feat: add MiniMax as a supported LLM provider with M3 as default - #815
Open
octo-patch wants to merge 3 commits into
Open
feat: add MiniMax as a supported LLM provider with M3 as default#815octo-patch wants to merge 3 commits into
octo-patch wants to merge 3 commits into
Conversation
Add native support for MiniMax large language models (MiniMax-M2.5, MiniMax-M2.5-highspeed) via their OpenAI-compatible API endpoint. Changes: - Add ChatMiniMax class extending ChatOpenAI with MiniMax-specific defaults and parameter handling (temperature clamping, response_format removal) - Register ChatMiniMax in LLMManager vendors for UI model selection - Add default MiniMax configuration in flowsettings.py - Add MINIMAX_API_KEY to .env.example - Add unit test for ChatMiniMax - Update README to mention MiniMax in supported providers Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list - Set MiniMax-M2.7 as default model - Keep all previous models as alternatives - Update related tests
octo-patch
changed the title
- Add MiniMax-M3 to model list and set as default - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed - Remove older models (M2.5/M2.5-highspeed) - Update related tests
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Changes
libs/kotaemon/kotaemon/llms/chats/minimax.py— ChatMiniMax class extending ChatOpenAI; defaultMiniMax-M3libs/ktem/ktem/llms/manager.py— Register ChatMiniMax as vendorflowsettings.py— Default MiniMax config usesMiniMax-M3.env.example—MINIMAX_API_KEYplaceholderREADME.md— MiniMax documentation listing M3 (default), M2.7, M2.7-highspeedlibs/kotaemon/tests/test_llms_chat_models.py— Unit tests verifying M3 as default and M2.7 backward compatibilityWhy
MiniMax-M3 is the latest flagship model, providing a 512K context window, up to 128K output, and image input via the OpenAI-compatible endpoint. Keeping M2.7 and M2.7-highspeed preserves access to the previous generation.
Testing
MiniMax-M3MiniMax-M2.7andMiniMax-M2.7-highspeedresponse_formatremoval still verified