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

tests/test_indexer.py

@@ -0,0 +1,54 @@
+from __future__ import annotations
+
+import sys
+import types
+
+import pytest
+
+from kg_ocr.embeddings import create_and_index
+from kg_ocr.rag import retrieve
+
+
+class _FakeEmbeddings:
+    instances: list[_FakeEmbeddings] = []
+
+    def __init__(self, config):
+        self.config = config
+        self.indexed: list[str] | None = None
+        _FakeEmbeddings.instances.append(self)
+
+    def index(self, data):
+        self.indexed = data
+
+
+def _install_fake_txtai(monkeypatch: pytest.MonkeyPatch) -> None:
+    fake_txtai = types.ModuleType("txtai")
+    fake_embeddings_mod = types.ModuleType("txtai.embeddings")
+    fake_embeddings_mod.Embeddings = _FakeEmbeddings  # type: ignore[attr-defined]
+    monkeypatch.setitem(sys.modules, "txtai", fake_txtai)
+    monkeypatch.setitem(sys.modules, "txtai.embeddings", fake_embeddings_mod)
+
+
+def test_create_and_index_config_and_data(monkeypatch: pytest.MonkeyPatch) -> None:
+    _install_fake_txtai(monkeypatch)
+    emb = create_and_index(["alpha", "beta"], model="some-model")
+    assert emb.config["path"] == "some-model"
+    assert emb.config["content"] is True
+    assert emb.config["hybrid"] is True
+    assert emb.indexed == ["alpha", "beta"]
+
+
+def test_create_and_index_raises_without_txtai(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setitem(sys.modules, "txtai", None)
+    monkeypatch.setitem(sys.modules, "txtai.embeddings", None)
+    with pytest.raises(ImportError, match="txtai"):
+        create_and_index(["x"])
+
+
+def test_retrieve_passes_through() -> None:
+    class FakeEmb:
+        def search(self, query, limit):
+            return [{"text": f"{query}-{i}", "score": 1.0} for i in range(limit)]
+
+    out = retrieve(FakeEmb(), "q", limit=2)
+    assert out == [{"text": "q-0", "score": 1.0}, {"text": "q-1", "score": 1.0}]