy",
-        "pandas",
-        "scipy",
-        "scikit-learn",
-        "rdflib",
-        "networkx",
-        "requests",
-        "chardet",
-        "protobuf",
-        "grpcio",
-        "pillow",
-        "pydantic",
-        "click",
-        "rich",
-        "tqdm",
-        "pyyaml",
-        "toml",
-        "python-dotenv",
-        "loguru",
-        "structlog",
-        "httpx",
-        "pyarrow",
-    }
-    assert normalized_names == expected_22
-    assert len(normalized_names) == 22
-
-
-def test_optional_extras_defined():
-    """All required optional extras must be declared in pyproject.toml."""
-    repo_root = Path(__file__).resolve().parents[1]
-    data = _load_toml(repo_root / "pyproject.toml")
-    extras = data["project"]["optional-dependencies"]
-    for extra in [
-        "documents",
-        "ingest-git",
-        "embeddings-local",
-        "nlp-spacy",
-        "viz",
-        "media",
-        "vectorstore-faiss",
-        "graph-embeddings",
-        "all",
-    ]:
-        assert extra in extras, f"Missing extra {extra}"
-    all_extra_str = str(extras["all"])
-    for expected_ref in [
-        "documents",
-        "ingest-git",
-        "embeddings-local",
-        "nlp-spacy",
-        "viz",
-        "media",
-        "graph-embeddings",
-        "vectorstore-all",
-    ]:
-        assert expected_ref in all_extra_str, f"Missing {expected_ref} in all"
-    # And vectorstore-faiss is in vectorstore-all
-    assert "vectorstore-faiss" in str(extras["vectorstore-all"])
-
-    # Verify nlp-spacy does not declare thinc directly (Qodo bot issue 1)
-    nlp_spacy_deps = str(extras.get("nlp-spacy", []))
-    assert "thinc" not in nlp_spacy_deps, "nlp-spacy should not directly declare thinc"
-    assert "spacy" in nlp_spacy_deps, "nlp-spacy must declare spacy"
-
-
-def test_core_modules_importable():
-    """Core modules must be importable without requiring optional extras."""
-    import semantica
-    import semantica.cli
-    import semantica.parse
-    import semantica.ingest
-    import semantica.embeddings
-    import semantica.export
-    import semantica.kg
-    import semantica.vector_store
-    import semantica.visualization
-    import semantica.semantic_extract
-    import semantica.pipeline
-
-    assert semantica.__version__ is not None
-
-
-def test_docx_parser_lazy_construction_and_parse_hint():
-    with patch("semantica.parse.docx_parser.Document", None):
-        parser = DOCXParser()
-        assert parser is not None
-        with pytest.raises(ProcessingError, match=r"semantica\[documents\]"):
-            parser.parse("nonexistent.docx")
-
-
-def test_excel_parser_lazy_construction_and_parse_hint():
-    with patch("semantica.parse.excel_parser.load_workbook", None):
-        parser = ExcelParser()
-        assert parser is not None
-        with pytest.raises(ProcessingError, match=r"semantica\[documents\]"):
-            parser.parse("nonexistent.xlsx")
-
-
-def test_html_parser_lazy_construction_and_parse_hint():
-    with patch("semantica.parse.html_parser.BeautifulSoup", None):
-        parser = HTMLParser()
-        assert parser is not None
-        with pytest.raises(ProcessingError, match=r"semantica\[documents\]"):
-            parser.parse("nonexistent.html")
-
-
-def test_xml_parser_etree_fallback():
-    with patch("semantica.parse.xml_parser.etree", None):
-        parser = XMLParser()
-        assert parser is not None
-        result = parser.parse("<root><item id='1'>Test</item></root>")
-        assert result is not None
-        assert result.root is not None
