feat: add MiniMax as LLM provider with M3 default model#1166
Open
octo-patch wants to merge 7 commits into
Open
feat: add MiniMax as LLM provider with M3 default model#1166octo-patch wants to merge 7 commits into
octo-patch wants to merge 7 commits into
Conversation
This reverts commit 17923847f40863e977588d1a81bec2ae16e9801f.
Add MiniMax (https://platform.minimax.io) as a new LLM provider, using their OpenAI-compatible API endpoint. Supported models: - MiniMax-M2.5 (default) - 204K context window - MiniMax-M2.5-highspeed - faster variant Key implementation details: - New MiniMaxClient class using the OpenAI SDK with MiniMax base URL - Temperature clamped to minimum 0.01 (MiniMax requires > 0) - response_format (json_mode) skipped as MiniMax does not support it - API key read from config or MINIMAX_API_KEY environment variable - Default base URL: https://api.minimax.io/v1 Changes: - core/llm/minimax_client.py: New MiniMax LLM client - core/config/__init__.py: Add MINIMAX to LLMProvider enum - core/llm/base.py: Register MiniMaxClient in provider factory - example-config.json: Add MiniMax configuration example - tests/llm/test_minimax.py: Unit tests (10 tests) - tests/integration/llm/test_minimax.py: Integration tests - README.md: Add minimax to supported providers list
|
Zvonimir Sabljic seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
- Update default model from MiniMax-M2.5 to MiniMax-M2.7 in tests and config - Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to available models list - Add integration tests for M2.7-highspeed model - Keep M2.5 and M2.5-highspeed as available alternatives with tests
octo-patch
changed the title
- Update default MiniMax model in example-config.json to M3 - Drop older M2.5 and M2.5-highspeed integration tests - Update unit tests to target MiniMax-M3 as the default model - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives
octo-patch
changed the title
LeonOstrez
force-pushed
the
main
branch
2 times, most recently
from
90f59f5 to
a372904
Compare
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 MiniMax as an LLM provider for GPT Pilot with the latest M3 model as default.
Changes
MiniMaxClientwith OpenAI-compatible API integrationWhy
MiniMax-M3 is the latest flagship model with a 512K context window, up to 128K output, and image input support via the OpenAI-compatible API. M2.7 and M2.7-highspeed are kept as alternatives for fallback / cost-sensitive usage.
Testing