Arron Zou

I got the same problem before. It's like your network environment is not available to access api.openai.com . You can give it a try to `ping https://api.openai.com`. if it failed,...

> > I don't see you passing the OPENAI_API_KEY anywhere, might that be the issue? Also, I'd recommend updating to 0.0.52 > > Upgrading to 0.0.52 made it worse, getting...

few-shot example do not need this kind of things. Just input it as normal Human input or system role input is enough. like: ``` here is some kind of examples...

just replace the request to openai with your own models service in `llm_utils.py`. But the embedding part may need to keep using openai's embedding api.

> > just replace the request to openai with your own models service in `llm_utils.py`. But the embedding part may need to keep using Openai's embedding api. > > Can...

the problem is probably caused by consuming the Request stream twice. I'm using `vercel dev` to start my project in my local machine. when I call `ctx.req.json` in a post...