chaithanyak42 and Claude Opus 4.6
e51df348ce
fix(ts-sdk): unwrap v1.1 search response in client, fix TS2339 type errors
...
search() now unwraps { results: [...] } -> [...] internally (same
pattern getAll() already uses), so callers always get Array<Memory>.
Removes redundant unwrap logic from integration test helpers and
search.test.ts that caused TS2339 'Property results does not exist
on type never' — the false branch of Array.isArray() was unreachable
since search() is typed as returning Array<Memory>.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-14 01:48:22 +05:30
Soumil Rathi and Claude Opus 4.6
b9d7ae5fa7
fix: update integration tests for v3 search response format
...
v3 search returns {results: [...]} instead of a bare array.
Updated waitForSearchResults helper and search edge case tests
to unwrap the v3 envelope.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 13:10:17 -07:00
Soumil Rathi and Claude Opus 4.6
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 and Claude Opus 4.6
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 and Claude Opus 4.6
163444e33b
fix: update TS client tests for v3 API endpoints
...
Update mock URLs in memoryClient.crud.test.ts and
memoryClient.search.test.ts to match v3 endpoints:
- add: /v1/memories/ -> /v3/memories/
- search: /v2/memories/search/ -> /v3/memories/search/
- deleteAll: stays on /v1/memories/ (no v3 equivalent)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 11:34:52 -07:00
Soumil Rathi and Claude Opus 4.6
e1e033daef
style: run prettier on TS SDK files
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 11:29:06 -07:00
Soumil Rathi and Claude Opus 4.6
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
Soumil Rathi
c0343aec1b
Merge remote-tracking branch 'origin/feat/v3-pipeline' into feat/v3-pipeline
...
# Conflicts:
# mem0-ts/src/oss/src/utils/factory.ts
# mem0/vector_stores/milvus.py
# mem0/vector_stores/qdrant.py
2026-04-12 16:30:05 -07:00
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 and GitHub
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 and GitHub
9d82e2329d
refactor(telemetry): sample OSS hot-path events at 10% to reduce PostHog volume ( #4771 )
2026-04-11 16:25:38 +05:30
398445c691
fix: filters did not support AND, OR and NOT in Qdant and other vector stores ( #4780 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-10 23:43:12 +05:30
e59e3d5f0c
Add deepseek.ts to src/llms with corresponding unit tests. Updates fa… ( #4613 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-04-10 20:06:22 +05:30
6cc1c15320
feat(sdk): add multilingual param to project update ( #4314 )
...
Co-authored-by: Soumil Rathi <soumilrathi@gmail.com >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-04-02 18:38:26 +05:30
Saharsh Patel and GitHub
713dba5d0a
fix: replace .single() with .maybeSingle() in SupabaseDB.get() to handle missing rows ( #4599 )
2026-04-01 18:41:24 +05:30
8ae7a06220
fix: pass dimensions parameter to OpenAI embeddings API ( #4632 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-04-01 18:40:17 +05:30
47969aaa6b
fix(ts): extract JSON from chatty LLM responses in fact retrieval ( #4533 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-03-30 20:33:11 +05:30
431cba20e9
fix(ts): work around Qdrant Cloud "Illegal host" error ( #4565 )
...
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 >
2026-03-28 21:50:36 +05:30
Felippe Mercurio and GitHub
3a9fcdbec2
fix(oss): make pgvector pg import compatible with ESM ( #4544 )
2026-03-26 20:07:39 +05:30
Himanshu and GitHub
316dc67a0a
fix(ts-oss): register pgvector in VectorStoreFactory ( #3367 ) ( #4502 )
2026-03-23 18:52:19 +05:30
Aditya Paul and GitHub
c39d5ada4d
fix: Bug: Zod Schema Incompatible with OpenAI Structured Outputs API ( #3462 )
2026-03-21 19:48:31 +05:30
06c25eb00b
fix: use root LLM config as fallback for graph store instead of hardcoded OpenAI default ( #4466 )
...
