Commit Graph

427 Commits

Author SHA1 Message Date
Yash Raj Pandey 7c841a2bce fix(redis): do not crash on empty or None filters in search and list (#5446)
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-16 16:10:57 +05:30
Bartok 94bbc13de0 fix(memory): skip messages without a content key in message parsers (#5575) 2026-06-16 15:29:53 +05:30
Hrushikesh Yadav a2f01a8fcc fix: async delete_all aborts on first error, leaving partial deletion (#5529) 2026-06-16 11:59:33 +05:30
Hrushikesh Yadav 30d172e826 fix: omit None config values from Gemini GenerateContentConfig (#5528) 2026-06-16 11:54:42 +05:30
ly-wang19 bb69b036b5 fix(vector_stores): return None from get() for missing IDs (milvus/weaviate/supabase) (#5562)
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
2026-06-16 11:52:59 +05:30
Hrushikesh Yadav 4d949022f2 fix: preserve custom metadata fields during memory update (#5480) 2026-06-15 16:29:44 +05:30
ly-wang19 3ef034a9e4 fix(vector_stores): return None from ChromaDB.get() for missing IDs (#5561)
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
2026-06-15 16:11:03 +05:30
Yash Singh b90e3c0b76 fix(reranker): respect config.top_k in Cohere and ZeroEntropy fallback paths (#5560) 2026-06-15 16:10:00 +05:30
ly-wang19 a8eeddde64 fix(llms): honor reasoning-model params in AzureOpenAIStructuredLLM (#5548)
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
2026-06-15 16:07:19 +05:30
Hrushikesh Yadav 09a9e34382 fix(litellm): function-calling check blocks all calls on non-tool models (#5536) 2026-06-15 15:59:46 +05:30
ly-wang19 32575a65fc fix(llms): honor reasoning-model params in OpenAIStructuredLLM (#5458)
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-15 12:36:15 +05:30
Yash Singh 66901d7393 fix(llms): accept and forward **kwargs in Together/LangChain/Sarvam providers (#5556) 2026-06-15 12:23:04 +05:30
Hrushikesh Yadav a1eefc31bc fix(bedrock): use dict literal instead of set in AI21 response parse default (#5527) 2026-06-15 12:09:34 +05:30
Davide Leopardi de471799d1 fix(llms): send max_completion_tokens for the GPT-5 family across providers (#5547) 2026-06-15 12:04:19 +05:30
youneshima 3553fc79dd feat(memory): add OSS-to-Platform notices (#5494) 2026-06-13 18:34:20 +05:30
Kartik 06d33f6cc4 fix: relax flaky entity boost parallelism timing threshold (#5511) 2026-06-12 21:07:47 +05:30
Hrushikesh Yadav 8f3b60f3e1 fix: prevent crash in parse_vision_messages when vision is disabled (#5487) 2026-06-12 20:41:18 +05:30
Yufeng He 4f10c986b5 fix: expose Qdrant https option (#5380) 2026-06-12 20:06:26 +05:30
Hrushikesh Yadav ced852033b fix: return 400 instead of 502 for invalid search filters (#5482) 2026-06-12 19:35:24 +05:30
Yufeng He e3f5ce7b41 fix: use valid S3 entity index names (#5416)
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai>
2026-06-12 19:22:32 +05:30
Oleg Ovcharuk b36847622d fix(langchain): search() crashes with TypeError when score is None (#5072)
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai>
2026-06-11 22:34:06 +05:30
Hrushikesh Yadav 2dd2872c08 fix: use 'is not None' instead of truthiness for vector/payload in pgvector update (#5488) 2026-06-11 22:12:38 +05:30
Eldar Shlomi 4c41f6deeb fix(vector-stores): index Valkey 'memory' field as TEXT not TAG (#5443)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-11 21:28:42 +05:30
Hrushikesh Yadav f84aa1eb31 fix: implement $not filter support in ChromaDB vector store (#5485) 2026-06-11 20:12:39 +05:30
shafdev b819d95d18 fix(pgvector): use open=False to prevent ConnectionPool hang in Docker (#5155)
