JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,505 Commits 152 Branches 420 Tags
opencode-v0.2.2
Commit Graph

509 Commits

Author SHA1 Message Date
Jiangtian Feng 7fa996261d perf: batch BM25 sparse encoding in Qdrant insert (#5592) 2026-06-23 16:29:16 +05:30
Yash Singh 87bd2d91e0 fix(llms): preserve reasoning fields in base-to-provider config conversion (#5638) 2026-06-23 16:27:43 +05:30
Yash Singh 15a930dac2 fix(llms): pass configured anthropic_base_url to the Anthropic client (#5626) 2026-06-23 16:26:22 +05:30
Hrushikesh Yadav 4e448269bc fix(mongodb): reject dict filter values to prevent NoSQL operator injection (#5748) 2026-06-22 18:09:01 +05:30
Hrushikesh Yadav 29d131f7aa fix(chroma): return None instead of {} from _generate_where_clause for empty filters (#5713) 2026-06-22 12:05:28 +05:30
Bartok 42fe129330 fix(opensearch): return [[]] from list() error path to honor list() contract (#5727) 2026-06-22 11:58:37 +05:30
Hrushikesh Yadav bd5996f41e fix(pinecone): return [[]] from list() error path instead of dict (#5706) 2026-06-22 11:57:52 +05:30
Bartok 299c423213 fix(faiss): return [[]] for uninitialized index to honor list() contract (#5725) 2026-06-22 11:57:06 +05:30
Hrushikesh Yadav ce0531a13e fix(mongodb): wrap list() return in outer list to match interface contract (#5729) 2026-06-22 11:54:16 +05:30
Lucas Kim 513b56159f fix(embeddings): forward embedding_dims to Titan V2 in AWS Bedrock embedder (#5671) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-22 11:49:23 +05:30
Yash Singh 1676b3168d fix(server): return 404/400 instead of 502 for not-found and invalid input (#5634) 2026-06-22 11:47:48 +05:30
Davide Leopardi 8a786bf72d fix(azure): stop mutating and corrupting caller messages in content rewrite (#5731) 2026-06-22 11:45:46 +05:30
Yash Singh a48f34cf77 fix(vector_stores): deep-copy Redis DEFAULT_FIELDS so instances keep distinct dims (#5633) 2026-06-22 11:29:25 +05:30
Hrushikesh Yadav 650b734b1b fix: reset() only drops history table, leaving stale messages (#5541) 2026-06-22 11:28:17 +05:30
Yash Raj Pandey 7a9f03af3f fix(llms,embeddings): repair HTTP proxy support (httpx>=0.28) and preserve proxies in LlmFactory (#5447) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-06-19 13:45:21 +05:30
Yash Singh 48f1d6f010 fix(reranker): clamp out-of-range LLM scores instead of mis-parsing them (#5635) 2026-06-19 12:49:50 +05:30
Yash Singh f0ccd99924 fix(vertex): pass required vectors arg in list and similarity search (#5627) 2026-06-19 12:44:48 +05:30
ly-wang19 c5971193a2 fix(vector_stores): return None from Redis.get() for missing IDs (#5625) 
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai>
 2026-06-19 12:25:24 +05:30
Yash Singh ff53fd60b7 fix(graph): keep distinct entities that share a substring prefix (#5630) 2026-06-19 12:23:15 +05:30
Yash Singh ffa334537a fix(client): check HTTP status before parsing ping response in _validate_api_key (#5639) 2026-06-19 12:19:13 +05:30
Yash Singh bd7ce2c13c fix(vector_stores): drop stray print in Weaviate list_cols (#5637) 2026-06-19 12:07:10 +05:30
Yash Singh 5d767219ff fix(reranker): export all five rerankers from package root (#5636) 2026-06-19 12:06:12 +05:30
Yash Singh 5b4478458b fix(server): return 404 not 500 for malformed api key id on revoke (#5640) 2026-06-18 17:45:05 +05:30
Bartok 7ae6a8c36a fix(memory): guard entity embed_batch count mismatch in v3 add pipeline (#5604) 
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai>
 2026-06-18 17:22:44 +05:30
Hrushikesh Yadav 466249113c fix: async delete_all race condition corrupts entity store linked_memory_ids (#5553) 2026-06-18 16:57:03 +05:30
Alok Tripathi 3e2ae734e7 feat(embeddings): add native embed_batch to 5 embedders (LMStudio, Together, HuggingFace, VertexAI, GoogleGenAI) (#5609) 2026-06-18 16:46:31 +05:30
Yash Raj Pandey 703e8a035d fix: FAISS filtered search drops over-fetched candidates before filtering (#5453) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-06-17 16:34:27 +05:30
Hrushikesh Yadav 7ed2faab84 fix: api_error_handler silently drops return values from async methods (#5540) 2026-06-17 14:46:08 +05:30
Lucas Kim 137b7519f7 fix(embeddings): honor aws_session_token in AWS Bedrock embeddings (#5566) 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-17 14:36:33 +05:30
Alok Tripathi e34f5835bd feat(embeddings): add native embed_batch to OllamaEmbedding (#5415) 
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai>
 2026-06-17 14:12:53 +05:30
Yash Raj Pandey f122eb7c65 fix(weaviate): pass embedding dims in reset() so it does not crash (#5570) 2026-06-17 13:29:13 +05:30
Aayush Soni d772f9a961 feat: support Gemini via Vertex AI as LLM provider (#4030) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-06-16 16:59:06 +05:30
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