kartik-mem0
2b8e4ea059
fix(llms/lmstudio): honor LMSTUDIO_BASE_URL in the LLM too
...
The embedder fix in this branch left the sibling LLM still hardcoded, so
a self-hosted LM Studio behind a non-default host worked for embeddings
and silently fell back to localhost for generation.
LMStudioConfig baked "http://localhost:1234/v1 " into __init__, which
makes any env-var lookup downstream dead code. The field now defaults to
None and LMStudioLLM resolves config value, then LMSTUDIO_BASE_URL, then
the localhost default, matching the embedder and DeepSeek.
2026-08-13 19:45:57 +05:30
kartik-mem0
08e9cc476c
fix(embeddings/lmstudio): honor LMSTUDIO_BASE_URL env var
...
BaseEmbedderConfig baked "http://localhost:1234/v1 " into the
lmstudio_base_url default, so the attribute was never falsy and the
embedder had no way to tell "unset" from "explicitly localhost". Setting
LMSTUDIO_BASE_URL had no effect.
The default moves to the provider, which now resolves explicit config,
then LMSTUDIO_BASE_URL, then the localhost default, matching how the
OpenAI embedder already reads OPENAI_BASE_URL. The resolved value is
written back to config.lmstudio_base_url, so the attribute still reads
the same after construction.
Closes #6692
2026-08-13 17:36:59 +05:30
Kartik and GitHub
71f2ebefa3
fix(memory): escape delimiters when building the session scope key ( #6892 )
2026-08-11 23:23:55 +05:30
Hrushikesh Yadav and GitHub
35a125585e
fix(pgvector): raise ValueError when 'in'/'nin' filter value is not a list ( #6879 )
2026-08-11 20:15:07 +05:30
Elif Sema Balcioglu and GitHub
6fe6140dba
fix(vector-stores/oracledb): Fix accuracy bug ( #6848 )
2026-08-07 18:07:12 +05:30
Kartik and GitHub
4a0a9a92a6
fix(ts-oss, py): release Oracle client on init failure, validate insert batches ( #6839 )
2026-08-06 18:16:25 +05:30
Saket Aryan and GitHub
12c47f5249
feat(sdk, docs): expose agent_custom_instructions for agent-scoped extraction ( #6809 )
2026-08-05 22:12:10 +05:30
Abhinav Singh and GitHub
45208feebb
fix(memory): stop add() metadata from setting a memory's identity scope ( #6656 )
2026-08-04 16:46:47 +05:30
Hrushikesh Yadav and GitHub
3ac9ba4b50
fix(upstash): escape quotes in filter values and validate filter types ( #5981 )
2026-08-04 15:16:24 +05:30
Kartik and GitHub
8ca9a0f2c0
fix: OSS Python SDK hygiene batch, 9 small bug fixes ( #6770 )
2026-08-03 20:36:28 +05:30
Kartik and GitHub
c90bdbdce0
feat(cli): Platform option parity across Python and Node CLIs (MEM-5893) ( #6696 )
2026-08-03 17:10:44 +05:30
Kartik and GitHub
cf3355e2ca
fix(reranker): align llm_reranker default model with SDK default ( #6703 )
2026-08-01 01:04:08 +05:30
54328ffd97
fix(memory): paginate delete_all across vector store pages ( #6636 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-08-01 00:20:37 +05:30
Kartik and GitHub
29fa41558c
fix(vector-stores): Supabase 1000-row cap, RLS init probe, and col_info crash ( #6695 )
2026-07-31 20:36:41 +05:30
Aari and GitHub
8d45fb3c9a
fix(elasticsearch): set size on KNN search to respect top_k ( #5910 )
2026-07-31 20:32:27 +05:30
Hrushikesh Yadav and GitHub
d653b63fac
fix(milvus): guard text field in update() with _has_bm25_schema check ( #5705 )
2026-07-24 18:27:54 +05:30
01afdde3e7
salvage: fix(opensearch) re-raise search errors (credit @yashwanth123 #6477 ) ( #6519 )
...
Co-authored-by: yashwanth123 <yashwanth123@users.noreply.github.com >
2026-07-24 18:19:26 +05:30
d6d89c987b
Add Oracle Vector Store Integration ( #5358 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-23 21:30:01 +05:30
microbluey and GitHub
56ec7d20f1
fix(vector_stores/opensearch): translate the '*' wildcard to an exists query for every key ( #6522 )
2026-07-23 19:41:09 +05:30
a58e0586ad
fix(vector_stores/opensearch): honor all filter keys instead of a hardcoded identity-key list ( #6454 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-23 00:24:16 +05:30
microbluey and GitHub
a9cb4bb644
fix(vector_stores/chroma): stop dropping filter conditions in where-clause translation ( #6452 )
2026-07-23 00:22:10 +05:30
Gyubin Son and GitHub
7bf84b8d38
fix: drop unused vector column from pgvector get() and list() queries ( #6483 )
2026-07-23 00:11:40 +05:30
Ayaan Gazali and GitHub
14393b5962
fix(llms/anthropic): find the text block in no-tools responses instead of indexing content[0] ( #6481 )
2026-07-22 21:34:48 +05:30
8005e18aec
fix(qdrant): actually clear points on reset() for local Qdrant ( #6412 )
...
