feat: add MiniMax as a supported LLM platform

[octo-patch]

Summary

Add MiniMax as a first-class platform type in Langchain-Chatchat, enabling users to connect to MiniMax LLM and embedding models via its OpenAI-compatible API.

Changes

• Add minimax to the platform_type enum in PlatformConfig
• Add default MiniMax platform configuration with the following models:
  • LLM models: MiniMax-M1, MiniMax-M1-40k, MiniMax-M2.5
  • Embedding model: embo-01
• Route MiniMax embeddings through OpenAIEmbeddings (API-compatible)
• Update README.md and README_en.md to list MiniMax as a supported online API provider

How to use

Users can configure MiniMax in their model_settings.yaml:

MODEL_PLATFORMS:
  - platform_name: minimax
    platform_type: minimax
    api_base_url: https://api.minimax.io/v1
    api_key: YOUR_MINIMAX_API_KEY
    llm_models:
      - MiniMax-M1
      - MiniMax-M1-40k
      - MiniMax-M2.5
    embed_models:
      - embo-01

Why MiniMax?

MiniMax offers high-performance LLMs with up to 204K context window (MiniMax-M2.5), competitive pricing, and an OpenAI-compatible API. This makes integration seamless with the existing Langchain-Chatchat architecture.

Test plan

• Python files parse without errors
• Changes follow existing platform configuration patterns
• MiniMax API is OpenAI-compatible, so existing ChatOpenAI wrapper works without modification