I am trying to create an action in GPT to connect to openai api to create an assistant. In a way when I ask GPT to create and assistant, creates one with openai api.
this is my schema:
info:
title: OpenAI API
version: "1.0.0"
servers:
- url: https://api.openai.com/v1
paths:
/assistants:
post:
operationId: createAssistants
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
model:
type: string
description: "ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them."
required:
- model
responses:
201:
description: Assistant created
content:
application/json:
schema:
type: object
properties:
id:
type: string
object:
type: string
created_at:
type: integer
model:
type: string
tools:
type: array
items:
type: object
properties:
type:
type: string
required:
- id
- object
- created_at
- model
- tools
components:
schemas: {}
securitySchemes:
ApiKeyAuth:
type: http
scheme: "bearer"
security:
- ApiKeyAuth: []
And I always get this error:
{
"response_data": {
"error": {
"message": "Invalid URL (POST /v1/assistants)",
"type": "invalid_request_error",
"param": null,
"code": null
}
},
"status_code": 404,
"action_id": "g-075f77c3d4247b6c2249d63423f9a5"
}
While this is correct:
POST https://api.openai.com/v1/assistants
How can I solve it? Is this beacuse I am using OpenAI api in another openAI tool or it has another reason.