kg: graph build, traversal queries, neo4j export - kg_ocr.graph builds a networkx graph (docs, chunks, entities, citations, co-occurrence) from chunk markdown - analyzer for summaries, top entities/citations, anomaly checks - traversal: chunks_for_entity/citation, related_entities, expand_context - export: JSON round-trip, GraphML, batched MERGE into neo4j - new CLI: ocr-pipeline kg build|stats|query|export - lazy kg_ocr imports, networkx/neo4j behind extras - dropped dead watch.py shim, added KgConfig stub - trimmed README, updated TODO

kg_ocr/embeddings/config_loader.py

@@ -1 +1,31 @@
-# in future prefer a config, especially for graph traversal
+"""Config for kg_ocr: graph traversal defaults and Neo4j credentials.
+
+Environment variables: NEO4J_URI, NEO4J_USER, NEO4J_PASSWORD.
+"""
+
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass, field
+
+
+@dataclass(frozen=True)
+class KgConfig:
+    """Tunables for graph building/traversal plus Neo4j connection."""
+
+    # Traversal
+    expand_limit: int = 5
+    related_limit: int = 10
+
+    # Neo4j
+    neo4j_uri: str = "bolt://localhost:7687"
+    neo4j_user: str = "neo4j"
+    neo4j_password: str = field(default="", repr=False)
+
+    @classmethod
+    def from_env(cls) -> KgConfig:
+        return cls(
+            neo4j_uri=os.environ.get("NEO4J_URI", cls.neo4j_uri),
+            neo4j_user=os.environ.get("NEO4J_USER", cls.neo4j_user),
+            neo4j_password=os.environ.get("NEO4J_PASSWORD", ""),
+        )

kg_ocr/embeddings/indexer.py

@@ -1,18 +1,27 @@
-from txtai.embeddings import Embeddings
+from __future__ import annotations
+
+from typing import Any
+
+DEFAULT_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
 
 
-def create_and_index(
-    data: list[str], model: str = "sentence-transformers/all-MiniLM-L6-v2"
-) -> Embeddings:
-    """Create and index embeddings from text."""
-    embeddings = Embeddings({
-        "path": model,
-        "content": True,
-        "hybrid": True,
-        "scoring": "bm25",
-    })
+def create_and_index(data: list[str], model: str = DEFAULT_MODEL) -> Any:
+    """Create and index embeddings from text.
+
+    Requires txtai (uv sync --extra kg). Returns a txtai Embeddings instance.
+    """
+    try:
+        from txtai.embeddings import Embeddings
+    except ImportError as exc:
+        raise ImportError("create_and_index needs txtai: uv sync --extra kg") from exc
+
+    embeddings = Embeddings(
+        {
+            "path": model,
+            "content": True,
+            "hybrid": True,
+            "scoring": "bm25",
+        }
+    )
     embeddings.index(data)
     return embeddings
-
-
-