-        assert result.root.tag == "root"
-
-
-def test_xml_parser_lxml_explicit_requires_documents_extra():
-    with patch("semantica.parse.xml_parser.etree", None):
-        parser = XMLParser(engine="lxml")
-        assert parser is not None
-        with pytest.raises(ProcessingError, match=r"semantica\[documents\]"):
-            parser.parse("<root/>")
-
-
-def test_xml_ingestor_missing_hint():
-    with patch("semantica.ingest.xml_ingestor.etree", None):
-        from semantica.ingest.xml_ingestor import XMLIngestor
-
-        with pytest.raises(ImportError, match=r"semantica\[documents\]"):
-            XMLIngestor()
-
-
-def test_xml_ingestor_package_import_missing_hint():
-    import semantica.ingest as ingest_mod
-
-    ingest_mod.__dict__.pop("XMLIngestor", None)
-    with patch("semantica.ingest.xml_ingestor.etree", None):
-        with pytest.raises(ImportError, match=r"semantica\[documents\]"):
-            _ = ingest_mod.XMLIngestor
-
-
-def test_repo_ingestor_missing_hint():
-    with patch("semantica.ingest.repo_ingestor.git", None):
-        from semantica.ingest.repo_ingestor import RepoIngestor
-
-        with pytest.raises(ImportError, match=r"semantica\[ingest-git\]"):
-            RepoIngestor()
-
-
-def test_repo_ingestor_package_import_missing_hint():
-    import semantica.ingest as ingest_mod
-
-    ingest_mod.__dict__.pop("RepoIngestor", None)
-    with patch("semantica.ingest.repo_ingestor.git", None):
-        with pytest.raises(ImportError, match=r"semantica\[ingest-git\]"):
-            _ = ingest_mod.RepoIngestor
-
-
-def test_git_analyzer_package_import_succeeds_without_git():
-    import semantica.ingest as ingest_mod
-
-    ingest_mod.__dict__.pop("GitAnalyzer", None)
-    with patch("semantica.ingest.repo_ingestor.git", None):
-        analyzer_cls = ingest_mod.GitAnalyzer
-        assert analyzer_cls is not None
-        analyzer = analyzer_cls()
-        assert analyzer is not None
-
-
-def test_salesforce_ingestor_package_import_missing_hint():
-    import semantica.ingest as ingest_mod
-
-    ingest_mod.__dict__.pop("SalesforceIngestor", None)
-    with patch("semantica.ingest.salesforce_ingestor.SALESFORCE_AVAILABLE", False):
-        with pytest.raises(ImportError, match=r"semantica\[db-salesforce\]"):
-            _ = ingest_mod.SalesforceIngestor
-
-
-def test_parse_methods_dynamic_default_resolution():
-    from semantica.parse.methods import (
-        get_parse_method,
-        list_available_methods,
-        parse_document,
-    )
-
-    assert get_parse_method("document", "default") == parse_document
-    methods = list_available_methods()
-    assert "default" in methods.get("document", [])
-    assert "default" in methods.get("structured", [])
-
-
-def test_node_embedder_gensim_missing_hint():
-    with patch("semantica.kg.node_embeddings.GENSIM_AVAILABLE", False):
-        from semantica.kg.node_embeddings import NodeEmbedder
-
-        with pytest.raises(ImportError, match=r"semantica\[graph-embeddings\]"):
-            NodeEmbedder()
-
-
-def test_faiss_store_missing_hint():
-    with patch("semantica.vector_store.faiss_store.FAISS_AVAILABLE", False):
-        from semantica.vector_store.faiss_store import FAISSIndexBuilder, FAISSStore
-
-        builder = FAISSIndexBuilder(128)
-        with pytest.raises(ProcessingError, match=r"semantica\[vectorstore-faiss\]"):
-            builder.build_index("flat")
-        store = FAISSStore(128)
-        with pytest.raises(ProcessingError, match=r"semantica\[vectorstore-faiss\]"):
-            store.load_index("nonexistent.faiss")
-
-
-def test_visualization_missing_hint():
