mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-03-16 04:17:49 +08:00
35cd56f990
## Summary Add MiniMax's latest M2.5 model family to the model registry and update the default API base URL to the international endpoint for broader accessibility. ## Changes - **Add MiniMax-M2.5 models** to `conf/llm_factories.json`: - `MiniMax-M2.5` — Peak Performance. Ultimate Value. Master the Complex. - `MiniMax-M2.5-highspeed` — Same performance, faster and more agile. - Both support 204,800 token context window and tool calling (`is_tools: true`). - **Update default MiniMax API base URL** in `rag/llm/__init__.py`: - From `https://api.minimaxi.com/v1` (domestic) to `https://api.minimax.io/v1` (international). - Chinese users can still override via the Base URL field in the UI settings (as documented in existing i18n strings). ## Supported Models | Model | Context Window | Tool Calling | Description | |-------|---------------|-------------|-------------| | `MiniMax-M2.5` | 204,800 tokens | Yes | Peak Performance. Ultimate Value. | | `MiniMax-M2.5-highspeed` | 204,800 tokens | Yes | Same performance, faster and more agile. | ## API Documentation - OpenAI Compatible API: https://platform.minimax.io/docs/api-reference/text-openai-api ## Testing - [x] JSON validation passes - [x] Python syntax validation passes - [x] Ruff lint passes - [x] MiniMax-M2.5 API call verified (returns valid response) - [x] MiniMax-M2.5-highspeed API call verified (returns valid response) Co-authored-by: PR Bot <pr-bot@minimaxi.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>