-
Notifications
You must be signed in to change notification settings - Fork 1.9k
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.
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
feat: Added new max_tokens_limit values and model_names in _openai_text_completion_tokenization_details function in openai_utils.py #7316
Conversation
Sorry, the PR should target the v1.x branch. Can you rebase (or merge v1.x branch) in this PR? |
I apologize for the error. I merged v1.x branch so it should be fine now! |
I'm trying to fix the commit history... |
Oh no! The git history is broken again. git remote add upstream https://github.com/deepset-ai/haystack # maybe not needed
git rebase --interactive upstream/v1.x #here, in the editor I would drop the unrelated commits
git push --force origin v1.25.x # this is your v1.25 branch |
@tradicio Something unexpected happened: your commits have been dropped from the git history. If you have your code locally, just push it again, then ping me and I'll take care of fixing git history. |
Thanks for your help! Now I restored all the changes |
…xt_completion_tokenization_details function in openai_utils.py (#7316) * Added back changes in openai_utils.py and tests are now working * release note --------- Co-authored-by: Tommaso Radicioni <[email protected]> Co-authored-by: anakin87 <[email protected]>
Related Issues
Proposed Changes:
The function _openai_text_completion_tokenization_details(model_name: str) in openai_utils.py now correctly maps the max_tokens_limit values of the gpt-3.5-turbo and gpt-4 models
How did you test it?
I have manually verified the correct max_tokens_limits in the OpenAI webpage https://platform.openai.com/docs/models/overview
Checklist
fix:
,feat:
,build:
,chore:
,ci:
,docs:
,style:
,refactor:
,perf:
,test:
.