a4633aa065
docs(api-reference): address reviewer comments on search defaults table and retrieval_criteria shape
...
- search-memories.mdx: collapse V1/V2/V3 comparison table to a single "Default" column showing current (v3) values only (threshold 0.1, rerank false, top_k 10)
- organizations-projects.mdx: replace bogus {role, content} retrieval_criteria examples with the correct {name, description, weight} shape, mirroring the canonical criteria-retrieval.mdx examples; update prose to name the three required fields
2026-06-26 16:48:19 +05:30
711f866e59
docs(api-reference): use literal em-dash instead of \u2014 escape in openapi.json
2026-06-26 16:03:50 +05:30
46757cb1fb
docs(api-reference): document project.update() retrieval_criteria and decay params
2026-06-25 14:02:51 +05:30
bbfe0f9bb2
docs(api-reference): align API docs and openapi schema with v3 spec
...
- create-memory-export.mdx: replace `session_id` filter with `app_id`
(spec: /v1/exports/ filters = user_id, agent_id, app_id, run_id)
- get-memory-export.mdx: replace stale filter list (session_id removed)
with correct fields: user_id, agent_id, app_id, run_id, created_at, updated_at
- search-memories.mdx: fix comparison table — rerank V1/V2 default was
`true`, spec shows `false`; threshold V1 is absent (not "No default"),
V2 default is 0.3 (not absent)
- organizations-projects.mdx: rewrite Key Capabilities bullet — org/project
are NOT init params; they resolve automatically from the API key via /v1/ping/
- openapi.json DELETE /v1/batch/: fix request schema from {memory_ids:[uuid]}
to {memories:[{memory_id:uuid}]} to match Python client.batch_delete()
- openapi.json PUT /v1/batch/: make `text` optional (remove from required),
add optional `metadata` property — matches Python client.batch_update() docstring
2026-06-25 12:01:24 +05:30
ac296f7534
docs: make example code fences copy-safe ( #5833 )
2026-06-24 22:19:40 -07:00
ac8f862ff7
fix(mem0-plugin): store files_touched as a list to stop double JSON-encoding ( #5806 )
2026-06-25 09:06:11 +05:30
b33fa5427c
fix(memory): align entity extraction precision ( #5829 )
...
Making the entity extraction function cleaner
Co-authored-by: Soumil Rathi <soumilrathi@gmail.com >
2026-06-24 15:48:37 -07:00
5d573dd2ae
docs: added typescript support to deepseek provider ( #5723 )
2026-06-24 20:55:14 +05:30
98dbf90864
chore: update changelog, bump SDK versions to Python 2.0.8 and TypeScript 3.0.10 ( #5825 )
2026-06-24 20:21:06 +05:30
6ddf1669f4
fix(vector_stores): point fastembed-missing warning at mem0ai[extras] ( #5622 )
2026-06-24 14:47:02 +05:30
d3d2e89fd5
fix(llms): skip JSON response_format for Groq compound models ( #5513 )
2026-06-24 14:42:22 +05:30
43175d85f2
fix: preserve empty Azure AI Search update values ( #5524 )
...
Signed-off-by: Xiaoju <xiaojuchh@gmail.com >
2026-06-24 14:41:55 +05:30
661ecb9f0f
docs(hermes): update for v3 API, OSS self-hosted mode, and new tools ( #5807 )
2026-06-24 11:59:13 +05:30
09f181c577
fix(server): fetch filtered dashboard memories beyond default page ( #5753 )
2026-06-24 11:49:06 +05:30
3497f26a00
fix: add auto_refresh option for OpenSearch Serverless compatibility ( #3893 )
...
