New serverless pattern - apigw-lambda-bedrock-nova-terraform

apigw-lambda-bedrock-nova-terraform/README.md

@@ -0,0 +1,135 @@
+# API Gateway Integration with AWS Lambda and Amazon Bedrock Nova Micro (Terraform)
+
+## Overview
+
+This pattern demonstrates how to create a serverless API that leverages Amazon Bedrock's Nova Micro model through AWS Lambda for generating AI responses. The solution uses API Gateway to create a REST endpoint that processes requests and returns AI-generated responses using Nova Micro's text-to-text capabilities.
+
+Learn more about this pattern at [Serverless Land Patterns](https://serverlessland.com/patterns/apigw-lambda-bedrock-nova-terraform).
+
+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](https://aws.amazon.com/pricing/) for details. You are responsible for any AWS costs incurred. No warranty is implied in this example.
+
+## Requirements
+
+* [Create an AWS account](https://portal.aws.amazon.com/gp/aws/developer/registration/index.html) 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](https://docs.aws.amazon.com/cli/latest/userguide/install-cliv2.html) installed and configured
+* [Git Installed](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git)
+* [Terraform](https://learn.hashicorp.com/tutorials/terraform/install-cli?in=terraform/aws-get-started) installed
+
+## Deployment Instructions
+
+1. Clone the project to your local working directory
+
+   ```sh
+   git clone https://github.com/aws-samples/serverless-patterns/ 
+   ```
+
+2. Change the working directory to this pattern's directory
+
+   ```sh
+   cd serverless-patterns/apigw-lambda-bedrock-nova-terraform
+   ```
+
+3. From the command line, run each of the command mentioned in the create_lambda_layer.sh file, this file contains the commands to create the Lambda Layer as well zip the bedrock_integration.py which invokes the Amazon Nova model.
+
+4. From the command line, initialize terraform to  to downloads and installs the providers defined in the configuration:
+    ```
+    terraform init
+    ```
+
+5. From the command line, apply the configuration in the main.tf file:
+    ```
+    terraform apply
+    ```
+
+6. During the prompts:
+   - Enter yes
+
+## How it works
+
+The pattern creates an API Gateway endpoint that accepts POST requests containing prompts. These requests are forwarded to a Lambda function that processes the input and interacts with Amazon Bedrock's Nova Micro model.
+
+Key components:
+
+* API Gateway REST API endpoint
+* Lambda function with Nova Micro integration
+* IAM roles and policies for Lambda and Bedrock access
+* Lambda layer for boto3 dependencies
+* Nova Micro Request Format:
+    ```
+
+    {
+    "system": [
+        {
+            "text": "You are a helpful AI assistant that provides accurate and concise information."
+        }
+    ],
+    "messages": [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "text": "<your-prompt>"
+                }
+            ]
+        }
+    ],
+    "inferenceConfig": {
+        "maxTokens": 1024,
+        "temperature": 0.7,
+        "topP": 0.9,
+        "topK": 50,
+        "stopSequences": []
+    }
+    }
+
+    ```
+
+## Testing
+
+   Using Curl:
+
+    ```
+    curl -X POST \
+    -H "Content-Type: application/json" \
+    -d '{"prompt": "What are the key benefits of using AWS services?"}' \
+    https://YOUR-API-ENDPOINT/dev/generate_content
+
+    ```
+
+## Viewing Test Results
+   ```
+   {
+    "generated-text": "<Model generated response>"
+   }
+   ```
+
+## Cleanup
+
+1. Change directory to the pattern directory:
+    ```sh
+    cd serverless-patterns/apigw-lambda-bedrock-nova-terraform
+    ```
+
+2. Delete all created resources
+    ```sh
+    terraform destroy
+    ```
+
+3. During the prompts:
+    * Enter yes
+
+4. Confirm all created resources has been deleted
+    ```sh
+    terraform show
+    ```
+
+## Reference
+
+- [Amazon Bedrock Nova Models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-nova.html)
+- [AWS Lambda with API Gateway](https://docs.aws.amazon.com/apigateway/latest/developerguide/getting-started-with-lambda-integration.html)
+- [Amazon API Gateway REST APIs](https://docs.aws.amazon.com/apigateway/latest/developerguide/apigateway-rest-api.html)
+
+----
+Copyright 2025 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+
+SPDX-License-Identifier: MIT-0

