while creating Conversation Model with openAI getting error

[saidagit77]

I'm not able to create a Conversation Model with OpenAI. Below error I'm getting while creating

Exception while calling handler conversations/models:create
Raw error: [json.exception.type_error.302] type must be string, but is null

Below request details I'm using creating model

curl -L -X POST 'http://localhost:8108/conversations/models' -H 'Content-Type: application/json' -H 'X-TYPESENSE-API-KEY: $TYPESENSE_API_KEYA' -d '{
  "model_name": "openai/gpt-3.5-turbo",
  "api_key": "api-key",
  "system_prompt": "You are an assistant for question-answering. You can only make conversations based on the provided context. If a response cannot be formed strictly using the provided context, politely say you don’t have knowledge about that topic.",
  "max_bytes": 1024
}'

[jasonbosco]

I just tried that command it seems to work for me:

Could you try using Docker and also make sure that there are no billing issues with your OpenAI API Key?

[saidagit77]

@jasonbosco thanks for responding.

1 . yes, I'm using Docker only. can you please confirm which version ur using and present im using this version [typesense/typesense:26.0]?

can you please suggest which version I have to use for this one?

2. im using free OpenAI API key

[saidagit77]

@jasonbosco can you please give suggestions for the next step

[jasonbosco]

I was indeed using v26 in my tests.

Could you try making calls directly to the OpenAI API using your OpenAI API key to make sure it works?