-    import numpy as np
-    from semantica.visualization.embedding_visualizer import EmbeddingVisualizer
-
-    # Plotly is checked via px and go in _check_dependencies
-    with patch("semantica.visualization.embedding_visualizer.px", None):
-        visualizer = EmbeddingVisualizer()
-        with pytest.raises(
-            ProcessingError, match=r"Plotly is required.*semantica\[viz\]"
-        ):
-            visualizer.visualize_2d_projection(np.array([[0.1, 0.2], [0.3, 0.4]]))
-
-    with patch("semantica.visualization.embedding_visualizer.go", None):
-        visualizer = EmbeddingVisualizer()
-        with pytest.raises(
-            ProcessingError, match=r"Plotly is required.*semantica\[viz\]"
-        ):
-            visualizer.visualize_2d_projection(np.array([[0.1, 0.2], [0.3, 0.4]]))
-
-
-def test_visualization_umap_missing_hint():
-    import numpy as np
-    from unittest.mock import MagicMock
-    from semantica.visualization.embedding_visualizer import EmbeddingVisualizer
-
-    # Stand in for Plotly so we reach dimensionality reduction
-    with patch("semantica.visualization.embedding_visualizer.px", MagicMock()), patch(
-        "semantica.visualization.embedding_visualizer.go", MagicMock()
-    ), patch("semantica.visualization.embedding_visualizer.umap", None):
-        visualizer = EmbeddingVisualizer()
-        # High-dimensional embeddings (>2D) trigger dimensionality reduction
-        # with method="umap"
-        embeddings = np.array([[0.1, 0.2, 0.3], [0.4, 0.5, 0.6], [0.7, 0.8, 0.9]])
-        with pytest.raises(
-            ProcessingError, match=r"UMAP is required.*semantica\[viz\]"
-        ):
-            visualizer.visualize_2d_projection(embeddings, method="umap")
-
-        # Also verify 3D projection triggers the same actionable error on >3D embeddings
-        embeddings_4d = np.array(
-            [[0.1, 0.2, 0.3, 0.4], [0.5, 0.6, 0.7, 0.8], [0.9, 1.0, 1.1, 1.2]]
-        )
-        with pytest.raises(
-            ProcessingError, match=r"UMAP is required.*semantica\[viz\]"
-        ):
-            visualizer.visualize_3d_projection(embeddings_4d, method="umap")
-
-
-def test_visualization_sklearn_missing_hint():
-    import numpy as np
-    from unittest.mock import MagicMock
-    from semantica.visualization.embedding_visualizer import EmbeddingVisualizer
-
-    # Stand in for Plotly so we reach dimensionality reduction
-    with patch("semantica.visualization.embedding_visualizer.px", MagicMock()), patch(
-        "semantica.visualization.embedding_visualizer.go", MagicMock()
-    ):
-        visualizer = EmbeddingVisualizer()
-        embeddings = np.array([[0.1, 0.2, 0.3], [0.4, 0.5, 0.6], [0.7, 0.8, 0.9]])
-
-        # Test direct dependency check
-        with patch("semantica.visualization.embedding_visualizer.PCA", None):
-            with pytest.raises(ProcessingError, match=r"scikit-learn is required"):
-                visualizer._check_dependencies(require_sklearn=True)
-
-        with patch("semantica.visualization.embedding_visualizer.PCA", None):
-            with pytest.raises(ProcessingError, match=r"scikit-learn is required"):
-                visualizer.visualize_2d_projection(embeddings, method="pca")
-
-        with patch("semantica.visualization.embedding_visualizer.TSNE", None):
-            with pytest.raises(ProcessingError, match=r"scikit-learn is required"):
-                visualizer.visualize_2d_projection(embeddings, method="tsne")
-
-
-def test_visualization_options_collision_free():
-    """Options like n_components, perplexity must not cause keyword collisions."""
