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/__init__.py

@@ -1,17 +1,50 @@
-"""Experimental txtai/litellm RAG interface built on the OCR pipeline.
+"""Knowledge graph + RAG interface built on the OCR pipeline.
 
-This package is a prototype. The supported interface is the `ocr-pipeline` CLI
-(src/ocr_pipeline). Extra dependencies are required: `uv sync --extra kg`.
+Lightweight submodules (graph, export) import without optional deps.
+The txtai/litellm RAG pieces need: uv sync --extra kg.
 """
 
-try:
-    from .ocr import get_screenshots, extract_text
-    from .embeddings import create_and_index
-    from .rag import retrieve, ask_wllm
-except ImportError as exc:
-    raise ImportError(
-        "kg_ocr is experimental and needs extra dependencies: "
-        "uv sync --extra kg  (or: uv pip install txtai litellm python-dotenv)"
-    ) from exc
+from __future__ import annotations
 
-__all__ = ["get_screenshots", "extract_text", "create_and_index", "retrieve", "ask_wllm"]
+from typing import Any
+
+_LAZY: dict[str, tuple[str, str]] = {
+    "get_screenshots": (".ocr", "get_screenshots"),
+    "extract_text": (".ocr", "extract_text"),
+    "create_and_index": (".embeddings", "create_and_index"),
+    "retrieve": (".rag", "retrieve"),
+    "ask_wllm": (".rag", "ask_wllm"),
+    "build_graph": (".graph", "build_graph"),
+    "build_from_directory": (".graph", "build_from_directory"),
+    "summary": (".graph", "summary"),
+    "top_entities": (".graph", "top_entities"),
+    "detect_anomalies": (".graph", "detect_anomalies"),
+    "chunks_for_entity": (".graph", "chunks_for_entity"),
+    "chunks_for_citation": (".graph", "chunks_for_citation"),
+    "related_entities": (".graph", "related_entities"),
+    "expand_context": (".graph", "expand_context"),
+    "export_json": (".export", "export_json"),
+    "export_graphml": (".export", "export_graphml"),
+    "load_json": (".export", "load_json"),
+    "Neo4jExporter": (".export", "Neo4jExporter"),
+}
+
+__all__ = list(_LAZY)
+
+
+def __getattr__(name: str) -> Any:
+    if name not in _LAZY:
+        raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+    module_name, attr = _LAZY[name]
+    try:
+        from importlib import import_module
+
+        module = import_module(module_name, __name__)
+    except ImportError as exc:
+        raise ImportError(
+            f"kg_ocr.{name} needs optional dependencies: uv sync --extra kg "
+            f"(graph/export only need networkx; embeddings/rag also need txtai, litellm)"
+        ) from exc
+    value = getattr(module, attr)
+    globals()[name] = value
+    return value