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
59880a6f8f
feat: TS SDK v3 port, graph store removal, client v3 API migration
...
TypeScript SDK v3 pipeline (full parity with Python):
- Single-pass additive extraction with ADDITIVE_EXTRACTION_PROMPT
- Hybrid search (semantic + BM25 + entity boost) with additive scoring
- 8-phase batch pipeline (batch embed, persist, entity linking)
- New utils: scoring.ts, lemmatization.ts (natural), entity_extraction.ts (compromise)
- keywordSearch() on 8 vector stores (3 full: PGVector, Memory, Azure AI Search)
- Message persistence in SQLiteManager (rolling window of 10)
- Entity store as second vector collection
- MAX_BATCH=100 chunking guard on OpenAI/Azure embedBatch
- Updated default LLM model to gpt-4.1-nano-2025-04-14
- compromise + natural added as peer dependencies
Graph store removal (Python + TypeScript):
- Removed Neo4j, Memgraph, Kuzu, Neptune, Apache AGE integrations
- Deleted 18 graph-related files across both SDKs
- Removed GraphStoreFactory, GraphStoreConfig, graph_store config field
- Removed "relations" key from all API responses
- Removed graph optional dependency group from pyproject.toml
- Removed neo4j-driver from TS peerDependencies
- Simplified add/search/delete/reset (no more parallel graph operations)
Client SDK v3 API migration:
- add() endpoint: /v1/memories/ -> /v3/memories/ (async response)
- search() endpoint: /v2/memories/search/ -> /v3/memories/search/
- Removed output_format injection and v1.1 unwrapping logic
- Applied to both Python (sync + async) and TypeScript clients
Review feedback fixes:
- Removed deprecated custom_update_memory_prompt from MemoryConfig
- Added MAX_BATCH=100 chunking to Python + TS embed_batch
- Moved all inline imports to top level in main.py
- Cleaned up GraphStoreError dead code from exceptions.py
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 10:45:40 -07:00
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
9d82e2329d
refactor(telemetry): sample OSS hot-path events at 10% to reduce PostHog volume ( #4771 )
2026-04-11 16:25:38 +05:30
6984958138
chore: sat release ( #4702 )
2026-04-06 16:55:08 +05:30
9c9b3d54e2
feat(oss): make spaCy an optional dependency
...
Move spacy from core dependencies to optional [nlp] extra.
The system gracefully degrades without spaCy:
- Lemmatization falls back to raw text
- Entity extraction returns empty (no entity boost)
- BM25 keyword search still works on raw text
- Semantic search and additive scoring unaffected
Install with NLP support: pip install mem0ai[nlp]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-02 11:04:38 -07:00
1bfaaf8750
chore: release ( #4657 )
2026-04-01 23:44:09 +05:30
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
b8a5ca1b70
chore: bump mem0ai and mem0-ts versions to 1.0.9/2.4.4 and update changelog ( #4585 )
2026-03-28 22:42:21 +05:30
4482228383
chore: fix failing CI lint errors ( #4584 )
2026-03-28 21:45:47 +05:30
e280665578
fix: remove README.md from wheel shared-data ( #4052 )
2026-03-28 20:57:51 +05:30
e8004b93db
chore: updating the sdk version and changelog ( #4561 )
...
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-26 22:21:31 +05:30
3c2683c1b5
feat: add Mem0 plugin for Claude Code and Cursor ( #4518 )
2026-03-25 14:45:59 -07:00
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
6663b738d5
refactor: fix webhook create/update serialization, add payload types, and MEMORY_CATEGORIZED event ( #4429 )
...
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com >
2026-03-19 22:26:17 +05:30
7539463f50
refactor: improve Ollama embedder, normalize model names, add error handling, update tests ( #4403 )
2026-03-18 23:34:35 +05:30
15218d4a7f
chore: bump mem0-ts to 2.4.1, pyproject to 1.0.6, update changelog with bug fixes ( #4361 )
...