-    import numpy as np
-    from unittest.mock import MagicMock
-    from semantica.visualization.embedding_visualizer import EmbeddingVisualizer
-
-    mock_pca = MagicMock()
-    mock_tsne = MagicMock()
-    mock_umap_cls = MagicMock()
-    mock_umap_module = MagicMock()
-    mock_umap_module.UMAP = mock_umap_cls
-
-    with patch("semantica.visualization.embedding_visualizer.PCA", mock_pca), patch(
-        "semantica.visualization.embedding_visualizer.TSNE", mock_tsne
-    ), patch(
-        "semantica.visualization.embedding_visualizer.umap", mock_umap_module
-    ), patch(
-        "semantica.visualization.embedding_visualizer.px", MagicMock()
-    ), patch(
-        "semantica.visualization.embedding_visualizer.go", MagicMock()
-    ):
-        visualizer = EmbeddingVisualizer()
-        embeddings = np.array([[0.1, 0.2, 0.3], [0.4, 0.5, 0.6], [0.7, 0.8, 0.9]])
-
-        # PCA with n_components
-        visualizer.visualize_2d_projection(embeddings, method="pca", n_components=2)
-        # TSNE with perplexity and random_state
-        visualizer.visualize_2d_projection(
-            embeddings, method="tsne", perplexity=1, random_state=42
-        )
-        # UMAP with n_neighbors and min_dist
-        visualizer.visualize_2d_projection(
-            embeddings, method="umap", n_neighbors=2, min_dist=0.1
-        )
-        # 3D with n_components
-        visualizer.visualize_3d_projection(embeddings, method="pca", n_components=3)
-
-
-def test_spacy_load_missing_hint():
-    from semantica.semantic_extract.methods import load_spacy_model
-
-    with patch("semantica.semantic_extract.methods.spacy", None):
-        with pytest.raises(ImportError, match=r"semantica\[nlp-spacy\]"):
-            load_spacy_model("en_core_web_sm")
-
-
-def test_xml_parser_handles_comments():
-    xml_content = (
-        "<root><!-- top comment --><item id='1'>Value</item>"
-        "<!-- bottom comment --></root>"
-    )
-    # lxml engine
-    p_lxml = XMLParser(engine="lxml")
-    res_lxml = p_lxml.parse(xml_content)
-    assert res_lxml.root.tag == "root"
-    assert len(res_lxml.root.children) == 1
-    assert res_lxml.root.children[0].tag == "item"
-    assert res_lxml.root.children[0].text == "Value"
-
-    # etree engine
-    p_etree = XMLParser(engine="etree")
-    res_etree = p_etree.parse(xml_content)
-    assert res_etree.root.tag == "root"
-    assert len(res_etree.root.children) == 1
-    assert res_etree.root.children[0].tag == "item"
-    assert res_etree.root.children[0].text == "Value"
-
-
-def test_public_api_ingestor_handles_xml_comments():
-    from semantica.ingest.public_api_ingestor import PublicAPIIngestor
-
-    xml_content = "<root><!-- comment --><item id='1'>Value</item></root>"
-    ingestor = PublicAPIIngestor(rate_limit_delay=0)
-
-    # 1. Default (defusedxml if available)
-    parsed = ingestor._parse_xml(xml_content)
-    assert parsed["tag"] == "root"
-    assert len(parsed["children"]) == 1
-    assert parsed["children"][0]["tag"] == "item"
-    assert parsed["children"][0]["text"] == "Value"
-
-    # 2. lxml fallback
-    with patch("semantica.ingest.public_api_ingestor.safe_xml_etree", None):
-        parsed_lxml = ingestor._parse_xml(xml_content)
-        assert parsed_lxml["tag"] == "root"
-        assert len(parsed_lxml["children"]) == 1
-        assert parsed_lxml["children"][0]["tag"] == "item"
-        assert parsed_lxml["children"][0]["text"] == "Value"
-
-
-def test_huggingface_model_loader_catches_oserror():
-    import builtins
-    from unittest.mock import MagicMock
-    from semantica.semantic_extract.providers import HuggingFaceModelLoader
-
-    mock_torch = MagicMock()
-    mock_torch.Tensor = type("Tensor", (), {})
-    with patch.dict("sys.modules", {"torch": mock_torch}):
-        loader = HuggingFaceModelLoader()
-        # 1. Test ModuleNotFoundError / ImportError
-        with patch.dict("sys.modules", {"transformers": None}):
