Documentation: AWS Bedrock Action (AI Analysis)¶

Overview¶

The AWS Bedrock Action is an automation node that allows you to analyze images using the artificial intelligence models available in Amazon Bedrock (AWS's managed foundational models service, which includes models such as Anthropic's Claude, among others). It belongs to the AI Models node family.

In IoT and security environments, it is ideal for organizations that already operate on AWS and want to run camera image analysis through Bedrock, taking advantage of their infrastructure, governance, and centralized billing.

When to use this action?¶

Use this action when you need to:

Analyze images from cameras with AI using models hosted on AWS Bedrock.
Keep AI processing within the AWS ecosystem (governance, security, billing).
Obtain structured descriptions (e.g., in JSON) of what is happening in an image.

Node Configuration¶

The node has two configuration tabs at the top: Form and JSON Editor.

Empty configuration of the AWS Bedrock node

Form View¶

1. AWS Credentials *Required¶

Select the AWS credential (containing access_key_id, secret_access_key, and optionally session_token) to authenticate access to Bedrock. Managed in a centralized and secure way.

2. Model ID *Required¶

The identifier of the Bedrock model to use (e.g., anthropic.claude-3-5-sonnet-20241022-v2:0).

3. Image URLs¶

The URLs of the images to analyze (one per line). Supports template expressions (e.g., {{get_snapshot_node.url}}).

4. Prompt *Required¶

The instruction or question for the model. Supports template expressions.

Configured form of the AWS Bedrock node

JSON Editor View¶

JSON Editor view of the AWS Bedrock node

JSON Structure (Input Parameters)¶

{
  "region": "us-east-1",
  "access_key_id": "",
  "secret_access_key": "",
  "session_token": "",
  "profile": "",
  "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
  "resource": "image",
  "operation": "analyze",
  "image_urls": [
    "{{get_snapshot_node.url}}"
  ],
  "prompt": "Describe in JSON format the objects and people visible in this security image."
}

JSON Fields¶

Field	Type	Description
`region`	string	AWS region (default `us-east-1`).
`access_key_id` / `secret_access_key` / `session_token`	string	References to the AWS credential (managed securely).
`profile`	string	AWS profile (optional).
`model_id`	string	Bedrock model ID (e.g. `anthropic.claude-3-5-sonnet-20241022-v2:0`).
`resource`	string	Resource type (`image`).
`operation`	string	Operation (`analyze`).
`image_urls`	array (string)	URLs of the images to analyze.
`prompt`	string	The instruction/question for the model.

Output: Where the node's data comes from¶

The analysis result (text generated by the Bedrock model) is available in the node's output and can be used in downstream nodes with {{node_key}}.

Usage Examples¶

Example 1: Security image analysis via AWS¶

Use case: An organization operating on AWS analyzes a camera snapshot with a Bedrock model to obtain a structured description of objects and people.

Model ID: anthropic.claude-3-5-sonnet-20241022-v2:0
Image URLs: {{get_snapshot_node.url}}
Prompt: Describe in JSON format the objects and people visible in this security image.

(see JSON structure above)

Validation and Errors¶

Condition	Common cause / fix
Authentication error	The AWS credential is invalid or lacks permissions for Bedrock.
Model not available	Verify that the `model_id` is enabled in your AWS Bedrock account and region.
URLs not working	Make sure the image URLs are publicly accessible.

Best Practices¶

Use centralized credentials: Do not write AWS keys in the node; select a credential managed securely.
Verify model access: Enable the desired model in the AWS Bedrock console for your region beforehand.
Request structured outputs: Ask for JSON in the prompt when you plan to process the result in downstream nodes.
Chain with snapshot capture: Typical pattern: Get snapshot → AWS Bedrock → condition/notification.