llama-stack-mirror/tests/unit/providers/vector_io
skamenan7 a14f79a362 fix(vector-io): handle missing document_id in insert_chunks
Fixed KeyError when chunks don't have document_id in metadata or chunk_metadata.
Updated logging to safely extract document_id using getattr and RAG memory
to handle different document_id locations. Added test for missing document_id scenarios.

Fixes issue #3494 where /v1/vector-io/insert would crash with KeyError.
2025-09-25 13:59:10 -04:00
..
remote feat: implement keyword, vector and hybrid search inside vector stores for PGVector provider (#3064) 2025-08-29 16:30:12 +02:00
conftest.py feat: implement keyword, vector and hybrid search inside vector stores for PGVector provider (#3064) 2025-08-29 16:30:12 +02:00
test_faiss.py chore: default to pytest asyncio-mode=auto (#2730) 2025-07-11 13:00:24 -07:00
test_qdrant.py fix: Fix mock vector DB schema in Qdrant tests (#3295) 2025-09-03 09:59:16 +02:00
test_sqlite_vec.py fix: SQLiteVecIndex.create(..., bank_id="test_bank.123") - bank_id with a dot - leads to sqlite3.OperationalError (#2770) (#2771) 2025-07-16 08:25:44 -07:00
test_vector_io_openai_vector_stores.py fix(vector-io): handle missing document_id in insert_chunks 2025-09-25 13:59:10 -04:00
test_vector_utils.py feat: migrate to FIPS-validated cryptographic algorithms (#3423) 2025-09-12 11:18:19 +02:00