Alex 63d93fc4b9 test(graphrag): pin that identical pages collapse into one ...

Review asked whether two document rows with the same text and metadata should
stay two pages. They should not: the caller gets four pages to hand a model,
and a crawl that ingested the same text twice would spend two of them on it.
The rows differ only by an id the model never sees. Pinned either way now.

2026-09-20 10:54:55 +01:00

..

__init__.py

feat(graphrag): config.graph sub-model + settings + pgvector availability gate

2026-06-23 00:39:27 +01:00

test_extraction.py

fix(graphrag): drop entities whose name normalizes to nothing

2026-09-20 10:45:05 +01:00

test_graph_search_tool.py

test(agents): give the graph tool tests the vector store they need

2026-09-20 10:54:55 +01:00

test_graphrag_available.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

test_naming.py

fix(graphrag): fold an entity's singular and plural onto one key

2026-09-19 14:33:14 +01:00

test_retriever_default_path.py

test(graphrag): cover the graph reads, graph tool and vector blend without pgvector

2026-09-19 14:33:14 +01:00

test_retriever_live.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

test_retriever_passages.py

fix(retriever): search a graph source classically when its graph answers nothing

2026-09-20 10:45:03 +01:00

test_retriever_seeding.py

feat(graphrag): seed the walk from what entities are, and rank with passages and vector hits

2026-09-19 14:07:41 +01:00

test_store.py

test(graphrag): pin that identical pages collapse into one

2026-09-20 10:54:55 +01:00