New Chat gpt vision with weweb help

Ask us anything How do I?
6

Oh ok, so by following the documentation you can try to put your api key in a REST API action. You need to add the REST API plugin, then you will have the Request action available.

This action allow you to use any API REST, including the one provided by OpenAPI. You will have to follow the documentation shared by @justifi

The documentation show

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-4-vision-preview",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What’s in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 300
  }'

It means you have to send a POST request to https://api.openai.com/v1/chat/completions with one header and some information in the body.

The header key must be Authorization and the value Bearer $OPENAI_API_KEY where you put your API KEY.

You will have to add 2 fields inside the body.

  • One with the key model and the value gpt-4-vision-preview
  • Another with the key messages and as value an object containing something formatted as in the code.
  • A third optional field (I guess) called max_tokens

Good luck!

1 Like