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-21 19:38:49 +05:30
30661ab427
Fix: add pgvector support to NodeJS OSS VectorStoreFactory ( fixes #3491 ) ( #3997 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-03-20 20:47:04 +05:30
Failfail2603 and GitHub
7ad5d6f442
fix: use toCamelCase in redis get method for the payload ( #3172 )
2026-03-20 20:28:41 +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
Kartik and GitHub
88abb29de9
fix: handle truncated code blocks in removeCodeBlocks function ( #4421 )
2026-03-19 18:18:11 +05:30
Kartik and GitHub
66e6f58fc6
chore: delete obsolete e2e tests ( #4419 )
2026-03-19 18:11:32 +05:30
Kartik and GitHub
22c2545d61
feat(test): integration test for ts-sdk ( #4395 )
2026-03-19 18:11:09 +05:30
Kartik and GitHub
ffd1b96916
fix(ts-sdk): externalize all peerDependencies in tsup config ( #4408 )
2026-03-18 23:49:16 +05:30
dhilip_binny and GitHub
4ffe1eaa4e
fix: forward tools parameter to Gemini API in GoogleLLM ( #4380 ) ( #4386 )
2026-03-18 23:48:26 +05:30
Kartik and GitHub
7539463f50
refactor: improve Ollama embedder, normalize model names, add error handling, update tests ( #4403 )
2026-03-18 23:34:35 +05:30
Kartik and GitHub
3cdcb6564c
chore: end to end test coverage for ts sdk ( #4357 )
2026-03-17 21:13:52 +05:30
336fbce60a
feat(mem0-ts): add LM Studio embedder and LLM support ( #4354 )
...
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com >
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-17 18:21:35 +05:30
Huvee and GitHub
9eb5b9ed29
fix(qdrant): handle 401/403 in ensureCollection for scoped JWTs ( #4356 )
2026-03-17 18:21:00 +05:30
Kartik and GitHub
b4b73deada
fix(oss): OllamaLLM now respects configured url instead of always falling back to localhost ( #4320 )
2026-03-16 21:42:46 +05:30
Saket Aryan and GitHub
df79a43925
chroe(ts-sdk): fix lints ( #4334 )
2026-03-14 23:39:23 +05:30
4e1e4c0c5a
fix(ts): extract content from code blocks instead of deleting it ( #4317 )
...
Co-authored-by: d 🔹 <258577966+voidborne-d@users.noreply.github.com >
2026-03-14 23:34:43 +05:30
Anisha Mahuli and GitHub
6f079c313f
fix OpenAI embedder baseurl ( #4275 )
2026-03-13 01:38:59 -07:00
Giulio Leone and GitHub
e95090e116
fix: add missing 'json' keyword to graph memory prompts ( fixes #4248 ) ( #4249 )
2026-03-13 01:38:24 -07:00
59c3b050bd
fix(oss): auto-detect embedding dimension to fix Qdrant mismatch with non-OpenAI embedders ( #4297 )
...
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com >
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-12 21:45:09 +05:30
Utkarsh and GitHub
5b3acf416b
fix(ts-sdk): resolve SQLite db paths correctly in OSS mode ( #4307 )
2026-03-12 09:13:44 -07:00
Utkarsh and GitHub
36537c8326
fix(ts-sdk): replace sqlite3 with better-sqlite3 to fix native binding resolution ( #4270 )
2026-03-09 11:00:36 -07:00
mgoulart and GitHub
db15d5c629
fix(oss): validate LLM fact output via FactRetrievalSchema before embedding ( #4083 )
2026-02-22 19:57:48 -08:00
Mragank Shekhar and GitHub
a140829395
chore: update user facing timestamp for a memory ( #4066 )
2026-02-18 03:27:46 +05:30
Saket Aryan and GitHub
69a832dc58
chore: add update project options ( #3947 )
2026-02-03 10:55:43 +05:30
Saket Aryan and GitHub
90a7b1afa0
feat(ts-sdk): add support for keyword arguments in add and search methods ( #3895 )
2026-01-10 21:19:55 +05:30
Mrinank Bhowmick and GitHub
5227b0a062
Fix embedder config schema to support embeddingDims and url parameters ( #3633 )
2025-10-21 09:30:44 -07:00
Parshva Daftari and GitHub
394203d1b5
Mem0 1.0.0 ( #3545 )
2025-10-16 15:50:20 +05:30
Parshva Daftari and GitHub
41cfb3ab1a
[Update] Default LLM ( #3587 )
2025-10-15 11:19:52 -07:00
G Karthik Koundinya and GitHub
a40314c971
feat: Add Azure AI Search vector store support for TypeScript SDK ( #3549 )
2025-10-15 11:19:10 -07:00
