Skip to content

Developer Tools > Test a Conversation Prompt Updated to use 4.1#2438

Merged
smian1 merged 2 commits intoBasedHardware:mainfrom
smian1:main
May 24, 2025
Merged

Developer Tools > Test a Conversation Prompt Updated to use 4.1#2438
smian1 merged 2 commits intoBasedHardware:mainfrom
smian1:main

Conversation

@smian1
Copy link
Copy Markdown
Collaborator

@smian1 smian1 commented May 24, 2025

Refactor conversation processing to utilize llm_medium_experiment (4.1) for Developer Tools > Test a Conversation Prompt

@smian1 smian1 requested a review from Copilot May 24, 2025 23:25
@vercel
Copy link
Copy Markdown

vercel Bot commented May 24, 2025

@smian1 is attempting to deploy a commit to the kodjima33's projects Team on Vercel.

A member of the Team first needs to authorize it.

Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull Request Overview

Refactors the summary generation function to use the upgraded llm_medium_experiment (4.1) model instead of llm_mini.

  • Swaps out the LLM invocation in generate_summary_with_prompt
  • Redirects summary calls to the new llm_medium_experiment interface
Comments suppressed due to low confidence (2)

backend/utils/llm/conversation_processing.py:260

  • Add or update unit tests to verify that generate_summary_with_prompt correctly invokes llm_medium_experiment and returns its response, ensuring behavior remained consistent after the model swap.
response = llm_medium_experiment.invoke(prompt)

backend/utils/llm/conversation_processing.py:260

  • [nitpick] Switching to a higher-capability model may increase latency or cost; consider documenting this trade-off or implementing a timeout/retry strategy if needed.
response = llm_medium_experiment.invoke(prompt)

@smian1 smian1 merged commit b61bb8c into BasedHardware:main May 24, 2025
1 check failed
Glucksberg pushed a commit to Glucksberg/omi-local that referenced this pull request Apr 28, 2026
…dHardware#2438)

Refactor conversation processing to utilize llm_medium_experiment (4.1)
for Developer Tools > Test a Conversation Prompt
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