Skip to content

Dev 20260126 v2.0.4 #976

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
CarltonXiang wants to merge 13 commits into
base: main
Choose a base branch
from
Open

Dev 20260126 v2.0.4 #976

CarltonXiang wants to merge 13 commits into from

Conversation

@CarltonXiang
Copy link
Collaborator

@CarltonXiang CarltonXiang commented Jan 28, 2026

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

bittergreen and others added 13 commits January 26, 2026 21:20
@bittergreen
feat: add recaller for fast-add process (#958)
9245076 
* feat: add recaller for fast-add process

* feat: add recaller for fast-add process
@CarltonXiang @CaralHsi
chore: update pr template (#959)
ffcea2f 
Co-authored-by: harvey_xiang <harvey_xiang22@163.com>
Co-authored-by: CaralHsi <caralhsi@gmail.com>
@Wang-Daoji @endxxxx
feat: skill memory (#964)
cd76b04 
* feat: skill memory

* feat: split task chunks for skill memories

* fix: refine the returned format from llm and parsing

* feat: add new pack oss

* feat: skill mem pipeline

* feat: fill code

* feat: modify code

* feat: modify code

* feat: async add skill memory

* feat: update ollama version

* feat: get memory return skill memory

* feat: get api add skill mem

* feat: get api add skill mem

* feat: modify env config

* feat: back set oss client

* feat: delete tmp skill code

* feat: process new package import error

* feat: modify oss config

---------

Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local>
Co-authored-by: Wenqiang Wei <wwq38556399@163.com>
@wustzdy
feat: fix get_nodes (#971)
7a018bd 
* feat: fix get_nodes

* feat: fix get_nodes

* feat: fix get_nodes

* feat: optimize get_nodes
@Wang-Daoji @endxxxx
feat: skill memory (#972)
42bbd0a 
* feat: skill memory

* feat: split task chunks for skill memories

* fix: refine the returned format from llm and parsing

* feat: add new pack oss

* feat: skill mem pipeline

* feat: fill code

* feat: modify code

* feat: modify code

* feat: async add skill memory

* feat: update ollama version

* feat: get memory return skill memory

* feat: get api add skill mem

* feat: get api add skill mem

* feat: modify env config

* feat: back set oss client

* feat: delete tmp skill code

* feat: process new package import error

* feat: modify oss config

* feat: modiy prompt and add two api

---------

Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local>
Co-authored-by: Wenqiang Wei <wwq38556399@163.com>
@Wang-Daoji @endxxxx
feat: skill memory (#974)
57ad88a 
* feat: skill memory

* feat: split task chunks for skill memories

* fix: refine the returned format from llm and parsing

* feat: add new pack oss

* feat: skill mem pipeline

* feat: fill code

* feat: modify code

* feat: modify code

* feat: async add skill memory

* feat: update ollama version

* feat: get memory return skill memory

* feat: get api add skill mem

* feat: get api add skill mem

* feat: modify env config

* feat: back set oss client

* feat: delete tmp skill code

* feat: process new package import error

* feat: modify oss config

* feat: modiy prompt and add two api

* feat: modify prompt

---------

Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local>
Co-authored-by: Wenqiang Wei <wwq38556399@163.com>
@CaralHsi
fix: playground chat bug & search_by_embedding in add process (#973)
f2e725e 
* chore: update version to 2.0.4

* fix: playground chat bug (#968)

* feat: add timer for split text

* feat: add chat_handler log

* feat: add chat_handler log

* fix: chat in playgound bug: use index in null list

* chore: deprecated warning

* fix: we don't use  query when search in graph-db

* chore: revert version to 2.0.3

---------

Co-authored-by: harvey_xiang <harvey_xiang22@163.com>
@bittergreen @CaralHsi
Add NLI model for fast detection of duplication/conflict. (#970)
4fd72bb 
* feat: Add NLI model server/client code for fast detection of duplication/conflict.

* test: Add test and example for NLI model.

* feat: Init the NLI client when the server initializes.

* fix: Avoid direct import of torch and transformers for the external NLI server.