Co-authored-by: freya0926 <299410795+freya0926@users.noreply.github.com >
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com >
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-21 13:04:47 +05:30
c2bc28e589
fix(memory): don't let update() metadata overwrite user_id/agent_id/run_id ( #6278 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-21 12:44:22 +05:30
Kartik and GitHub
fec2fe6a2c
fix(vector-stores): scope Pinecone delete_col()/reset() to namespace ( #6287 )
2026-07-21 12:24:57 +05:30
Abhinav Singh and GitHub
726bcc80b2
fix(vector-stores/baidu): convert L2 distance to similarity score in search() ( #6435 )
2026-07-20 12:44:26 +05:30
Jupiter and GitHub
ddaa655edf
fix(llms): honor OPENAI_BASE_URL in structured provider ( #6322 )
2026-07-17 20:45:58 +05:30
Kartik and GitHub
50c3cf44f1
refactor(sdk): remove dead retrieval_criteria parameter ( #6313 )
2026-07-14 20:03:53 +05:30
17836748d7
feat(vector-stores): add Databricks provider to TypeScript OSS SDK ( #5824 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-11 16:35:47 +05:30
c9af55986e
fix(anthropic): Remove sampling parameters when using new model. ( #6211 )
...
Co-authored-by: HJ Qu <35272962+ChristopherQu@users.noreply.github.com >
2026-07-10 21:39:04 +05:30
f69f8dcc7b
fix(weaviate): don't write OutputData model fields as properties on update ( #6149 )
...
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai >
2026-07-10 20:47:59 +05:30
Qun and GitHub
1d383c4ee2
fix(vector-stores): improve milvus wildcard search ( #6187 )
2026-07-10 20:36:22 +05:30
Abhay Singh and GitHub
770ce97bd9
fix(core): coerce non-string entity ids instead of crashing on .strip() ( #6206 )
2026-07-10 20:00:33 +05:30
Abhay Singh and GitHub
44bcfbe1f3
fix(core): don't require langchain-core for default async procedural memory ( #6209 )
2026-07-10 19:59:21 +05:30
Kartik and GitHub
99206f0c64
feat(oss): accept text in Memory.update(), deprecate data ( #6044 )
2026-07-09 19:32:51 +05:30
d122479687
security: fix SQL and Cypher injection vulnerabilities in PGVector, Azure MySQL, and Neptune ( #4878 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-07 16:16:36 +05:30
cc52f0e367
fix: encode dynamic URL path segments ( #5963 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-07 16:11:54 +05:30
Kartik and GitHub
002fe46ab3
feat(ts-sdk): add xAI (Grok) LLM provider to OSS SDK ( #6115 )
2026-07-07 11:29:56 +05:30
9d36b2c94d
feat(ts-sdk): add Upstash Vector vector store ( #5811 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-06 23:41:05 +05:30
4c974c8fa8
Add Together embedder to TS SDK ( #5989 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-07-06 20:24:14 +05:30
Hrushikesh Yadav and GitHub
59484f066f
fix(elasticsearch): validate filter keys and values to prevent term injection ( #5980 )
...
Signed-off-by: Hrushikesh Yadav <yadavhrushikesh65@gmail.com >
2026-07-02 18:35:02 +05:30
Hrushikesh Yadav and GitHub
a36a392cd3
fix(opensearch): validate filter values to prevent term query injection ( #5986 )
2026-07-01 20:47:45 +05:30
Bartok and GitHub
152d1e66f7
fix(embeddings): guard embed_batch count mismatch in OpenAI and Azure OpenAI ( #5966 )
2026-07-01 18:53:28 +05:30
Hrushikesh Yadav and GitHub
bc05fd9623
fix(neptune): escape filter values in openCypher queries to prevent injection ( #5982 )
...
Signed-off-by: Hrushikesh Yadav <yadavhrushikesh65@gmail.com >
2026-07-01 18:48:04 +05:30
Bartok and GitHub
ad7e09851c
fix(memory): re-raise LLM extraction failures instead of returning [] (salvage of #5178 ) ( #5878 )
2026-07-01 18:36:19 +05:30
Kartik and GitHub
754034abbc
Revert "fix(memory): accept llm kwarg in sync Memory.add()/_create_procedural_memory ( #5911 )" ( #5990 )
2026-06-29 21:27:16 +05:30
bedf862d64
fix(memory): accept llm kwarg in sync Memory.add()/_create_procedural_memory ( #5911 ) ( #5953 )
...
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com >
2026-06-29 20:43:35 +05:30
Hrushikesh Yadav and GitHub
3619fd77ae
fix(azure-ai-search): validate filter value types and escape quotes in OData ( #5983 )
2026-06-29 20:31:26 +05:30
Hrushikesh Yadav and GitHub
2dcb3542f8
fix(databricks): validate catalog/schema/table identifiers to prevent SQL injection ( #5988 )
2026-06-29 20:30:27 +05:30
kartik-mem0