This pattern creates an API Gateway REST API with Lambda proxy integration which invokes Amazon Bedrock models for text and image generation.
Learn more about this pattern at Serverless Land Patterns: https://serverlessland.com/patterns/dynamic-bedrock-svls-sam
Important: this application uses various AWS services and there are costs associated with these services after the Free Tier usage - please see the AWS Pricing page for details. You are responsible for any AWS costs incurred. No warranty is implied in this example.
- Create an AWS account if you do not already have one and log in. The IAM user that you use must have sufficient permissions to make necessary AWS service calls and manage AWS resources.
- AWS CLI installed and configured
- Git Installed
- AWS Serverless Application Model (AWS SAM) installed
-
Create a new directory, navigate to that directory in a terminal and clone the GitHub repository:
git clone https://github.com/aws-samples/serverless-patterns
-
Change directory to the pattern directory:
cd dynamic-bedrock-svls-sam
-
From the command line, use AWS SAM to deploy the AWS resources for the pattern as specified in the template.yml file:
sam build sam deploy --guided
-
During the prompts:
- Enter a stack name
- Enter the desired AWS Region
- Allow SAM CLI to create IAM roles with the required permissions.
- Allow 'ApiFunction has no authentication. Is this okay?' for the time being, this can be modified as per requirement.
Once you have run
sam deploy --guided
mode once and saved arguments to a configuration file (samconfig.toml), you can usesam deploy
in future to use these defaults.
- Note the outputs from the SAM deployment process. These contain the resource names and/or ARNs which are used for testing.
A REST API is created that has /image and /text resources associated with the available models in Amazon Bedrock for image and text generation respectively. All resources integrate with a Lambda function over proxy integration.
- Place a request to /image over HTTP POST method with the required prompt as the request body to generate an image using StabilityAI stable diffusion XL model.
- Place a request to /text/model* over HTTP POST method with the required prompt as the request body to generate a text output using various models offered by Anthropic, AI21 labs.
Once you place POST requests to the API endpoint's URL (invoke URL) with prompt in the request body (for example - via Postman client), you will receive an image or a text generated by the LLM models as the response.
sam delete
Copyright 2023 Amazon.com, Inc. or its affiliates. All Rights Reserved.
SPDX-License-Identifier: MIT-0