-            with pytest.raises(ImportError, match=r"semantica\[models-huggingface\]"):
-                loader.load_ner_model("bert-base-cased")
-
-            with pytest.raises(ImportError, match=r"semantica\[models-huggingface\]"):
-                loader.load_relation_model("bert-base-cased")
-
-            with pytest.raises(ImportError, match=r"semantica\[models-huggingface\]"):
-                loader.load_triplet_model("t5-base")
-
-        # 2. Test OSError (e.g. corrupt DLL / missing shared library)
-        real_import = builtins.__import__
-
-        def fake_import(name, *args, **kwargs):
-            if name == "transformers":
-                raise OSError("DLL load failed")
-            return real_import(name, *args, **kwargs)
-
-        try:
-            builtins.__import__ = fake_import
-            with pytest.raises(ImportError, match=r"semantica\[models-huggingface\]"):
-                loader.load_ner_model("bert-base-cased-oserror")
-
-            with pytest.raises(ImportError, match=r"semantica\[models-huggingface\]"):
-                loader.load_relation_model("bert-base-cased-oserror")
-
-            with pytest.raises(ImportError, match=r"semantica\[models-huggingface\]"):
-                loader.load_triplet_model("t5-base-oserror")
-        finally:
-            builtins.__import__ = real_import

tests/vector_store/test_qdrant_collection_search.py

@@ -0,0 +1,377 @@
+"""Tests for QdrantCollection.search_points and QdrantStore.get_stats.
+
+These cover the qdrant-client >=1.16.0 compatibility fixes:
+
+1. search_points() must call client.query_points() (not the removed .search()),
+   read ScoredPoints from response.points, and map them to the documented
+   Semantica result shape.
+
+2. get_stats() must not access vectors_count unconditionally; when the field
+   is absent (qdrant-client >=1.16), it falls back to points_count for
+   single-vector collections, and to None for named/multi-vector collections
+   where the per-point vector count is unknown.
+
+All tests drive the real implementation against a MagicMock client, following
+the established pattern in test_qdrant_store.py.
+"""
+
+from unittest.mock import MagicMock, patch
+
+import numpy as np
+import pytest
+
+from semantica.utils.exceptions import ProcessingError
+from semantica.vector_store.qdrant_store import QdrantCollection, QdrantStore
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _scored_point(point_id, score, payload=None):
+    """Build a stand-in for a qdrant_client ScoredPoint."""
+    sp = MagicMock()
+    sp.id = point_id
+    sp.score = score
+    sp.payload = payload
+    return sp
+
+
+def _query_response(*scored_points):
+    """Build a stand-in for a qdrant_client QueryResponse."""
+    qr = MagicMock()
+    qr.points = list(scored_points)
+    return qr
+
+
+def _collection_with_query_response(*scored_points):
+    """QdrantCollection whose client.query_points() returns the given points."""
+    client = MagicMock()
+    client.query_points.return_value = _query_response(*scored_points)
+    return QdrantCollection(client, "test_collection")
+
+
+# ---------------------------------------------------------------------------
+# QdrantCollection.search_points — API call
+# ---------------------------------------------------------------------------
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_calls_query_points_not_search():
+    """search_points() must call .query_points(), NOT the removed .search()."""
+    collection = _collection_with_query_response()
+    query = np.array([0.1, 0.2, 0.3, 0.4])
+
+    collection.search_points(query, limit=5)
+
+    collection.client.query_points.assert_called_once()
+    collection.client.search.assert_not_called()
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_passes_correct_arguments():
+    """query_points() must receive collection_name, query list, limit, and payload flag."""