Co-authored-by: Saket Aryan <saketaryan2002@gmail.com >
2026-03-16 22:49:31 +05:30
fa5c85f9f6
chore: bump protobuf dependency to 5.29.6 and extend upper bound to 7.0.0 ( #4326 )
2026-03-14 10:58:58 -07:00
34c797d285
fix: disable ph telemetry still calls posthog ( #4203 )
2026-03-04 03:55:34 +05:30
a140829395
chore: update user facing timestamp for a memory ( #4066 )
2026-02-18 03:27:46 +05:30
69a832dc58
chore: add update project options ( #3947 )
2026-02-03 10:55:43 +05:30
dba7f0458a
(version-bump): update the project version to v1.0.2 ( #3902 )
2026-01-13 13:01:38 +05:30
3b84a234e1
Updates to python sdk ( #3749 )
2025-11-13 14:22:39 -08:00
9ef644b95e
Add Apache Cassandra vector store support ( #3578 )
2025-10-17 23:48:49 +05:30
1090784302
[feat add]FastEmbed embedding for local embeddings ( #3552 )
2025-10-16 22:52:22 +05:30
394203d1b5
Mem0 1.0.0 ( #3545 )
2025-10-16 15:50:20 +05:30
fbf3bd640c
support dependency openai 2.x ( #3533 )
2025-10-03 21:50:49 +05:30
346d89d244
Added azure mysql for mem0 ( #3531 )
2025-10-02 21:41:03 +05:30
445286a138
fix: update license information in README and pyproject.toml ( #3522 )
2025-09-30 13:58:08 -07:00
ed5a1e9fc6
Update version to 0.1.118 ( #3505 )
2025-09-26 02:03:37 +05:30
6b5582f474
Feat: Mem0 vector store backend integration for Neptune Analytics ( #3453 )
...
Signed-off-by: Andy Kwok <andy.kwok@improving.com >
2025-09-17 19:26:03 +05:30
d48b1832c7
Fixes ollama and updates openai dependency ( #3452 )
2025-09-12 01:39:39 +05:30
e3f0277cb9
feat(vector-store): Add Valkey vector store support ( #3272 )
2025-09-10 04:01:53 +05:30
5e8d5e4664
Release 0.1.117 ( #3411 )
2025-09-03 23:09:00 +05:30
3d0ece1bcf
Refactor PGVector to Use Internal Connection Pools and Context Managers ( #3373 )
2025-08-29 19:06:39 +05:30
6237a6acb9
Adding weaviate, faiss, pgvector, chroma, redis, elasticsearch, milvus vector store to openmemory ( #3366 )
...
Co-authored-by: Vikram Iyer <vikramiyer@mac.local.meter >
2025-08-27 01:47:39 +05:30
4487785cec
feature: add Azure Identity for Azure OpenAI and Azure AI Search authentication ( #3262 )
2025-08-21 02:00:27 +05:30
c8ee17b884
Fix dependency and tests and updated docstring ( #3337 )
2025-08-19 02:12:24 +05:30
3a1eff425b
feat(vector-store): Add Databricks Mosaic AI vector store support ( #3325 )
2025-08-18 22:20:33 +05:30
a6a3928091
Add support for graph memory using Kuzu ( #2934 )
2025-08-16 02:22:31 +05:30
5e895c240a
Update version to 0.1.116 ( #3312 )
2025-08-14 00:06:34 +05:30
7159221d2e
Restrict package version ( #3305 )
2025-08-12 16:53:21 -05:00
23d31a830b
Added support for python 3.12 ( #3295 )
2025-08-12 15:01:41 -05:00
57a16aeb4b
Updated psycopg -> 3 ( #3271 )
2025-08-04 14:46:44 -07:00
37ee3c5eb2
docs: Update for new Project API and deprecation notices ( #3212 )
2025-07-24 15:16:47 +05:30
c0a930a7d3
Update version to 0.1.114 ( #3107 )
2025-07-04 16:28:39 -07:00
05c404d8d3
Add Amazon Neptune Analytics graph_store configuration & integration ( #2949 )
2025-07-04 16:26:21 -07:00
7484eed4b2
Fix CI issues related to missing dependency ( #3096 )
2025-07-03 18:52:50 -07:00
5a1083b709
Fix: Gemini embedder config and version bump -> 0.1.113 ( #3070 )
2025-06-30 13:31:51 +05:30
ac085db500
version bump -> 0.1.112 ( #3058 )
2025-06-27 15:19:57 +05:30
Soumil Rathi