Error "The model: `gpt-4` does not exist"

[ChristianWeyer]

The following call http POST http://localhost:8000/command key=1 files:=\[\] query="Hey there!"

produces this:

HTTP/1.1 200 OK
content-length: 59
content-type: application/json
date: Wed, 05 Apr 2023 16:11:59 GMT
server: uvicorn

{
    "files": [],
    "response": "The model: `gpt-4` does not exist"
}

Am I missing some config, maybe?

[hanchchch]

It might because you don't have access to gpt-4 on OpenAI API. Try using gpt-3.5-turbo by change line 118 of core/agents/llm.py.

    model_name: str = "gpt-3.5-turbo"

I think I should make it to use env var so we can change it without changing the code.

[ChristianWeyer]

How would one get access to gpt-4 via the API?

[ChristianWeyer]

Ah... 🙂 https://openai.com/waitlist/gpt-4-api

[hanchchch]

yes, the waitlist ... 🥲 is it working with gpt-3.5 though?

[ChristianWeyer]

Yes!