feat: add MiniMax as alternative LLM provider for video chat (M3 default)#265
Open
octo-patch wants to merge 2 commits into
Open
feat: add MiniMax as alternative LLM provider for video chat (M3 default)#265octo-patch wants to merge 2 commits into
octo-patch wants to merge 2 commits into
Conversation
Add MiniMax M2.7 as an alternative LLM provider alongside OpenAI GPT-4 in the video_chat_with_ChatGPT component. MiniMax offers an OpenAI-compatible API, enabling users to choose between providers via a Gradio dropdown or the LLM_PROVIDER environment variable. Changes: - chatbot.py: add create_llm() factory with LLM_PROVIDERS registry, ChatOpenAI-based MiniMax integration with temperature clamping - app.py: add LLM Provider dropdown, configurable API key input - README.md: add MiniMax to the provider list in main README - video_chat_with_ChatGPT/README.md: add MiniMax setup instructions - tests/: 25 unit tests + 3 integration tests
- Set MiniMax-M3 as the default model for the minimax provider - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed available - Update README docs and unit-test expectations
octo-patch
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 MiniMax M3 as an alternative LLM provider for the
video_chat_with_ChatGPTcomponent. Users can now choose between OpenAI GPT-4 and MiniMax via a Gradio dropdown or theLLM_PROVIDERenvironment variable. MiniMax-M3 is the default, withMiniMax-M2.7andMiniMax-M2.7-highspeedretained as alternatives.Changes
create_llm()factory with anLLM_PROVIDERSregistry. MiniMax usesChatOpenAIwith an OpenAI-compatible endpoint and clamps temperature to(0.01, 1.0]. Default model isMiniMax-M3.os.environ.get()for the API key.init_agentwith both providers.Why MiniMax-M3?
MiniMax-M3is the latest MiniMax model — 512K context window, up to 128K output, and image input support — providing a high-quality, cost-effective alternative to GPT-4 for reasoning about video descriptions through an OpenAI-compatible API. Older modelsM2.5/M2.1/M2/M1were never wired in;M2.7andM2.7-highspeedremain selectable for users that prefer the previous generation.Test Plan
create_llmfactory, temperature clamping,init_agentwith both providers, env-var fallback) — default-model assertions updated toMiniMax-M3create_llm, chat completion,MiniMax-M2.7-highspeedmodel)