utkarsh240799 and Claude Opus 4.6
596a624716
fix: improve double-embedding fix with type safety and UPDATE path test ( #3723 )
...
Make isinstance checks numpy-safe by using `not isinstance(dict)` instead
of `isinstance(list)`, add type hints to existing_embeddings parameter,
and add regression test for the infer=True UPDATE path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-25 17:35:18 +05:30
Varun Chawla and kartik-mem0
211a7570e7
Fix: prevent double embedding in mem0.add ( fixes #3723 )
...
This fix addresses issue #3723 where mem0.add() was calling the
embedding API twice, unnecessarily doubling costs and latency.
Changes made:
1. Modified _create_memory() to accept embeddings as either a dict
(for caching) or a precomputed vector, preventing redundant calls
2. Updated infer=False path to pass embeddings as a dict
3. Added caching for action_text embeddings in infer=True path for
both ADD and UPDATE operations, since the LLM may rephrase facts
4. Applied same fixes to both sync and async Memory classes
5. Added regression test to verify embedding is called only once
The root cause was that when infer=False, embeddings were passed
directly to _create_memory without a dict wrapper, causing it to
re-embed. When infer=True, if the LLM rephrased extracted facts,
the action_text wouldn't match the cache key, triggering re-embedding.
2026-03-23 14:15:05 +05:30
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 and GitHub
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
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
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
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 and GitHub
abdb07c204
fix: handle None content and empty candidates in GeminiLLM parsing ( #4462 )
2026-03-21 13:52:13 +05:30
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
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
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 and GitHub
2b9558335b
fix: raise ValueError when deleting nonexistent memory ( #4455 )
2026-03-20 18:28:58 +05:30
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
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 and GitHub
73038900f5
fix: wrap vector and payload in lists for Langchain.update ( #4446 )
2026-03-20 14:42:17 +05:30
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
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 and GitHub
348f44b632
fix(reranker): support nested llm config in LLMReranker for non-OpenAI providers ( #4405 )
2026-03-19 15:26:00 +05:30
Atharva Jaiswal and GitHub
a172de9c22
fix: pass encoding_format='float' in OpenAI embeddings for proxy compatibility ( #4058 )
2026-03-18 23:46:44 +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
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
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 and GitHub
35fe30aabd
fix: ensure JSON instruction in prompts for json_object response format ( #3559 ) ( #4271 )
2026-03-16 21:57:57 +05:30
Kartik and GitHub
82d67430dd
fix: remove destructive vector_store.reset() from delete_all() ( #4349 )
2026-03-16 20:55:29 +05:30
Kartik and GitHub
8fcf2b0b29
fix: skip telemetry vector store init when MEM0_TELEMETRY is disabled ( #4351 )
2026-03-16 20:55:04 +05:30
Anisha Mahuli and GitHub
2e5e290434
fix: key error when llm omits entities key tool call ( #4313 )
2026-03-16 20:52:26 +05:30
liviaellen and GitHub
72e2c5c24b
Fix handle malformed entity dicts and None LLM response in memgraph_memory ( #4238 )
2026-03-07 12:05:32 -08:00
Saket Aryan and GitHub
34c797d285
fix: disable ph telemetry still calls posthog ( #4203 )
2026-03-04 03:55:34 +05:30
Saket Aryan and GitHub
27e5db5831
(fix): mongodb distribution name, azure ai search, and workflow trigger ( #3900 )
2026-01-13 12:52:49 +05:30
Parth Sharma and GitHub
84687fc3d2
[fix] list' object has no attribute 'id' - Id fault with chroma pinecone and other providers ( #3693 )
2025-10-31 16:46:10 +05:30
eb2f8a3738
fix: Prevent Mock object issues in graph memory tests ( #3627 )
...
Co-authored-by: parshvadaftari <daftariparshva@gmail.com >
2025-10-22 03:53:12 +05:30
Faizan Habib and GitHub
9ef644b95e
Add Apache Cassandra vector store support ( #3578 )
2025-10-17 23:48:49 +05:30
Tarun Jain and GitHub
1090784302
[feat add]FastEmbed embedding for local embeddings ( #3552 )
2025-10-16 22:52:22 +05:30
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
Vedant Thakkar and GitHub
ea22e8d9cd
feat: Allow custom model and params with huggingface_base_url ( #3574 )
2025-10-14 17:33:18 +05:30
Alex Kondratev and GitHub
ce8a285003
Validate embedding_dims in kuzu, fix #3556 ( #3558 )
2025-10-11 03:55:03 +05:30
Parshva Daftari and GitHub
4559623501
[fix] milvus db bug and added tests ( #3566 )
2025-10-11 02:21:35 +05:30
Vishaal LS and GitHub
9000576173
fix: handle non-serializable objects in config deepcopy ( #3464 ) ( #3544 )
2025-10-09 19:35:08 +05:30
Josh Hayes and GitHub
922471f43b
fix: Databricks Vector Store ( #3546 )
2025-10-09 19:19:07 +05:30
Alex Kondratev and GitHub
ee0202764b
Tool call support for LangchainLLM ( #3542 )
2025-10-06 00:03:44 +05:30
dog-last and GitHub
51ce6f1347
Bug fix of thinking llm in vllm ( #3510 )
2025-10-03 19:13:08 +05:30
Parshva Daftari and GitHub
346d89d244
Added azure mysql for mem0 ( #3531 )
2025-10-02 21:41:03 +05:30
Vishaal LS and GitHub
58cc44ff38
fix: handle missing 'data' key in memory payload during search operations ( #3524 )
2025-09-30 15:10:43 -07:00
Karthikeya Kollu and GitHub
dc883b0f9e
[test] Add comprehensive test suite for SQLiteManager ( #3494 )
2025-09-25 22:30:03 +05:30
Abdullah Irfan and GitHub
9df392b26a
Fixed s3 vectors memory initialization issue from configuration ( #3481 )
2025-09-20 12:43:18 +05:30
Parshva Daftari and GitHub
ead210ffe4
Added weaviate db test ( #3483 )
2025-09-18 14:40:44 -07:00
a015e2ff4a
Add Neptune-DB graph store with vector store ( #3443 )
...
Signed-off-by: Andrew Carbonetto <andrew.carbonetto@improving.com >
Co-authored-by: Siddhartha Sahu <dev@sdht.in >
2025-09-19 02:54:33 +05:30
Andy Kwok and GitHub
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
Parshva Daftari and GitHub
d48b1832c7
Fixes ollama and updates openai dependency ( #3452 )
2025-09-12 01:39:39 +05:30