---------

Co-authored-by: CaralHsi <caralhsi@gmail.com>
@Wang-Daoji @endxxxx
feat: skill memory (#981)
c91be79 
* feat: skill memory

* feat: split task chunks for skill memories

* fix: refine the returned format from llm and parsing

* feat: add new pack oss

* feat: skill mem pipeline

* feat: fill code

* feat: modify code

* feat: modify code

* feat: async add skill memory

* feat: update ollama version

* feat: get memory return skill memory

* feat: get api add skill mem

* feat: get api add skill mem

* feat: modify env config

* feat: back set oss client

* feat: delete tmp skill code

* feat: process new package import error

* feat: modify oss config

* feat: modiy prompt and add two api

* feat: modify prompt

* feat: modify code

---------

Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local>
Co-authored-by: Wenqiang Wei <wwq38556399@163.com>
@hijzy @CaralHsi @CarltonXiang
feat: add mmr deduplication (#954)
6e5e2c4 
* test: add mmr dedup

* test: decrease lambda

* test: add tag penalty

* test: increase lambda_relevance

* test: fix top 5 candidates

* test: adjust alpha_tag

* test: increase lambda_relevance

* test: decrease lambda_relevance

* test: adjust params

* test: delete tag penalty

* test: delete fix top5

* test: readd fix top5

* test: delete threshold-based penalties

* test: delete threshold-based penalties

* test: restore best score version, add resort

* chore: update version to 2.0.4

* test: add diversity

* test: reformat

* fix: playground chat bug (#968)

* feat: add timer for split text

* feat: add chat_handler log

* feat: add chat_handler log

* fix: chat in playgound bug: use index in null list

* chore: deprecated warning

* fix: we don't use  query when search in graph-db

* fix: fix Nan and 0 embedding

* feat: add mmr deduplication

* feat: add preference memory deduplication

* fix: recall less preference memory

* test: memory text deduplication

* test: memory text deduplication

* test: restore

* test: restore

* test: add 2 gram dedup

* test: add more dedup

* chore: revert version to 2.0.3

* test: 增大 prefill

* test: 调整阈值参数

* fix: reformat

* fix: reformat

* fix: reformat

* fix: reformat

* fix: reformat

* fix: reformat

* fix: use deepcopy, add log

* fix: reformat

---------

Co-authored-by: harvey_xiang <harvey_xiang22@163.com>
Co-authored-by: CaralHsi <caralhsi@gmail.com>
Co-authored-by: HarveyXiang <harvey_xiang@163.com>
@Wang-Daoji @endxxxx
feat: skill memory (#982)
8a5e1ed 
* feat: skill memory

* feat: split task chunks for skill memories

* fix: refine the returned format from llm and parsing

* feat: add new pack oss

* feat: skill mem pipeline

* feat: fill code

* feat: modify code

* feat: modify code

* feat: async add skill memory

* feat: update ollama version

* feat: get memory return skill memory

* feat: get api add skill mem

* feat: get api add skill mem

* feat: modify env config

* feat: back set oss client

* feat: delete tmp skill code

* feat: process new package import error

* feat: modify oss config

* feat: modiy prompt and add two api

* feat: modify prompt

* feat: modify code

* feat: add logger

---------

Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local>
Co-authored-by: Wenqiang Wei <wwq38556399@163.com>
@endxxxx @CaralHsi
fix: embedding service timeout occasionally (#983)
b39df53 
* chore: update version to 2.0.4

* fix: embedding service timeout occasionally

* style: remove useless comment

* fix: add standby link for embedding

* fix: remove timeout attribute from UniversalEmbedderConfig

* fix: timeout parameter format error

* fix: add backup client when creating embedder

* style: adjust the log printing position

---------

Co-authored-by: harvey_xiang <harvey_xiang22@163.com>
Co-authored-by: CaralHsi <caralhsi@gmail.com>
@Wang-Daoji @endxxxx
feat: skill memory (#984)
fd25c3d 
* feat: skill memory

* feat: split task chunks for skill memories

* fix: refine the returned format from llm and parsing

* feat: add new pack oss

* feat: skill mem pipeline

* feat: fill code

* feat: modify code

* feat: modify code

* feat: async add skill memory

* feat: update ollama version

* feat: get memory return skill memory

* feat: get api add skill mem

* feat: get api add skill mem

* feat: modify env config

* feat: back set oss client

* feat: delete tmp skill code

* feat: process new package import error

* feat: modify oss config

* feat: modiy prompt and add two api

* feat: modify prompt

* feat: modify code

* feat: add logger

* feat: fix bug in memory id

---------

Co-authored-by: yuan.wang <yuan.wang@yuanwangdebijibendiannao.local>
Co-authored-by: Wenqiang Wei <wwq38556399@163.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

8 participants

@CarltonXiang @bittergreen @Wang-Daoji @wustzdy @CaralHsi @hijzy @endxxxx