chore: remote provider error handling and chore bug fix #4480
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
louis-jan
changed the title
urmauur
approved these changes
Jan 17, 2025
louis-jan
deleted the
chore/correct-mistral-ai-request-transformation-template
branch
|
This is the build for this pull request. You can download it from the Artifacts section here: Build URL. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Describe Your Changes
This PR resolved the issue where first-time users were directed to the My Models page before the engines were fully populated. Consequently, they were unable to view a comprehensive list of supported engines.
To address this, bump cortex.cpp to the latest RC version to handle the streamed error from remote providers.
This version bump also addressed llava vision model load issue.
Self Checklist
This pull request includes a significant update to the
mistral.jsonfile within theengine-management-extensionresources. The most important change involves the transformation template for chat completions, which has been modified to include a more detailed and specific JSON structure.Improvements to transformation template:
extensions/engine-management-extension/resources/mistral.json: Thetemplatefor thechat_completionsURL has been updated to selectively include specific keys from theinput_requestand format them into a JSON object. This change ensures that only relevant keys are included in the request payload, improving the accuracy and efficiency of the transformation process.