Co-authored-by: Zaid Malhis <Malhis@users.noreply.github.com >
2026-06-24 11:48:52 +05:30
e9c0547423
fix(ts-sdk): preserve customCategories names through key conversion ( #5741 )
2026-06-24 11:15:19 +05:30
25bc1b7426
fix(memory): guard against malformed image_url in parse_vision_messages ( #5631 )
2026-06-24 11:10:36 +05:30
fee344db85
fix(chroma): wrap scalar vector_id in list for delete() ( #5703 )
2026-06-24 10:54:36 +05:30
b611f69381
fix(chroma): wrap update() ids/embeddings/metadatas in lists ( #5757 )
2026-06-24 10:54:15 +05:30
c2862831db
fix(reranker): log reranking failures instead of swallowing them silently ( #5717 )
2026-06-24 10:44:37 +05:30
1678e682ee
fix(ts-sdk): check message.role instead of content for system messages ( #3921 )
2026-06-23 17:18:00 +05:30
ced4af681f
fix(claude-plugin): rerank auto-injected memory context by default ( #5690 )
2026-06-23 16:52:35 +05:30
565db27121
fix(milvus,baidu): sanitize filter values to prevent expression injection ( #5746 )
2026-06-23 16:51:05 +05:30
c0ac9f81fa
fix(milvus): wrap scalar vector_id in list for delete() ( #5704 )
2026-06-23 16:48:47 +05:30
879c68555c
fix(memory): return attributed_to from get/get_all/search ( #5629 )
2026-06-23 16:43:30 +05:30
c2e723352e
fix(ts-oss): return attributedTo from get/search/getAll ( #5675 )
2026-06-23 16:42:57 +05:30
716f021df8
fix(pinecone): map all comparison operators in _create_filter() ( #5707 )
2026-06-23 16:38:28 +05:30
7fa996261d
perf: batch BM25 sparse encoding in Qdrant insert ( #5592 )
2026-06-23 16:29:16 +05:30
87bd2d91e0
fix(llms): preserve reasoning fields in base-to-provider config conversion ( #5638 )
2026-06-23 16:27:43 +05:30
15a930dac2
fix(llms): pass configured anthropic_base_url to the Anthropic client ( #5626 )
2026-06-23 16:26:22 +05:30
fa9abc77a6
fix(ts-oss): honor configured baseURL in AnthropicLLM ( #5740 )
2026-06-23 16:25:51 +05:30
4e448269bc
fix(mongodb): reject dict filter values to prevent NoSQL operator injection ( #5748 )
2026-06-22 18:09:01 +05:30
29d131f7aa
fix(chroma): return None instead of {} from _generate_where_clause for empty filters ( #5713 )
2026-06-22 12:05:28 +05:30
42fe129330
fix(opensearch): return [[]] from list() error path to honor list() contract ( #5727 )
2026-06-22 11:58:37 +05:30
bd5996f41e
fix(pinecone): return [[]] from list() error path instead of dict ( #5706 )
2026-06-22 11:57:52 +05:30
299c423213
fix(faiss): return [[]] for uninitialized index to honor list() contract ( #5725 )
2026-06-22 11:57:06 +05:30
ce0531a13e
fix(mongodb): wrap list() return in outer list to match interface contract ( #5729 )
2026-06-22 11:54:16 +05:30
513b56159f
fix(embeddings): forward embedding_dims to Titan V2 in AWS Bedrock embedder ( #5671 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-22 11:49:23 +05:30
1676b3168d
fix(server): return 404/400 instead of 502 for not-found and invalid input ( #5634 )
2026-06-22 11:47:48 +05:30
8a786bf72d
fix(azure): stop mutating and corrupting caller messages in content rewrite ( #5731 )
2026-06-22 11:45:46 +05:30
a48f34cf77
fix(vector_stores): deep-copy Redis DEFAULT_FIELDS so instances keep distinct dims ( #5633 )
2026-06-22 11:29:25 +05:30
650b734b1b
fix: reset() only drops history table, leaving stale messages ( #5541 )
2026-06-22 11:28:17 +05:30
871a1de7d2
docs: fix add memory v3 behavior ( #5694 )
2026-06-21 12:18:58 -07:00
e615cc66de
docs: rebrand Keywords AI integration to Respan ( #5098 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai >
2026-06-20 23:10:15 +05:30
ca86a164bd
fix(pi-agent-plugin): resolve undici CVE-2026-9697 / CVE-2026-9678 ( #5669 )
2026-06-19 16:21:18 +05:30
2ac3f3956a
fix(cli): pass telemetry context via stdin instead of argv ( #5668 )
...
Co-authored-by: JunghwanNA <70629228+shaun0927@users.noreply.github.com >
2026-06-19 13:57:53 +05:30
7a9f03af3f
fix(llms,embeddings): repair HTTP proxy support (httpx>=0.28) and preserve proxies in LlmFactory ( #5447 )
...
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai >
2026-06-19 13:45:21 +05:30
48f1d6f010
fix(reranker): clamp out-of-range LLM scores instead of mis-parsing them ( #5635 )
2026-06-19 12:49:50 +05:30
f0ccd99924
fix(vertex): pass required vectors arg in list and similarity search ( #5627 )
2026-06-19 12:44:48 +05:30
c5971193a2
fix(vector_stores): return None from Redis.get() for missing IDs ( #5625 )
...
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com >
Co-authored-by: Kartik <kartik.labhshetwar@mem0.ai >
2026-06-19 12:25:24 +05:30
kartik-mem0