You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
[FOR CHINESE USERS] 请务必使用英文提交 Issue,否则会被关闭。谢谢!:)
Please do not modify this template :) and fill in all the required fields.
1. Is this request related to a challenge you're experiencing? Tell me about your story.
Story 1: The rerank model is important during use, but currently deployed locally, the rerank model cannot be added to the model vendor. The local rerank model uses the OpenAI interface specification, but when adding the OpenAI interface, only LLM, Text Embedding, Speech2text, Modulation, TTS type models are allowed to be added. However, when adding other model vendors, the same problem exists, as many model vendors only allow LLM type models to be added.
Story 2: Because some model vendors have a certain amount of free quota, and there are local deployment models and remote deployment models at the same time, the same model vendor exists, but there are multiple api addresses and accounts, but it seems unable to support this situation at present. I tried to use the One API project to solve this problem, but due to Story 1, I am unable to support rerank type models
2. Additional context or comments
Regarding Story 1: It is recommended to lift the restriction on 'model types' provided by' model suppliers'. For clearer display, only the added 'model types' can be shown
Regarding Story 2: It is recommended to refer to the One API project. It is allowed to add multiple api addresses and keys in the format of the same model vendor. Allow users to add custom API interface formats.
3. Can you help us with this feature?
I am interested in contributing to this feature.
The text was updated successfully, but these errors were encountered:
Self Checks
1. Is this request related to a challenge you're experiencing? Tell me about your story.
Story 1: The rerank model is important during use, but currently deployed locally, the rerank model cannot be added to the model vendor. The local rerank model uses the OpenAI interface specification, but when adding the OpenAI interface, only LLM, Text Embedding, Speech2text, Modulation, TTS type models are allowed to be added. However, when adding other model vendors, the same problem exists, as many model vendors only allow LLM type models to be added.
Story 2: Because some model vendors have a certain amount of free quota, and there are local deployment models and remote deployment models at the same time, the same model vendor exists, but there are multiple api addresses and accounts, but it seems unable to support this situation at present. I tried to use the One API project to solve this problem, but due to Story 1, I am unable to support rerank type models
2. Additional context or comments
Regarding Story 1: It is recommended to lift the restriction on 'model types' provided by' model suppliers'. For clearer display, only the added 'model types' can be shown
Regarding Story 2: It is recommended to refer to the One API project. It is allowed to add multiple api addresses and keys in the format of the same model vendor. Allow users to add custom API interface formats.
3. Can you help us with this feature?
The text was updated successfully, but these errors were encountered: