Function Documentation: OpenAI -> Describe an Image from a URL

OpenAI Vision API

Overview

This function generates a description of an image using the OpenAI API based on the provided image URL. It requires parameters such as the image URL & model. The function ensures necessary environment variables are set and verifies conditions before making the API request and processing the response.

Inputs

1. openai_api_key (registry|text) Required Sensitive data

   • Description: The API key for your OpenAI account.

2. image_url (text) Required

   • Description: The URL of the image that will be sent to the OpenAI API for generating the description.

3. model (enum) Required

   • Description: Specifies the model to be used for generating the image description.
   • Options:
     • gpt-4o-mini (default)
     • gpt-4o

Function Stack

1. OpenAI API Request

1. API Request to https://api.openai.com

   • Purpose: Sends a request to the OpenAI API using the specified model and image URL.

2. Precondition: openai_api_response.status == 200

   • Purpose: Confirms that the API request was successful (HTTP status code 200).

2. OpenAI API Response

1. Create Variable: response
   • Purpose: Stores the response from the OpenAI API.

Response

• The function returns the generated image description, optionally including token usage details if the show_token_usage flag is set to true.

Success response

{
   "The image depicts a model or miniature of a fortified castle or walled city. It features a large structure at the top, resembling a castle, with walls and towers surrounding smaller buildings that likely represent a village or town inside the fortifications. The overall layout suggests a historical or fantasy setting, commonly seen in architectural models or films."
}

Error response

{
  "message":"Invalid image."
} 

Example

Input

{
  "image_url": "https://upload.wikimedia.org/wikipedia/commons/b/b7/Medieval_Durr%C3%ABs.jpg",
  "model": "gpt-4o-mini",
}

Response

{
   "The image depicts a model or miniature of a fortified castle or walled city. It features a large structure at the top, resembling a castle, with walls and towers surrounding smaller buildings that likely represent a village or town inside the fortifications. The overall layout suggests a historical or fantasy setting, commonly seen in architectural models or films."
}