Skip to content

Fix hardcoded temperature #4470

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

Merged
merged 1 commit into from
Apr 7, 2025
Merged

Fix hardcoded temperature #4470

merged 1 commit into from
Apr 7, 2025

Conversation

emerzon
Copy link
Contributor

@emerzon emerzon commented Apr 7, 2025

Description

Fixes hardcoded "0" temperature

How Has This Been Tested?

Checked correct temperature being sent to LLM

@emerzon emerzon requested a review from a team as a code owner April 7, 2025 19:26
Copy link

vercel bot commented Apr 7, 2025

@emerzon is attempting to deploy a commit to the Danswer Team on Vercel.

A member of the Team first needs to authorize it.

Copy link
Contributor

@greptile-apps greptile-apps bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

PR Summary

This PR replaces the hardcoded temperature value in the LLM completion call with a dynamic one pulled from the configuration, ensuring consistency with the LLMConfig settings.

  • Updated temperature retrieval in backend/onyx/llm/chat_llm.py replacing the hardcoded “0”.
  • Ensures temperature is dynamically set via the object's configuration, aligning with validated LLMConfig values.
  • Provides runtime flexibility and maintains valid float range for model calls.

💡 (4/5) You can add custom instructions or style guidelines for the bot here!

1 file(s) reviewed, no comment(s)
Edit PR Review Bot Settings | Greptile

@Weves Weves merged commit 88d4a65 into onyx-dot-app:main Apr 7, 2025
3 of 9 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.

2 participants