+    collection = _collection_with_query_response()
+    query = np.array([0.1, 0.2, 0.3, 0.4])
+
+    collection.search_points(query, limit=7)
+
+    _, kwargs = collection.client.query_points.call_args
+    assert kwargs["collection_name"] == "test_collection"
+    assert kwargs["query"] == [0.1, 0.2, 0.3, 0.4]
+    assert kwargs["limit"] == 7
+    assert kwargs["with_payload"] is True
+    assert kwargs["with_vectors"] is False
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_passes_query_filter_through():
+    """The query_filter argument must be forwarded verbatim to query_points()."""
+    collection = _collection_with_query_response()
+    mock_filter = MagicMock()
+    query = np.array([0.5, 0.6])
+
+    collection.search_points(query, limit=3, query_filter=mock_filter)
+
+    _, kwargs = collection.client.query_points.call_args
+    assert kwargs["query_filter"] is mock_filter
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_passes_none_filter_when_unfiltered():
+    """query_filter=None must be passed through (not omitted) so the server
+    returns all matching vectors rather than raising a missing-argument error."""
+    collection = _collection_with_query_response()
+    query = np.array([0.1, 0.2])
+
+    collection.search_points(query, limit=5, query_filter=None)
+
+    _, kwargs = collection.client.query_points.call_args
+    assert kwargs["query_filter"] is None
+
+
+# ---------------------------------------------------------------------------
+# QdrantCollection.search_points — result shape
+# ---------------------------------------------------------------------------
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_result_shape():
+    """Each result dict must contain id, score, metadata, vector, distance."""
+    sp = _scored_point(42, 0.8, payload={"tag": "ml"})
+    collection = _collection_with_query_response(sp)
+    query = np.array([0.1, 0.2, 0.3])
+
+    results = collection.search_points(query, limit=1)
+
+    assert len(results) == 1
+    r = results[0]
+    assert set(r.keys()) == {"id", "score", "metadata", "vector", "distance"}
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_maps_id_and_payload():
+    """id and metadata must come from ScoredPoint.id and ScoredPoint.payload."""
+    sp = _scored_point(99, 0.5, payload={"source": "wiki", "year": 2024})
+    collection = _collection_with_query_response(sp)
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=1)
+
+    assert results[0]["id"] == 99
+    assert results[0]["metadata"] == {"source": "wiki", "year": 2024}
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_null_payload_becomes_empty_dict():
+    """A ScoredPoint with payload=None must produce metadata={}."""
+    sp = _scored_point(7, 0.9, payload=None)
+    collection = _collection_with_query_response(sp)
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=1)
+
+    assert results[0]["metadata"] == {}
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_vector_and_distance_are_none():
+    """vector and distance fields must always be None (vectors are not fetched)."""
+    sp = _scored_point(1, 0.7, payload={})
+    collection = _collection_with_query_response(sp)
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=1)
+
+    assert results[0]["vector"] is None
+    assert results[0]["distance"] is None
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_score_normalization_midrange():
+    """Score=0 must map to exactly 0.5 under the normalization formula."""
+    sp = _scored_point(1, 0.0)
+    collection = _collection_with_query_response(sp)
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=1)
+
+    assert results[0]["score"] == pytest.approx(0.5)
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_score_normalization_positive():
+    """Positive raw scores must map to (0.5, 1.0) under the normalization formula."""
+    sp = _scored_point(1, 1.0)
+    collection = _collection_with_query_response(sp)
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=1)
+
+    # (1.0/(1+1.0) + 1.0) / 2.0 = (0.5 + 1.0) / 2.0 = 0.75
+    assert results[0]["score"] == pytest.approx(0.75)
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_score_normalization_negative():
+    """Negative raw scores must map to (0.0, 0.5) under the normalization formula."""