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-10 17:15:53 +05:30
Sense_wang 3ac1c9452c fix(vector-stores): filter S3 vector list results (#5018)
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-10 16:55:31 +05:30
Gaurav Dubey d6347f6660 fix(vector_stores): pass namespace as top-level kwarg to UpstashVector query_many (#5202) 2026-06-10 16:41:26 +05:30
Hrushikesh Yadav e769502baa feat: warn when hybrid search silently degrades to semantic-only (#5444) 2026-06-10 16:26:48 +05:30
Aarkin Karnik 652193d599 fix(llms/xai): forward tools, add XAIConfig, parse tool_calls (#5190) 2026-06-10 12:46:27 +05:30
Chirag Arora a86c87236d fix(server): forward explain in REST search (#5423) 2026-06-10 12:15:31 +05:30
Ritwij Aryan Parmar f32eb4406b fix(memory): reject empty search queries (#5258) 2026-06-08 21:11:11 +05:30
Chirag Arora a44855af9e feat(memory): add search score explanations (#5102)
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-05 21:30:10 +05:30
Kartik d817aa9c12 fix(oss): parallelize entity boost searches in Memory.search (#5377) 2026-06-05 21:03:42 +05:30
Kartik 7ac8ab154b fix(vector_stores): normalize scores to similarity (higher = better) across all backends (#5391) 2026-06-05 19:13:26 +05:30
Bartok 069ea0887c fix(llms): add is_reasoning_model config override for versioned deployments (#5327)
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-06-05 18:42:56 +05:30
Ren yiwei 866888df41 Fix pgvector sslmode handling for PostgreSQL URIs (#5308) 2026-06-04 19:32:47 +05:30
Abhinav 95b6f95f7b fix: replace mutable default arguments with None sentinels (B006) (#5302) 2026-06-04 18:53:03 +05:30
Chaithanya Kumar 75a37ec93d feat(sdk): add delete_linked option to MemoryClient.delete (Python + TS) (#5270)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 22:38:16 +05:30
Kartik 5a2201d76b fix(pgvector): boolean filter casing, LIKE escaping, and TS scalar coercion (#5264) 2026-05-26 23:03:47 +05:30
Kartik ad736d9a06 fix(pgvector, server): add rich filter operators and fix /search 502 (#5263) 2026-05-26 22:47:41 +05:30
youneshima a623cfaf76 Oss qdrant hosted memories to platform migration (#5080) 2026-05-08 08:04:09 +05:30
Chaithanya Kumar 397f3414ee feat(sdk): expose decay on project.update (Python + TypeScript) (#5062)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-06 15:33:32 +05:30
Gabriel Stein a734e057cf fix (telemetry): stitch oss and platform telemetry identities for python and typescript sdk
Co-authored-by: Younes Slaoui <younes.slaoui@mem0.ai>
2026-05-05 13:48:21 -07:00
Harsh Vardhan Gupta 1b95c99db4 fix: sql injection, prompt injection (#4997)
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
2026-04-29 00:51:16 +05:30
Pratik Rai 693e709389 fix(api): map entity params to filters in GET /memories (#4955) (#4960) 2026-04-24 23:52:14 +05:30
Andrew Halpern cca7551192 fix(memory): honor prompt param in vector store extraction (#4914) 2026-04-23 22:36:54 +05:30
cid 5be2630f5b fix: add missing text_lemmatized in AsyncMemory._create_memory (#4886) 2026-04-23 20:04:43 +05:30
Rudrasinh Nimeshkumar Ravalji 15feaa8ac4 fix(llms): narrow _is_reasoning_model to not match gpt-5.x variants (#4746)
Co-authored-by: Claude <noreply@anthropic.com>
2026-04-23 18:58:12 +05:30
jessai2099 573e5212a4 fix(vector-stores): add agent_id and run_id to Elasticsearch/OpenSearch default mappings (#4906)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-20 23:10:59 +05:30
Yarizakura 8ba225cec8 fix: merge same-key operator dicts in AND metadata filters (#4853) 2026-04-20 21:54:02 +05:30