support local llm using ollama, lm-studio or any other OpenAPI-compatible local servers #5
Conversation
This file contains hidden or 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
…ible local servers hardcoded local server URL is: http//localhost:1234 - default from LM Studio - imported partial working code from Yhozen:feat/ai-sdk - add new model-context - extension-model ui component - use model context inside chat and summary - add new background port to auto-retrieve available models from local server - improve select ui adding tabs for Online and Local models
Owner
|
Thank you for your contribution @b3nab! The updates you've made, the integration of the local server support, look great. I really appreciate the way you've extended the work from the @Yhozen Yhozen:feat/ai-sdk branch to enhance the model management capabilities. I'll take a closer look at the changes soon and plan to merge them afterward. You've done a fantastic job with this great work! 🍒. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
hardcoded local server URL is: http//localhost:1234 - default from LM Studio
Briefly I took the work you were already doing with @Yhozen from the Yhozen:feat/ai-sdk branch and extended it to support a local server. I didn't went down the path to fully create an interface to manage settings like the url of the server (or other things like editing the prompts with proper {variables} for transcript, video title etc..) so I hardcoded it to the default server url from LM Studio.
I wanted to share this, feel free to do whatever you want with this code. 😆
Great work done with this extension @PaoloJN , this local llm feature is just the cherry on top 🍒 .