+    sp = _scored_point(1, -1.0)
+    collection = _collection_with_query_response(sp)
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=1)
+
+    # (-1.0/(1+1.0) + 1.0) / 2.0 = (−0.5 + 1.0) / 2.0 = 0.25
+    assert results[0]["score"] == pytest.approx(0.25)
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_multiple_results_preserve_order():
+    """All ScoredPoints in response.points must appear in the output, in order."""
+    points = [_scored_point(i, 1.0 - i * 0.1) for i in range(5)]
+    collection = _collection_with_query_response(*points)
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=5)
+
+    assert len(results) == 5
+    assert [r["id"] for r in results] == [0, 1, 2, 3, 4]
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_empty_response():
+    """An empty response.points list must produce an empty result list."""
+    collection = _collection_with_query_response()  # zero points
+
+    results = collection.search_points(np.array([0.1, 0.2]), limit=10)
+
+    assert results == []
+
+
+# ---------------------------------------------------------------------------
+# QdrantCollection.search_points — error handling
+# ---------------------------------------------------------------------------
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", False)
+def test_search_points_raises_when_qdrant_unavailable():
+    client = MagicMock()
+    collection = QdrantCollection(client, "test_collection")
+
+    with pytest.raises(ProcessingError):
+        collection.search_points(np.array([0.1, 0.2]), limit=5)
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_search_points_wraps_client_errors_as_processing_error():
+    client = MagicMock()
+    client.query_points.side_effect = RuntimeError("network failure")
+    collection = QdrantCollection(client, "test_collection")
+
+    with pytest.raises(ProcessingError, match="network failure"):
+        collection.search_points(np.array([0.1, 0.2]), limit=5)
+
+
+# ---------------------------------------------------------------------------
+# QdrantStore.get_stats — vectors_count compatibility
+# ---------------------------------------------------------------------------
+
+def _store_with_collection_info(**info_attrs):
+    """QdrantStore with a mocked client.get_collection() response."""
+    store = QdrantStore()
+    store.client = MagicMock()
+    store.collection = MagicMock()
+    store.collection.collection_name = "test_coll"
+
+    info = MagicMock(spec=list(info_attrs.keys()))
+    for attr, val in info_attrs.items():
+        setattr(info, attr, val)
+    store.client.get_collection.return_value = info
+    return store
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_get_stats_uses_vectors_count_when_present():
+    """On qdrant-client <1.16, vectors_count exists and must be returned."""
+    store = _store_with_collection_info(
+        points_count=10, vectors_count=10, status="green"
+    )
+
+    stats = store.get_stats()
+
+    assert stats["points_count"] == 10
+    assert stats["vectors_count"] == 10
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_get_stats_uses_points_count_when_vectors_count_absent():
+    """On qdrant-client >=1.16, vectors_count is absent.
+    For a single unnamed-vector collection (config.params.vectors is a
+    VectorParams instance), points_count is the correct substitute.
+    indexed_vectors_count must NOT be used: it counts only vectors
+    in optimised segments and is 0 for freshly-inserted data."""
+    from qdrant_client.models import VectorParams, Distance
+    store = QdrantStore()
+    store.client = MagicMock()
+    store.collection = MagicMock()
+    store.collection.collection_name = "test_coll"
+
+    info = MagicMock(spec=["points_count", "indexed_vectors_count", "config", "status"])
+    info.points_count = 5
+    info.indexed_vectors_count = 0  # typical for freshly-inserted, unoptimised data
+    info.config.params.vectors = VectorParams(size=4, distance=Distance.COSINE)
+    info.status = "green"
+    store.client.get_collection.return_value = info
+
+    stats = store.get_stats()
+
+    assert stats["points_count"] == 5
+    # Must equal points_count (5), NOT indexed_vectors_count (0)
+    assert stats["vectors_count"] == 5
+    assert stats["vectors_count"] != info.indexed_vectors_count
+    assert stats["status"] == "green"
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_get_stats_vectors_count_equals_points_count_when_vectors_count_absent():
+    """On qdrant-client >=1.16, vectors_count is absent.  For a single unnamed-
+    vector collection the fallback is points_count, so both keys are equal.
