dify
dify copied to clipboard
Bedrock cohere fix max length 2048
Description
It includes 2 changes:
- For Cohere, count the tokens as text length to avoid 2048 length limitation..
- For others, count the tokens with tiktoken tokennizer, uses gpt-4 instead of gpt2.
Fixes #3942
Type of Change
Please delete options that are not relevant.
- [x] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
- [ ] This change requires a documentation update, included: Dify Document
- [x] Improvement, including but not limited to code refactoring, performance optimization, and UI/UX improvement
- [ ] Dependency upgrade
How Has This Been Tested?
Test with text file with consecutive punctuation marks or long English words. It will failed with expected maxLength: 2048 before. Now it is fixed by counting the tokens as chars.
- [ ] TODO
Suggested Checklist:
- [x] I have performed a self-review of my own code
- [x] have commented my code, particularly in hard-to-understand areas
- [x] My changes generate no new warnings
- [ ] I ran
dev/reformat(backend) andcd web && npx lint-staged(frontend) to appease the lint gods - [ ]
optionalI have made corresponding changes to the documentation - [ ]
optionalI have added tests that prove my fix is effective or that my feature works - [ ]
optionalNew and existing unit tests pass locally with my changes
@kerlion Please resolve the conversation above, we will merge it later.
Hello please fix the conflicts :) dm on wechat if you finished this -> crazyphage
Close for now. You can resolve those conflicts and open a new one.