Function Documentation: OpenAI -> Create a Chat Completion

OpenAI API documentation

Overview

This function generates a chat completion using the OpenAI API based on a user-provided input text. It requires parameters such as the model & input message. The function validates environment variables and conditions before making an 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. model (enum) Required
   • Description: Specifies the model to be used for generating the chat completion.
   • Options:
     • gpt-4o-mini (default)
     • gpt-4o
3. message (text) Required
   • Description: The input message or prompt that will be sent to the OpenAI API for generating the chat completion.

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 message.
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 chat completion

Success response

{"Barack Obama is 6 feet 1 inch tall (185 cm)."}

Error response

{
  "message": "Incorrect API key provided: ssk-None*********************************************GQPD. You can find your API key at https://platform.openai.com/account/api-keys."
}

Example

Input

{ "model": "gpt-4o-mini", "message": "What is Obama's height?" }

Response

{"Barack Obama is 6 feet 1 inch tall (185 cm)."}