JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,133 Commits 152 Branches 420 Tags
0aa0f44ac4bb233590ebad675fa88901289b2ffa
Commit Graph

376 Commits

Author SHA1 Message Date
Soumil Rathi 7f19c499ca fix: delete remaining graph test files 
Remove test_neo4j_cypher_syntax.py and test_graph_delete_docker.py
which reference deleted graph_memory module.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 13:15:03 -07:00
Soumil Rathi c5e748b469 fix: remove all graph references from tests/test_main.py 
Strip graph_memory patches, GraphStoreFactory mocks, graph_store config,
enable_graph parametrize, _add_to_graph assertions, and "relations"
assertions from all test fixtures and test functions. Graph store has
been removed from the codebase.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 13:14:40 -07:00
Soumil Rathi 78cc11ef1f fix: restore lmstudio/deepseek providers in TS factory, add langchain to extras 
- Restore LMStudioEmbedder, LMStudioLLM, DeepSeekLLM in TS factory.ts
  (accidentally removed during graph store cleanup — unrelated to graphs)
- Add langchain>=0.1.0 to Python extras dep group (was transitively
  provided by langchain-neo4j in the removed graph group, still needed
  by mem0/llms/langchain.py and mem0/embeddings/langchain.py)
- Add pytest.importorskip("langchain") to test_langchain.py for graceful
  skip when langchain isn't installed

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 12:55:36 -07:00
Soumil Rathi 1a2edf739d fix: delete graph test files that import removed graph modules 
These test files import mem0.memory.graph_memory, kuzu_memory,
memgraph_memory, apache_age_memory, and mem0.graphs.neptune which
were deleted in the graph store removal commit.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 12:17:35 -07:00
Soumil Rathi 66446bd118 fix: address reviewer bugs — metadata mutation, test args, embedding dict, output_format 
1. Fix _create_procedural_memory metadata mutation: use spread operator
   instead of in-place dict assignment (sync + async)
2. Fix test_add assertion: remove trailing None arg that doesn't match
   _add_to_vector_store(messages, metadata, filters, infer) signature
3. Restore output_format: "v1.1" in TS client search payload as fallback
4. Fix infer=False path: pass {text: embedding} dict to _create_memory
   instead of raw embedding list to avoid redundant embed() calls (sync + async)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 11:50:56 -07:00
Soumil Rathi 3ae22be8a2 fix: resolve CI failures — lint errors, pytz in redis, lockfile mismatch 
- Remove unused imports: get_update_memory_messages, get_fact_retrieval_messages
- Fix pytz.timezone("US/Pacific") → timezone.utc in redis vector store
- Remove unused entity_types variable in test_entity_extraction
- Regenerate pnpm-lock.yaml after neo4j-driver removal

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 11:24:14 -07:00
Soumil Rathi 3402c67805 fix: address PR review feedback 
- Remove deprecated custom_update_memory_prompt from MemoryConfig entirely
- Add MAX_BATCH=100 chunking guard to embed_batch in openai.py and azure_openai.py
- Move all inline imports (mem0.utils.*) to top-level in main.py
- Remove custom_update_memory_prompt from test fixture

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 09:01:07 -07:00
Soumil Rathi b9e26acf4d merge: integrate main into feat/v3-pipeline + port AsyncMemory to v3 
Merge 190 commits from main including:
- limit→top_k rename across all vector store APIs
- custom_fact_extraction_prompt→custom_instructions rename
- enable_graph flag removal (use self.graph truthiness)
- US/Pacific→timezone.utc normalization
- 18 Category A bug fixes (partial updates, graph cleanup on delete,
  telemetry gating, metadata mutation prevention, filter operator
  merging, delete timestamps, actor_id preservation, etc.)