apigw-lambda-bedrock-nova-terraform/api_gateway.tf

@@ -0,0 +1,44 @@
+resource "aws_api_gateway_rest_api" "generate_content_api" {
+  name = "generate-content-api"
+}
+
+resource "aws_api_gateway_resource" "generate_content" {
+  rest_api_id = aws_api_gateway_rest_api.generate_content_api.id
+  parent_id   = aws_api_gateway_rest_api.generate_content_api.root_resource_id
+  path_part   = "generate_content"
+}
+
+resource "aws_api_gateway_method" "generate_content_post" {
+  rest_api_id   = aws_api_gateway_rest_api.generate_content_api.id
+  resource_id   = aws_api_gateway_resource.generate_content.id
+  http_method   = "POST"
+  authorization = "NONE"
+}
+
+resource "aws_api_gateway_integration" "lambda_integration" {
+  rest_api_id = aws_api_gateway_rest_api.generate_content_api.id
+  resource_id = aws_api_gateway_resource.generate_content.id
+  http_method = aws_api_gateway_method.generate_content_post.http_method
+
+  integration_http_method = "POST"
+  type                    = "AWS_PROXY"
+  uri                     = aws_lambda_function.content_generation.invoke_arn
+}
+
+resource "aws_api_gateway_deployment" "api_deployment" {
+  rest_api_id = aws_api_gateway_rest_api.generate_content_api.id
+
+  depends_on = [
+    aws_api_gateway_integration.lambda_integration
+  ]
+
+  lifecycle {
+    create_before_destroy = true
+  }
+}
+
+resource "aws_api_gateway_stage" "dev" {
+  deployment_id = aws_api_gateway_deployment.api_deployment.id
+  rest_api_id   = aws_api_gateway_rest_api.generate_content_api.id
+  stage_name    = "dev"
+}

apigw-lambda-bedrock-nova-terraform/bedrock_integration.py

@@ -0,0 +1,120 @@
+import json
+import boto3
+import botocore
+
+# Create Bedrock Runtime client
+bedrock = boto3.client(
+    service_name='bedrock-runtime',
+    region_name='us-east-1',
+    endpoint_url='https://bedrock-runtime.us-east-1.amazonaws.com' 
+)
+
+def lambda_handler(event, context):
+    try:
+        # Handle both direct Lambda invocation and API Gateway requests
+        if isinstance(event, dict):
+            if 'body' in event:
+                body = json.loads(event["body"])
+            else:
+                body = event
+        else:
+            return {
+                'statusCode': 400,
+                'body': json.dumps({
+                    'error': 'Invalid input format'
+                })
+            }
+
+        # Extract the prompt
+        prompt = body.get("prompt")
+        if not prompt:
+            return {
+                'statusCode': 400,
+                'body': json.dumps({
+                    'error': 'Prompt is required'
+                })
+            }
+
+        print("Prompt = " + prompt)
+
+        # Create the request body for Nova Micro
+        request_body = json.dumps({
+            "system": [
+                {
+                    "text": "You are a helpful AI assistant that provides accurate and concise information."
+                }
+            ],
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "text": prompt
+                        }
+                    ]
+                }
+            ],
+            "inferenceConfig": {
+                "maxTokens": 1024,
+                "temperature": 0.7,
+                "topP": 0.9,
+                "topK": 50,
+                "stopSequences": []
+            }
+        })
+
+        # Invoke Bedrock API with Nova Micro model
+        try:
+            response = bedrock.invoke_model(
+                body=request_body,
+                modelId='amazon.nova-micro-v1:0',
+                accept='application/json',
+                contentType='application/json'
+            )
+
+            # Parse the response body
+            response_body = json.loads(response['body'].read())
+            print("Nova Micro Response:", response_body)
+
+            # Extract text from the nested response structure
+            generated_text = response_body.get('output', {}).get('message', {}).get('content', [{}])[0].get('text', '')
+
+            return {
+                'statusCode': 200,
+                'headers': {
+                    'Content-Type': 'application/json',
+                    'Access-Control-Allow-Origin': '*'
+                },
+                'body': json.dumps({
+                    'generated-text': generated_text
+                })
+            }
+
+        except botocore.exceptions.ClientError as e:
+            print(f"Bedrock API Error: {str(e)}")
+            return {
+                'statusCode': 500,
+                'headers': {
+                    'Content-Type': 'application/json',
+                    'Access-Control-Allow-Origin': '*'
+                },
+                'body': json.dumps({
+                    'error': f"Bedrock API Error: {str(e)}"
+                })
+            }
+
+    except Exception as e:
+        print(f"Error: {str(e)}")
+        import traceback
+        print(f"Traceback: {traceback.format_exc()}")
+        return {
+            'statusCode': 500,
+            'headers': {
+                'Content-Type': 'application/json',
+                'Access-Control-Allow-Origin': '*'
+            },
+            'body': json.dumps({
+                'error': str(e),
+                'traceback': traceback.format_exc()
+            })
+        }

