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/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
-
-
-