+    indexed_vectors_count is intentionally absent from this mock to confirm
+    it is not required by the fallback path."""
+    from qdrant_client.models import VectorParams, Distance
+    store = QdrantStore()
+    store.client = MagicMock()
+    store.collection = MagicMock()
+    store.collection.collection_name = "test_coll"
+
+    info = MagicMock(spec=["points_count", "config", "status"])
+    info.points_count = 7
+    info.config.params.vectors = VectorParams(size=8, distance=Distance.COSINE)
+    info.status = "green"
+    store.client.get_collection.return_value = info
+
+    stats = store.get_stats()
+
+    assert stats["points_count"] == 7
+    assert stats["vectors_count"] == 7
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_get_stats_vectors_count_is_none_for_named_multi_vector_collection():
+    """When vectors_count is absent and the collection uses named/multi vectors
+    (config.params.vectors is a dict), the total cannot be inferred and
+    vectors_count must be None rather than a misleading points_count value."""
+    from qdrant_client.models import VectorParams, Distance
+    store = QdrantStore()
+    store.client = MagicMock()
+    store.collection = MagicMock()
+    store.collection.collection_name = "test_coll"
+
+    info = MagicMock(spec=["points_count", "config", "status"])
+    info.points_count = 4
+    # Named multi-vector: qdrant-client returns a dict of VectorParams
+    info.config.params.vectors = {
+        "text": VectorParams(size=4, distance=Distance.COSINE),
+        "image": VectorParams(size=8, distance=Distance.DOT),
+    }
+    info.status = "green"
+    store.client.get_collection.return_value = info
+
+    stats = store.get_stats()
+
+    assert stats["points_count"] == 4
+    # vectors_count must be None: total vectors = points * num_named_vectors,
+    # and that multiplier is unknown to the caller.
+    assert stats["vectors_count"] is None
+
+
+@patch("semantica.vector_store.qdrant_store.QDRANT_AVAILABLE", True)
+def test_get_stats_vectors_count_is_none_when_config_inaccessible():
+    """If the collection config cannot be read (e.g. an older schema or
+    unexpected server response), vectors_count must fall back to None safely
+    without raising."""
+    store = QdrantStore()
+    store.client = MagicMock()
+    store.collection = MagicMock()
+    store.collection.collection_name = "test_coll"
+
+    # Simulate a CollectionInfo that has no config attribute at all
+    info = MagicMock(spec=["points_count", "status"])
+    info.points_count = 3
+    info.status = "green"
+    store.client.get_collection.return_value = info
+
+    stats = store.get_stats()
+
+    assert stats["points_count"] == 3
+    assert stats["vectors_count"] is None

tests/visualization/test_optional_dependencies.py

@@ -38,13 +38,14 @@ class TestOptionalDependencies(unittest.TestCase):
         with import_without(
             "semantica.visualization.embedding_visualizer", "umap"
         ) as module:
-            with plotly_doubles(module):
+            with plotly_doubles(module), patch.object(module, "PCA") as mock_pca_class:
+                mock_pca_class.return_value.fit_transform.return_value = np.zeros((4, 2))
+
                 viz = module.EmbeddingVisualizer()
                 embeddings = np.array([[0, 1, 2], [1, 0, 3], [0, 0, 0], [1, 1, 1]])
-                with self.assertRaises(module.ProcessingError) as cm:
-                    viz.visualize_2d_projection(embeddings, method="umap")
-                self.assertIn("UMAP is required", str(cm.exception))
-                self.assertIn("semantica[viz]", str(cm.exception))
+                viz.visualize_2d_projection(embeddings, method="umap")
+
+            mock_pca_class.assert_called()
 
     def test_ontology_visualizer_without_graphviz(self):
         """Test OntologyVisualizer behavior when graphviz is missing."""