99797a183b
Add unit tests for normalize_facts covering all LLM fact shapes
...
Tests plain strings, {"fact": ...}, {"text": ...}, mixed lists,
and empty string filtering.
2026-03-05 12:19:40 -05:00
b3ec0978d3
Add reproduction test for infer=true AttributeError on malformed LLM facts
...
When smaller LLMs return facts as objects ({"fact": "..."}) instead of
plain strings, embedding_model.embed() crashes with
'dict' object has no attribute 'replace'. This test confirms the bug
by mocking the LLM to return dict-shaped facts and asserting the
failure at mem0/memory/main.py:473.
2026-03-05 11:41:30 -05:00
84687fc3d2
[fix] list' object has no attribute 'id' - Id fault with chroma pinecone and other providers ( #3693 )
2025-10-31 16:46:10 +05:30
9000576173
fix: handle non-serializable objects in config deepcopy ( #3464 ) ( #3544 )
2025-10-09 19:35:08 +05:30
58cc44ff38
fix: handle missing 'data' key in memory payload during search operations ( #3524 )
2025-09-30 15:10:43 -07:00
e4c5582808
fix-migration-collection-override ( #3100 )
...
Co-authored-by: parshvadaftari <daftariparshva@gmail.com >
2025-08-21 00:11:28 +05:30
4433666117
Fix failing tests ( #3162 )
2025-07-25 00:58:45 +05:30
55c54beeab
[Misc] Lint code and fix code smells ( #1871 )
2024-09-16 17:39:54 -07:00
28bc4fe05b
Improve: consistency in the test_memory.py ( #1777 )
2024-08-29 11:36:01 -07:00
e585d3c1cc
Skip few tests in Mem0 ( #1625 )
2024-08-01 08:31:57 -07:00
f842a92e25
Rename embedchain to mem0 and open sourcing code for long term memory ( #1474 )
...
Co-authored-by: Deshraj Yadav <deshrajdry@gmail.com >
2024-07-12 20:21:33 +05:30
anishamahuli