Skip to content

Conversation

@fridayL
Copy link
Collaborator

@fridayL fridayL commented Oct 20, 2025

Description

Summary: (summary)

Fix: #(issue)

Docs Issue/PR: (docs-issue-or-pr-link)

Reviewer: @(reviewer)

Checklist:

  • I have performed a self-review of my own code | 我已自行检查了自己的代码
  • I have commented my code in hard-to-understand areas | 我已在难以理解的地方对代码进行了注释
  • I have added tests that prove my fix is effective or that my feature works | 我已添加测试以证明我的修复有效或功能正常
  • I have created related documentation issue/PR in MemOS-Docs (if applicable) | 我已在 MemOS-Docs 中创建了相关的文档 issue/PR(如果适用)
  • I have linked the issue to this PR (if applicable) | 我已将 issue 链接到此 PR(如果适用)
  • I have mentioned the person who will review this PR | 我已提及将审查此 PR 的人

fridayL and others added 19 commits September 10, 2025 16:27
## This PR introduces multiple major updates across MemOS, focusing on
evaluation, request context/logging, graph DB backends,
retrieval/quoting, API capabilities, and prompts/templates.

<!--
Please include a summary of the changes below;
Fill in the issue number that this PR addresses (if applicable);
Fill in the related MemOS-Docs repository issue or PR link (if
applicable);
Mention the person who will review this PR (if you know who it is);
Replace (summary), (issue), (docs-issue-or-pr-link), and (reviewer) with
the appropriate information.

请在下方填写更改的摘要;
填写此 PR 解决的问题编号(如果适用);
填写相关的 MemOS-Docs 仓库 issue 或 PR 链接(如果适用);
提及将审查此 PR 的人(如果您知道是谁);
替换 (summary)、(issue)、(docs-issue-or-pr-link) 和 (reviewer) 为适当的信息。
-->

Summary:

- **Evaluation**: Added LoCoMo RAG & LongMemEval scripts with
reproducible run commands.

- **API & Middleware**: Introduced request context and middleware for
trace IDs and multi-user support; added non-streaming Chat Complete and
“further questions” generation.

- **Logging & Observability**: Implemented custom logger with trace ID,
and asynchronous handling for logs, notifications, and memory writes.

- **Graph Backends**: Improved NebulaGraph session pool management and
stability; fixed Neo4j Community bug.

- **Retrieval & References**: Enabled memos_cube-scoped retrieval,
adjusted reference display/format, and added reject-answer path.

- **Prompts & Templates**: Added multilingual templates and refined Mem
Reader prompt.

- **LLM & Examples**: Updated vLLM adapter, fixed multi-user example,
added user_id field to general_text.

- **Testing**: Added/updated tests for request context, memory reader,
searcher, and logging.

Fix: #(issue)

Docs Issue/PR: (docs-issue-or-pr-link)

Reviewer: @(reviewer)

## Checklist:

- [ ] I have performed a self-review of my own code | 我已自行检查了自己的代码
- [ ] I have commented my code in hard-to-understand areas |
我已在难以理解的地方对代码进行了注释
- [ ] I have added tests that prove my fix is effective or that my
feature works | 我已添加测试以证明我的修复有效或功能正常
- [ ] I have created related documentation issue/PR in
[MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) (if applicable) |
我已在 [MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) 中创建了相关的文档
issue/PR(如果适用)
- [ ] I have linked the issue to this PR (if applicable) | 我已将 issue
链接到此 PR(如果适用)
- [ ] I have mentioned the person who will review this PR | 我已提及将审查此 PR
的人
## Description

<!--
Please include a summary of the changes below;
Fill in the issue number that this PR addresses (if applicable);
Fill in the related MemOS-Docs repository issue or PR link (if
applicable);
Mention the person who will review this PR (if you know who it is);
Replace (summary), (issue), (docs-issue-or-pr-link), and (reviewer) with
the appropriate information.

