Skip to content
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

[Bug]: Performance improvements on RAG analyzer for long text #2159

Open
1 task done
yingfeng opened this issue Nov 1, 2024 · 0 comments
Open
1 task done

[Bug]: Performance improvements on RAG analyzer for long text #2159

yingfeng opened this issue Nov 1, 2024 · 0 comments
Labels
bug Something isn't working

Comments

@yingfeng
Copy link
Member

yingfeng commented Nov 1, 2024

Is there an existing issue for the same bug?

  • I have checked the existing issues.

Version or Commit ID

f9ef948

Other environment information

No response

Actual behavior and How to reproduce it

Related with #2147, the OOM issue has been fixed by #2154
The performance should be also improved. The following long text will take more than 80s for tokenization.

湘西土家族苗族自治州人民政府办公室湘西土家族苗族自治州发展和改革委员会湘西土家族苗族自治州财政局湘西土家族苗族自治州经信委湘西土家族苗族自治州教育局湘西土家族苗族自治州科技局湘西土家族苗族自治州民委湘西土家族苗族自治州公安局湘西土家族苗族自治州监察局湘西土家族苗族自治州民政局湘西土家族苗族自治州司法局湘西土家族苗族自治州人力资源和社会保障局湘西土家族苗族自治州国土资源局湘西土家族苗族自治州住建局湘西土家族苗族自治州交通运输局湘西土家族苗族自治州水利局湘西土家族苗族自治州农业局湘西土家族苗族自治州林业局湘西土家族苗族自治州商务局湘西土家族苗族自治州文广新局湘西土家族苗族自治州卫生局湘西土家族苗族自治州计划生育委员会湘西土家族苗族自治州审计局湘西土家族苗族自治州环保局湘西土家族苗族自治州统计局湘西土家族苗族自治州物价局湘西土家族苗族自治州安监局湘西土家族苗族自治州旅游局湘西土家族苗族自治州食品药品监督局湘西土家族苗族自治州体育局湘西土家族苗族自治州无线电管理处湘西

Expected behavior

No response

Additional information

No response
@yingfeng yingfeng added the bug Something isn't working label Nov 1, 2024
@yingfeng yingfeng mentioned this issue Nov 5, 2024
Merged
2 tasks
yingfeng added a commit that referenced this issue Nov 5, 2024
@yingfeng
Improve performance of RAG tokenizer (#2177)
bcde525 
### What problem does this PR solve?

- Split long text into short ones. Further improvements are required for
smarter splitting.
- Fix deadlock of memory_indexer during offline building.

Issue link:#2159

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Performance Improvement
@yingfeng yingfeng changed the title [Bug]: Performance improvements on RAG analyzer for long text [Feature Request]: Performance improvements on RAG analyzer for long text Nov 13, 2024
@yingfeng yingfeng mentioned this issue Nov 13, 2024
Merged
4 tasks
@yingfeng yingfeng changed the title [Feature Request]: Performance improvements on RAG analyzer for long text [Bug]: Performance improvements on RAG analyzer for long text Nov 13, 2024
yingfeng pushed a commit that referenced this issue Nov 15, 2024
@yangzq50
Update rag analyzer (#2232)
ba0ceb8 
### What problem does this PR solve?

* Add `RAGAnalyzer::GetBestTokens` function
 It is now only for test in Debug mode
 It differs with dfs in some cases
* Fix some existing bugs

Issue link:#2159

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
- [x] Test cases
@yangzq50 yangzq50 mentioned this issue Nov 15, 2024
Merged
2 tasks
yingfeng pushed a commit that referenced this issue Nov 15, 2024
@yangzq50
Update rag analyzer (#2249)
1ddde0a 
### What problem does this PR solve?

Support a new score function
Support get topn result by dp

Issue link:#2159

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
@yangzq50 yangzq50 mentioned this issue Nov 20, 2024
Merged
2 tasks
yingfeng pushed a commit that referenced this issue Nov 20, 2024
@yangzq50
Update rag_analyzer.cpp (#2273)
7b3ba74 
### What problem does this PR solve?

Improve performance of `RAGAnalyzer::GetBestTokensTopN`, reduce memory
cost

Issue link:#2159

### Type of change

- [x] Refactoring
- [x] Performance Improvement
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@yingfeng