Amazon Titan: Prompt AI action

Amazon Titan: Prompt AI action connects automations to Amazon Bedrock Titan prompt AI functionality. This action enables automations to generate human-quality text, translate languages, write different kinds of creative content, and answer questions in an informative way, all based on user-defined prompts.

Prerequisites

  • You must have the Bot creator role to use the Amazon Titan: Prompt AI action in a bot.
  • Ensure that you have the necessary credentials to send a request and have included Amazon Bedrock: Authenticate action before calling any Amazon Bedrock actions.

This example shows how to send a natural language message using the Titan Prompt AI action and get an appropriate response.

Procedure

  1. In the Automation Anywhere Control Room, navigate to the Actions pane, select Generative AI > Amazon Bedrock, drag Amazon Titan: Prompt AI, and place it in the canvas.
  2. Enter or select the following fields:

    Titan Prompt AI

    1. Enter the Region. For information on Region, see Amazon Bedrock GA regions.
    2. Click the Model drop-down and select a model with which to communicate.
      • Titan Text G1 - Lite: Amazon's Titan Text G1-Lite is a smaller and more efficient version of the larger Titan Text G1 model, making it more suitable for devices with limited resources.
      • Titan Text G1 - Express: Amazon's Titan Text G1 - Express model is a versatile and cost-effective large language model (LLM) designed for a wide range of text generation tasks.
      • Other supported version: To input other supported models.
    3. Enter a prompt Message to use by the model to generate a response.
    4. Enter the Response Length.
      By default, if you do not enter a value, then the Response Length is automatically set to keep it within the maximum context length of the selected model by considering the length of the generated response.
    5. Enter a Temperature. This value refers to the randomness of the response. As the temperature approaches zero, the response becomes specific. The higher the value, the more random is the response.
    6. Enter Default as the session name to limit the session to the current session.
    7. To manage the optional parameters, click the Show more options and select Yes. If you select Yes, you can add other parameters such as: Top P and Stop Sequences. For information about these optional parameters, see Learn Models.
    8. Save the response to a variable. In this example, the response is saved to str_PromptResponse.
  3. Click Run to start the bot.
    You can read the value of the field by printing the response in a Message box action. In this example, str_PromptResponse prints the response.