请在下方填写更改的摘要;
填写此 PR 解决的问题编号(如果适用);
填写相关的 MemOS-Docs 仓库 issue 或 PR 链接(如果适用);
提及将审查此 PR 的人(如果您知道是谁);
替换 (summary)、(issue)、(docs-issue-or-pr-link) 和 (reviewer) 为适当的信息。
-->

Summary: (summary)

Fix: #(issue)

Docs Issue/PR: (docs-issue-or-pr-link)

Reviewer: @(reviewer)

## Checklist:

- [ ] I have performed a self-review of my own code | 我已自行检查了自己的代码
- [ ] I have commented my code in hard-to-understand areas |
我已在难以理解的地方对代码进行了注释
- [ ] I have added tests that prove my fix is effective or that my
feature works | 我已添加测试以证明我的修复有效或功能正常
- [ ] I have created related documentation issue/PR in
[MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) (if applicable) |
我已在 [MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) 中创建了相关的文档
issue/PR(如果适用)
- [ ] I have linked the issue to this PR (if applicable) | 我已将 issue
链接到此 PR(如果适用)
- [ ] I have mentioned the person who will review this PR | 我已提及将审查此 PR
的人
## Description

<!--
Please include a summary of the changes below;
Fill in the issue number that this PR addresses (if applicable);
Fill in the related MemOS-Docs repository issue or PR link (if
applicable);
Mention the person who will review this PR (if you know who it is);
Replace (summary), (issue), (docs-issue-or-pr-link), and (reviewer) with
the appropriate information.

请在下方填写更改的摘要;
填写此 PR 解决的问题编号(如果适用);
填写相关的 MemOS-Docs 仓库 issue 或 PR 链接(如果适用);
提及将审查此 PR 的人(如果您知道是谁);
替换 (summary)、(issue)、(docs-issue-or-pr-link) 和 (reviewer) 为适当的信息。
-->

Summary: 
Added OpenTelemetry support (MemTensor#298, MemTensor#307).
Introduced OpenTelemetry to enhance observability and monitoring for the
system, helping to trace requests and measure system performance.

Chatbot API and reranker filter, fixed Pydantic bug (MemTensor#294, MemTensor#303).
Added a new chatbot API and incorporated a reranker filter to improve
the response quality. Also, fixed issues related to Pydantic validation
errors.

Updated Nebula to version 5.1.1 (MemTensor#311).
Updated to the latest version of Nebula (5.1.1), addressing any known
bugs and ensuring better performance with the new features.

Parallelized recall and searcher processes (MemTensor#337).
Improved the performance of recall and search operations by
parallelizing them, allowing for faster query handling.

Added API client feature (MemTensor#334).
Introduced a new API client to facilitate easier interactions with the
system's API, likely for external integrations.


Fix: 
Fixed bugs in retriever, and added new auth info for Neo4j DB (MemTensor#313).
Addressed bugs in the retriever and improved authentication handling for
the Neo4j database, ensuring more reliable connections and data
retrieval.

Docs Issue/PR: (docs-issue-or-pr-link)

Reviewer: @(reviewer)

## Checklist:

- [x] I have performed a self-review of my own code | 我已自行检查了自己的代码
- [x] I have commented my code in hard-to-understand areas |
我已在难以理解的地方对代码进行了注释
- [ ] I have added tests that prove my fix is effective or that my
feature works | 我已添加测试以证明我的修复有效或功能正常
- [ ] I have created related documentation issue/PR in
[MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) (if applicable) |
我已在 [MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) 中创建了相关的文档
issue/PR(如果适用)
- [ ] I have linked the issue to this PR (if applicable) | 我已将 issue
链接到此 PR(如果适用)
- [ ] I have mentioned the person who will review this PR | 我已提及将审查此 PR
的人
* feat: add memory size config in product api

* fix: memory_size config bug
* fix: nebula search bug

* fix: nebula search bug

* fix: auto create bug

* feat: add single-db-only assertion

* feat: make count_nodes support optional memory_type filtering

* fix: dim_field when filter non-embedding nodes

* feat: add optional whether include embedding when export graph

* fix[WIP]: remove oldest memory update

* feat: modify nebula search embedding efficiency

* fix: modify nebula remove old memory
* fix: api client get_message models

* fix: format error

---------

Co-authored-by: chunyu li <78344051+fridayL@users.noreply.github.com>
Co-authored-by: harvey_xiang <harvey_xiang22@163.com>
Co-authored-by: CaralHsi <caralhsi@gmail.com>
…efficiency (MemTensor#363)

* feat: only single-db mode in nebula now; modify index gql for better effciency

* feat: delete multi-db nebula example
@fridayL fridayL merged commit e1de4ad into MemTensor:test Oct 20, 2025
20 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants