JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,035 Commits 152 Branches 420 Tags
fix/normalize-vector-store-scores
Commit Graph

356 Commits

Author SHA1 Message Date
utkarsh240799 224fd6c7d8 fix: normalize vector store scores to similarity (higher = better) 
The threshold parameter in Memory.search() was silently broken for 11
vector stores because they returned raw distance scores (lower = better)
while the threshold check assumed similarity scores (higher = better).
This caused threshold filtering to be inverted — good matches got
dropped and bad matches passed through.

Convert all affected vector stores to return similarity scores:
- Cosine distance stores: score = max(0.0, 1.0 - distance)
- L2 distance stores: score = 1.0 / (1.0 + distance)
- Stores computing similarity then discarding it: return similarity directly

Fixes #4453
Related: #3283

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-28 21:57:40 +05:30
Himanshu ae49edec44 fix(memory): centralize entity cleanup and skip malformed LLM relation dicts (#4515) 2026-03-28 21:23:05 +05:30
Br1an 27a6e7863e fix: rebuild FAISS index on vector deletion (#4178) 2026-03-28 20:56:39 +05:30
Kartik cd2dd7cc54 refactor: update default Gemini and Vertex AI embedder model to gemini-embedding-001 (#4571) 2026-03-28 20:39:27 +05:30
Kartik c2698f2b71 fix: preserve original actor_id during memory update (#4570) 2026-03-28 00:02:58 +05:30
Utkarsh e87240d4d9 fix(vector_stores): handle vector=None in Milvus and Qdrant update methods (#4568) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-27 21:50:54 +05:30
Gopal Bagaswar 68cf4e118d feat: add reasoning_effort parameter support for reasoning models (#4461) 2026-03-27 17:54:44 +05:30
Utkarsh 12624555b4 fix(memory): set updated_at on creation and preserve pre-existing created_at (#4499) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-27 16:59:44 +05:30
Utkarsh 3ac4e047de fix: merge multiple filter operators for same key (#4559) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 20:28:37 +05:30
Utkarsh a2ffca3266 fix: prevent SQL injection in Databricks vector store (#4558) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 20:22:34 +05:30
zaid khan 5edc0cc99f fix: update parameter added to the update function which is exposed t… (#3799) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 20:02:33 +05:30
VictorECDSA 1aecfadf45 fix: add timestamps for DELETE operations in history (#4492) 2026-03-26 18:52:10 +05:30
Utkarsh 2a59c9fd99 fix: handle chatty LLM responses in JSON parsing (#4525) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 16:39:17 +05:30
Himanshu f06e2d744d Fix/OpenAI embedding dimensions 4153 (#4481) 2026-03-25 19:59:28 +05:30
lamost423 f9e30304d7 fix: sanitize hyphens in Neo4j Cypher relationship names (#4154) 2026-03-25 19:58:27 +05:30
Varun Chawla 7e3b727528 Fix: prevent double embedding in mem0.add (fixes #3723) (#3996) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 18:14:48 +05:30
Utkarsh 2a36960f4c fix: prevent in-place mutation of metadata in _create_memory (#4529) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 13:56:30 +05:30
Himanshu 2e0f91e70d fix(bedrock): omit topP for Anthropic Converse; use AWSBedrockConfig in LlmFactory (#4469) 2026-03-25 11:22:52 +05:30
Kartik 5431badfd4 fix: preserve custom metadata when updating memory (#4495) 2026-03-24 10:58:21 +05:30
Utkarsh bda5b726bd fix: avoid sending both temperature and top_p to Anthropic API (#4471) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 21:00:41 +05:30
Utkarsh 5332741961 fix: clean up graph store data on Memory.delete() (#4505) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 19:27:38 +05:30
Utkarsh d8a6960b4a fix: align Databricks docs with config and fix query mode selection (#4477) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 19:20:11 +05:30
Himanshu ecedbc11d9 fix(qdrant): do not remove local path on init (#4473) (#4475) 2026-03-23 14:58:06 +05:30
Utkarsh 9aadfa3221 fix: add missing limit, threshold, infer, memory_type, and prompt params to REST API (#4496) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 14:48:13 +05:30
