Amazon GenAI

See the changelog of this Action type here.

Note that this Action is only available in Tenants with access to Amazon Bedrock. Get in touch with us if you don't see it and want to access it.

Overview

The Amazon GenAI Action allows users to enrich events by generating structured outputs using models hosted on Amazon Bedrock, such as Claude, Titan, or Jurassic.

In order to configure this action, you must first link it to a Listener. Go to Building a Pipeline to learn how this works.

Ports

These are the input and output ports of this Action:

Input ports

• Default port - All the events to be processed by this Action enter through this port.

Output ports

• Default port - Events are sent through this port if no error occurs while processing them.

• Error port - Events are sent through this port if an error occurs while processing them.

Configuration

1

Find Amazon GenAI in the Actions tab (under the AI group) and drag it onto the canvas.

2

To open the configuration, click the Action in the canvas and select Configuration.

3

Enter the required parameters:

Parameter	Description
Region*	Choose the Google Cloud location for AWS (e.g., eu-central-1). Your region is displayed in the top right-hand corner of your AWS console.
Model*	Enter your Model ID or Model Inference Profile (arn) e.g. e.g., arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-v2 Go to the Amazon Bedrock console. Go to Model Access in the left sidebar. You’ll see a list of available foundation models (FMs) like Anthropic Claude, AI21, Amazon Titan, Meta Llama, etc. Click on a model to view its Model ID (e.g., anthropic.claude-v2) and ARN (e.g., arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-v2).
System Instructions	Optional instructions to influence the behavior of the model (e.g., "You are a security analyst...").
Prompt Field*	Select the field in the event containing the prompt to send to the model. Must be string. This field will be sent as-is to the model. Amazon Bedrock models support both English and multilingual prompts, depending on the model selected.
Temperature	Adjusts randomness of outputs: greater than 1 is random, 0 is deterministic, and 0.75 is a good starting value. Default value is 0.1
Max Tokens	Maximum number of tokens to generate. A word is generally 2-3 tokens. The default value is 128 (min 1, max 8892).
Top P	Top P sets a probability threshold to limit the pool of possible next words. Whereas temperature controls how random the selection is,top_p controls how many options are considered. Range: 0–1. Default is 1.0.
JSON credentials*	Provide the secret JSON credentials used to authenticate against Amazon Bedrock.
Output Field*	Give a name to the output field that will return the evaluation.

4

Click Save to complete.

Use conditional logic upstream to prevent sending unstructured or non-informative prompts to the model, helping to optimize costs and relevance.

Example

Read our use case to learn how to use this Action in a real cybersecurity scenario.

Using Amazon GenAI to classify HTTP logs