Start by configuring the following settings:

• OpenAIModel
  • ID of the Open AI model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
• OpenAIStoredKey
  • OpenAI Key from your OpenAI account.
• OpenAITemperature
  • Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 means that the highest probability tokens are always selected.

To use the connector in an application, add a dependency to server action CreateChatCompletion from the library Open AI Connector.

The input OpenAIKey is not mandatory. If its value is empty, the API Key from the OpenAIStoredKey will be used in its stead to authenticate the request.

The input SystemMessage helps set the behavior of the assistant (e.g: You are a bot that returns an extended list of user stories to build the required application from the text that will be given by the user. The return value must be in the following json format: ["UserStory"].).

The input UserMessage is the user prompt: provide requests or comments for the assistant to respond to.