Sending prompt using GenAI endpoint

This topic describes how to use API endpoints.

To send the prompt:

  1. Use the api/v1/prompt endpoint to send the prompt.
  2. Fill in the request body with properties from GET/api/v1/models to specify the model and its version.

Ensure that these requirements are met for successfully sending a prompt:

  • A valid Infor Registry logical ID header is required to invoke the /prompt endpoint. Failure to provide a valid header value results in an invocation error.
  • You can only select a single model at the time. If a model and version is not selected, the /prompt endpoint selects Claude 3 Haiku by default.
Note: When invoking the same prompt, we remind users that mild variations to the output must be expected from every invocation of the LLM.

For reference, review this sample payload:

{
  "model": "CLAUDE",
  "version": "claude-3-haiku-20240307-v1:0",
  "prompt": "Hello world!"
}

Where:

  • Model parameter inside the api/v1/prompt is the Name parameter in the GET/api/v1/models
  • Version parameter inside the api/v1/prompt is the ID parameter in the GET/api/v1/models