chore: adjust for ollama support #4129
Conversation
|
@fred-bf is attempting to deploy a commit to the NextChat Team on Vercel. A member of the Team first needs to authorize it. |
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
|
Your build has completed! |
| @@ -151,7 +151,6 @@ export function getHeaders() { | |||
| const accessStore = useAccessStore.getState(); | |||
| const headers: Record<string, string> = { | |||
| "Content-Type": "application/json", | |||
| "x-requested-with": "XMLHttpRequest", | |||
There was a problem hiding this comment.
You may need to test this by removing it just for ollama support which currently is unstable. Be aware that this action might disrupt the custom URL endpoint.
There was a problem hiding this comment.
Tested works fine with OpenAI & Gemini API, do you have any other suggestions?
There was a problem hiding this comment.
Tested works fine with OpenAI & Gemini API, do you have any other suggestions?
The one-api works fine with both OpenAI (gpt,dalle) and Gemini. However, I haven't been able to test other models yet because I don't have access to them.
There was a problem hiding this comment.
Because both the OpenAI and Google Gemini APIs return data in JSON format, this field is not expected to be necessary for the current scenario.
There was a problem hiding this comment.
The origin commit aims to resolve not showing auth page, I just double check it works as expected when server returns 401 status code.
There was a problem hiding this comment.
The origin commit aims to resolve not showing auth page, I just double check it works as expected when server returns 401 status code.
It's better to keep I think
ref: #4030
doc: https://docs.nextchat.dev/models/ollama