feat(minimax): add LLM provider support#5170
Open
octo-patch wants to merge 2 commits intolivekit:mainfrom
Open
feat(minimax): add LLM provider support#5170octo-patch wants to merge 2 commits intolivekit:mainfrom
octo-patch wants to merge 2 commits intolivekit:mainfrom
Conversation
The existing MiniMax plugin only supports TTS. This adds LLM support by extending the OpenAI-compatible LLM base class, following the same pattern used by the Groq plugin. Supported models: MiniMax-M2.7, MiniMax-M2.5, MiniMax-M2.5-highspeed Changes: - Add llm.py with LLM class extending OpenAILLM - Update __init__.py to export LLM - Update pyproject.toml to add openai dependency - Update README.md with LLM usage docs - Add 9 unit tests and 3 integration tests Co-Authored-By: octopus <noreply@github.com>
|
|
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
Member
|
Hi, thanks for the PR! Could you sign the CLA? |
Author
|
@tinalenguyen thanks, already signed it. |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add LLM provider support to the existing MiniMax plugin, which currently only supports TTS.
The MiniMax LLM API is OpenAI-compatible, so the implementation follows the same pattern used by the Groq plugin — extending
OpenAILLMwith MiniMax-specific defaults (base URL, API key, models).Changes
llm.py: NewLLMclass extendingOpenAILLMwith MiniMax base URL (https://api.minimax.io/v1) andMINIMAX_API_KEYenv var support__init__.py: Export the newLLMclass alongside existingTTSpyproject.toml: Addopenaiextra dependency (required byOpenAILLMbase class), fix descriptionREADME.md: Add LLM usage documentationtests/test_minimax_llm.py: 9 unit tests + 3 integration testsSupported Models
MiniMax-M2.7(default, latest)MiniMax-M2.5MiniMax-M2.5-highspeed(204K context)Usage
Test plan