apigw-lambda-bedrock-nova-terraform/create_lambda_layer.sh

@@ -0,0 +1,23 @@
+# Create a directory for the layer
+mkdir -p lambda-layer/python
+
+# Navigate to the python directory
+cd lambda-layer/python
+
+# Create a requirements.txt file
+echo "boto3" > requirements.txt
+echo "botocore" >> requirements.txt
+
+# Install the requirements
+pip install -r requirements.txt -t .
+
+# Go back to the lambda-layer directory
+cd ..
+
+# Zip the contents
+zip -r boto3-bedrock-layer.zip python/
+
+# Move back to the main project directory
+cd ..
+
+zip lambda_function.zip bedrock_integration.py

apigw-lambda-bedrock-nova-terraform/example-pattern.json

@@ -0,0 +1,71 @@
+{
+    "title": "API Gateway Integration with AWS Lambda and Amazon Bedrock Nova Micro (Terraform)",
+    "description": "This pattern demonstrates how to create a serverless API that leverages Amazon Bedrock's Nova Micro model through AWS Lambda for generating text responses. The architecture enables real-time text generation through a RESTful API endpoint.",
+    "language": "Python",
+    "level": "200",
+    "framework": "Terraform",
+    "introBox": {
+        "headline": "How it works",
+        "text": [
+            "An Amazon API Gateway REST endpoint accepts POST requests containing prompts. These requests are automatically routed to an AWS Lambda function, which processes the input and interacts with Amazon Bedrock's Nova Micro model.",
+            "The Lambda function formats the request according to Nova Micro's requirements, invokes the model, and returns the generated response through API Gateway. This serverless architecture ensures scalability and cost-effectiveness, as you only pay for actual API calls and compute time."
+        ]
+    },
+    "gitHub": {
+        "template": {
+            "repoURL": "https://github.com/aws-samples/serverless-patterns/tree/main/apigw-lambda-bedrock-nova-terraform",
+            "templateURL": "serverless-patterns/apigw-lambda-bedrock-nova-terraform",
+            "projectFolder": "apigw-lambda-bedrock-nova-terraform",
+            "templateFile": "apigw-lambda-bedrock-nova-terraform/main.tf"
+        }
+    },
+    "resources": {
+        "bullets": [
+            {
+                "text": "Amazon API Gateway REST APIs",
+                "link": "https://docs.aws.amazon.com/apigateway/latest/developerguide/welcome.html"
+            },
+            {
+                "text": "AWS Lambda Function Integration",
+                "link": "https://docs.aws.amazon.com/apigateway/latest/developerguide/getting-started-with-lambda-integration.html"
+            },
+            {
+                "text": "Amazon Bedrock Nova Models",
+                "link": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-nova.html"
+            }
+        ]
+    },
+    "deploy": {
+        "text": [
+            "terraform init",
+            "terraform plan",
+            "terraform apply"
+        ]
+    },
+    "testing": {
+        "text": [
+            "Test the API endpoint using curl:",
+            "curl -X POST -H \"Content-Type: application/json\" -d '{\"prompt\": \"What are the key benefits of using AWS services?\"}' https://YOUR-API-ENDPOINT/dev/generate_content",
+            "",
+            "Or use Python with the requests library:",
+            "import requests",
+            "response = requests.post('https://YOUR-API-ENDPOINT/dev/generate_content',",
+            "                        json={'prompt': 'What are the key benefits of using AWS services?'})",
+            "print(response.json())"
+        ]
+    },
+    "cleanup": {
+        "text": [
+            "terraform destroy",
+            "terraform show"
+        ]
+    },
+    "authors": [
+        {
+            "name": "Naresh Rajaram",
+            "image": "",
+            "bio": "Senior Partner Solutions Architect, AWS",
+            "linkedin": "https://www.linkedin.com/nareshrajaram"
+        }
+    ]
+}