ragflow icon indicating copy to clipboard operation
ragflow copied to clipboard

Published 20 hours ago • verified publisher icon infiniflow

Integrates more models

Open JinHai-CN opened this issue 9 months ago • 3 comments

This issue is used to document the LLM, embedding, reranker, etc. models that need to be integrated with RAGFlow.

  • [x] Azure Open AI service
  • [x] Google Gemini #1036
  • [x] Mixtral AI #433
  • [x] Together.AI #1890
  • [x] Cohere model #367
  • [x] AWS Bedrock models #308
  • [x] Baichuan AI #934
  • [x] 01.AI #1951
  • [x] Wenxin
  • [x] Minimax
  • [x] BCE embedding model #326
  • [x] Jina embedding models #650
  • [x] GPT4o #775 (Only text now)
  • [x] VolcEngine #885
  • [x] SiliconFlow #1926
  • [x] Novita.ai #1910
  • [x] Upstage #1902
  • [x] GPT4o-mini #1827
  • [x] Cohere #1849
  • [x] Step #1686 #1751

JinHai-CN avatar May 10 '24 12:05 JinHai-CN

Request to support Qwen-max. Can I modify the code?

OXOOOOX avatar May 29 '24 17:05 OXOOOOX

@OXOOOOX We intend to create an international community, so we encourage using English for communication.

Yes, you can modify the code and submit a PR. We will merge it into the code base.

JinHai-CN avatar May 30 '24 13:05 JinHai-CN

Would you pls add llama-3.1-70b-versatile and llama-3.1-8b-instant for Groq , for now is only llama3.0

Thank you

lionkingc avatar Aug 23 '24 12:08 lionkingc

#1853

JinHai-CN avatar Sep 23 '24 10:09 JinHai-CN