Br1an cc45561abd fix: accept default /tmp/chroma path in ChromaDbConfig validator (#4179) 2026-03-23 14:12:49 +05:30
Varun Chawla 7cebaba0a2 fix: upgrade MongoDB vector store from deprecated knnVector to GA vectorSearch (#3995) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 12:20:17 +05:30
Kartik eb780f4880 refactor: add vector validation to OpenSearchDB to ensure non‑null, non‑empty, and correct‑dimension vectors (#4472) 2026-03-21 20:36:26 +05:30
longway 7a09663156 fix(qdrant): implement enhanced metadata filtering operators (#4127) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-21 19:37:26 +05:30
Utkarsh bf9a5703b1 feat: integrate turbopuffer as vector database provider (#4428) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-21 19:28:25 +05:30
darrenxu 884e740b53 fix(graph): soft-delete graph relationships instead of hard DELETE (#4188) 
Signed-off-by: sxu75374 <imshuaixu@gmail.com>
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-03-21 17:32:59 +05:30
Kartik abdb07c204 fix: handle None content and empty candidates in GeminiLLM parsing (#4462) 2026-03-21 13:52:13 +05:30
Utkarsh 305ce7b6b3 feat: add Apache AGE graph store support (#4448) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-20 20:27:48 +05:30
Matt Van Horn 4437c3e8a8 fix: add missing _parse_response to AzureOpenAIStructuredLLM (#4434) 
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-20 20:14:47 +05:30
Himanshu 54bdbde6e6 feat: add MiniMax LLM provider (#4132) (#4431) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-03-20 19:18:36 +05:30
Kartik 2b9558335b fix: raise ValueError when deleting nonexistent memory (#4455) 2026-03-20 18:28:58 +05:30
Utkarsh 2520edb404 feat: add optional API key authentication to REST API server (#4442) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-20 16:15:25 +05:30
dhilip_binny 401754ca65 fix: prevent embedding corruption in Valkey and Redis when vector is None (#4336) (#4362) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-03-20 15:07:17 +05:30
Kartik 73038900f5 fix: wrap vector and payload in lists for Langchain.update (#4446) 2026-03-20 14:42:17 +05:30
Anisha Mahuli 08de18f860 replace hardcoded US/Pacific timezone references with timezone.utc (#4404) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-03-19 17:29:29 +05:30
Utkarsh 46b4b2e9c8 fix: preserve http_auth in _safe_deepcopy_config for OpenSearch (#3580) (#4418) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-19 16:37:56 +05:30
Kartik 348f44b632 fix(reranker): support nested llm config in LLMReranker for non-OpenAI providers (#4405) 2026-03-19 15:26:00 +05:30
Atharva Jaiswal a172de9c22 fix: pass encoding_format='float' in OpenAI embeddings for proxy compatibility (#4058) 2026-03-18 23:46:44 +05:30
Kartik 7539463f50 refactor: improve Ollama embedder, normalize model names, add error handling, update tests (#4403) 2026-03-18 23:34:35 +05:30
Anisha Mahuli 577a5a2feb fix(oss): normalize malformed LLM fact output before embedding (#4224) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-03-18 20:19:29 +05:30
darrenxu d7a34c24dd fix(ollama): pass tools to client.chat and parse tool_calls from response (#4176) 
Signed-off-by: sxu75374 <imshuaixu@gmail.com>
Signed-off-by: Small <imshuaixu@gmail.com>
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-03-18 19:19:36 +05:30
dhilip_binny 35fe30aabd fix: ensure JSON instruction in prompts for json_object response format (#3559) (#4271) 2026-03-16 21:57:57 +05:30
Kartik 82d67430dd fix: remove destructive vector_store.reset() from delete_all() (#4349) 2026-03-16 20:55:29 +05:30
Kartik 8fcf2b0b29 fix: skip telemetry vector store init when MEM0_TELEMETRY is disabled (#4351) 2026-03-16 20:55:04 +05:30
Anisha Mahuli 2e5e290434 fix: key error when llm omits entities key tool call (#4313) 2026-03-16 20:52:26 +05:30
liviaellen 72e2c5c24b Fix handle malformed entity dicts and None LLM response in memgraph_memory (#4238) 2026-03-07 12:05:32 -08:00