Conflict resolutions:
- openai.py: merged _pass_dimensions_to_api with embed_batch
- milvus.py: merged partial-update logic with BM25 text field
- qdrant.py: took main's enhanced _create_filter, merged BM25
  sparse vectors with partial-update endpoints
- test_main.py: adopted main's test structure, removed obsolete
  test_custom_prompts, kept hybrid search over-fetch assertion

AsyncMemory v3 port (full parity):
- Rewrote AsyncMemory._add_to_vector_store with the same 8-phase
  batch pipeline as sync Memory (single LLM call, batch embed,
  hash dedup, batch persist, batch entity linking, message saving)
- All blocking calls wrapped in await asyncio.to_thread()
- Moved _build_session_scope to module level for shared access

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-12 16:26:10 -07:00
Kartik 9d6b79a14e fix(sdk): removing the enable graph flag and switching from snake case to camel case for client ts sdk (#4776) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-12 02:40:54 +05:30
Kartik e44b46ef2e fix(sdk): removing deprecating param from our sdk and docs changes with it (#4740) 2026-04-12 00:34:58 +05:30
Gabriel Stein 9d82e2329d refactor(telemetry): sample OSS hot-path events at 10% to reduce PostHog volume (#4771) 2026-04-11 16:25:38 +05:30
Ignazio De Santis 081eca6d8f fix: guard temp_uuid_mapping lookups against LLM-hallucinated IDs (fixes #3931) (#4674) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-04-08 21:55:52 +05:30
Rakhee Singh 3ffea554bc fix(azure_openai): forward response_format to Azure OpenAI API (#4689) 2026-04-08 19:22:02 +05:30
Utkarsh fcbb70ab3b fix: prevent thread and memory leaks from PostHog telemetry (#4535) 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-04-03 20:01:04 +05:30
Shaik Faizan Roshan Ali 66d34fab3c fix: update_memory endpoint passing dict instead of str (#3933) (#4595) 2026-04-02 19:35:09 +05:30
Krishna Chaitanya 868b63af63 fix: use DatetimeRange for datetime string values in Qdrant range filters (#4659) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-04-02 18:43:58 +05:30
Soumil Rathi a33c557a25 feat(oss): port v3 pipeline with hybrid search, entity extraction, and additive scoring 
Replace the 2-LLM-call add pipeline with a single-pass additive extraction
using ADDITIVE_EXTRACTION_PROMPT. Memories now accumulate (ADD-only) instead
of being updated/deleted during extraction.

Search pipeline upgraded to hybrid scoring combining three signals:
- Semantic similarity (vector search)
- BM25 keyword matching (native per vector store, 15 stores supported)
- Entity boost (spaCy NER with entity collection linking)

Combined score = (semantic + bm25 + entity_boost) / max_possible, where
max_possible adapts based on which signals are active.

Key changes:
- Add spaCy-based lemmatization for BM25 keyword search
- Add spaCy-based entity extraction (PROPER, QUOTED, COMPOUND, NOUN types)
- Add entity store as second vector collection ({collection}_entities)
- Add native keyword_search() to 15 vector store adapters
- Add batch embedding support (embed_batch) for OpenAI and Azure OpenAI
- Add message persistence in SQLite (rolling window of 10 per scope)
- Add additive scoring with adaptive normalization
- Add observation_date parameter to add()
- Add custom_instructions config field
- Default search threshold changed to 0.1

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-31 14:09:37 -07:00
Rakhee Singh 93bd4e248c fix(deepseek): forward response_format to OpenAI-compatible API (#4635) 2026-03-31 18:06:53 +05:30
Rakhee Singh dbac83218f fix(vllm): forward response_format to OpenAI-compatible API (#4608) 
Co-authored-by: rasingh5 <rasingh@demandbase.com>
 2026-03-31 13:25:45 +05:30
HUANG XIAO 5d30af9560 feat(bedrock): add MiniMax provider support for AWS Bedrock (#4609) 2026-03-30 20:40:24 +05:30
Br1an 7213e1b1a6 fix: reset graph database in Memory.reset() (#4185) 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
 2026-03-30 18:45:38 +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