[Feature Request]: Supports Minimax M2.5 and M2.7 models.

[hongruiji]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (Language Policy).
• Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
• Please do not modify this template :) and fill in all the required fields.

Is your feature request related to a problem?

When using Ragflow version 0.24.0, I attempted to configure the LLM using MiniMax; however, the available models were limited to m2 and m2.1, with the latest m2.5 and m2.7 models missing.

Describe the feature you'd like

1. I hope future versions will support Minimax M2.5 and M2.7.
2. I hope future versions will allow for the manual configuration of the models supported by each provider, rather than the current unconfigurable approach.

Describe implementation you've considered

I hope future versions will allow for the manual configuration of the models supported by each provider, rather than the current unconfigurable approach.

Documentation, adoption, use case

Use Case: Pre-integrating models from specific vendors adds a maintenance overhead to the project; furthermore, the greater the number of supported vendors, the heavier this maintenance burden becomes. It would be a more effective approach to instead implement a custom model feature.

Additional information

[Magicray1217]

I'd like to work on this. Will submit a PR shortly.

[Magicray1217]

This has been resolved in the latest main branch. MiniMax M2.5, M2.5-highspeed, M2.7, and M2.7-highspeed are now all available in \conf/llm_factories.json. If you're on v0.24.0, upgrading to the latest version should fix this.