Pushing new pattern code to serveless-patterns

[Monalisu]

Issue #, if available:

New serverless pattern - Lambda-bedrock-dynamodb-sam

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[ellisms]

Hi @Monalisu thanks for the submission. Requesting a few changes.

[Monalisu]

Hi @***@***.***> , Thank you for the suggestions and help . I have implemented the changes mentioned . Let me know if anything else to be done from my side . Warm regards, Monalisa Nath Solutions Architect, Field-AGS-India-ENT-CS Amazon Web Services Thoughts on our interaction? Provide feedback here<https://feedback.aws.amazon.com/?ea=monalisu&fn=Monalisa&ln=Nath> From: ellisms ***@***.***> Reply to: aws-samples/serverless-patterns ***@***.***> Date: Monday, 2 December 2024 at 10:37 PM To: aws-samples/serverless-patterns ***@***.***> Cc: "Nath, Monalisa" ***@***.***>, Mention ***@***.***> Subject: Re: [aws-samples/serverless-patterns] Pushing new pattern code to serveless-patterns (PR #2511) @ellisms requested changes on this pull request. Hi @Monalisu<https://github.com/Monalisu> thanks for the submission. Requesting a few changes.

________________________________ In lambda-bedrock-dynamodb-sam/src/app.py<#2511 (comment)>:

@@ -0,0 +1,33 @@

+import json +import boto3 +import os + +bedrock = boto3.client('bedrock-runtime') +dynamodb = boto3.resource('dynamodb') +table_name = os.environ['table_name'] + +model_id = "anthropic.claude-3-haiku-20240307-v1:0" Recommend making this an environment variable so user can easily change model without changing code.

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

@@ -0,0 +1,162 @@

+# Amazon Bedrock to Amazon DynamoDB + +This pattern demonstrates how to use AWS Lambda to process queries using Amazon Bedrock's Claude 3 Haiku model and store the results in Amazon DynamoDB. ⬇️ Suggested change

-This pattern demonstrates how to use AWS Lambda to process queries using Amazon Bedrock's Claude 3 Haiku model and store the results in Amazon DynamoDB. +This pattern demonstrates how to use AWS Lambda to process queries using Amazon Bedrock's Claude 3 Haiku model and store the conversation results in Amazon DynamoDB.

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

@@ -0,0 +1,162 @@

+# Amazon Bedrock to Amazon DynamoDB + +This pattern demonstrates how to use AWS Lambda to process queries using Amazon Bedrock's Claude 3 Haiku model and store the results in Amazon DynamoDB. +This pattern helps the system to persist the conversation with the model in DynamoDB which is a NoSQL database offering from AWS ⬇️ Suggested change

-This pattern helps the system to persist the conversation with the model in DynamoDB which is a NoSQL database offering from AWS

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

+# Amazon Bedrock to Amazon DynamoDB

+ +This pattern demonstrates how to use AWS Lambda to process queries using Amazon Bedrock's Claude 3 Haiku model and store the results in Amazon DynamoDB. +This pattern helps the system to persist the conversation with the model in DynamoDB which is a NoSQL database offering from AWS + +Learn more about this pattern at Serverless Land Patterns: [Serverless Land](https://serverlessland.com/patterns/) + +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) +* [AWS Serverless Application Model](https://docs.aws.amazon.com/serverless-application-model/latest/developerguide/serverless-sam-cli-install.html) (AWS SAM) installed + Add a prerequisite for Bedrock model access.

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

+

+* [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) +* [AWS Serverless Application Model](https://docs.aws.amazon.com/serverless-application-model/latest/developerguide/serverless-sam-cli-install.html) (AWS SAM) installed + +## Deployment Instructions + +1. 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/lambda-bedrock-dynamodb-sam + + ``` +1. Change directory to the pattern directory: + ``` + cd bedrock-to-dynamodb ⬇️ Suggested change - cd bedrock-to-dynamodb + cd lambda-bedrock-dynamodb-sam

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

+ ```

+1. Change directory to the pattern directory: + ``` + cd bedrock-to-dynamodb + ``` +1. From the command line, use AWS SAM to deploy the AWS resources for the pattern as specified in the template.yml file: + ``` + sam deploy --guided + ``` +1. During the prompts: + * Enter a stack name + * Enter the desired AWS Region + * Enter a name for your DynamoDB table + * Allow SAM CLI to create IAM roles with the required permissions. + + Once you have run `sam deploy --guided` mode once and saved arguments to a configuration file (samconfig.toml), you can use `sam deploy` in future to use these defaults. ⬇️ Suggested change - Once you have run `sam deploy --guided` mode once and saved arguments to a configuration file (samconfig.toml), you can use `sam deploy` in future to use these defaults. + After the first run of `sam deploy --guided` and saving the arguments to a configuration file (samconfig.toml), you can use `sam deploy` in future to use these defaults.

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

+ * Enter a name for your DynamoDB table

+ * Allow SAM CLI to create IAM roles with the required permissions. + + Once you have run `sam deploy --guided` mode once and saved arguments to a configuration file (samconfig.toml), you can use `sam deploy` in future to use these defaults. + +1. Note the outputs from the SAM deployment process. These contain the resource names and/or ARNs which are used for testing. + +## How it works + +This pattern creates a Lambda function that uses Amazon Bedrock's Claude 3 Haiku model to process queries. The function then stores both the query and the response in a DynamoDB table. The Lambda function is triggered by an event containing a 'query' key, processes the query using Bedrock, and stores the result in DynamoDB. + +## Testing + +1. Invoke the Lambda function with a test event containing a query: + ```bash + aws lambda invoke --function-name lambda-processor --payload '{"query": "What is the capital of France?"}' output.txt ⬇️ Suggested change - aws lambda invoke --function-name lambda-processor --payload '{"query": "What is the capital of France?"}' output.txt + aws lambda invoke --function-name lambda-processor --cli-binary-format raw-in-base64-out --payload '{"query": "What is the capital of France?"}' output.txt

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

+1. Invoke the Lambda function with a test event containing a query:

+ ```bash + aws lambda invoke --function-name lambda-processor --payload '{"query": "What is the capital of France?"}' output.txt + ``` +2. Check the DynamoDB table to see the stored query and response: + ```bash + aws dynamodb scan --table-name YOUR_TABLE_NAME + ``` + +Replace `YOUR_TABLE_NAME` with the actual name of your DynamoDB table. + +## Cleanup + +1. Delete the stack + ```bash + aws cloudformation delete-stack --stack-name STACK_NAME ⬇️ Suggested change - aws cloudformation delete-stack --stack-name STACK_NAME +sam delete

________________________________ In lambda-bedrock-dynamodb-sam/README.md<#2511 (comment)>:

+## Cleanup

+ +1. Delete the stack + ```bash + aws cloudformation delete-stack --stack-name STACK_NAME + ``` +1. Confirm the stack has been deleted + ```bash + aws cloudformation list-stacks --query "StackSummaries[?contains(StackName,'STACK_NAME')].StackStatus" + ``` +---- +Copyright 2024 Amazon.com, Inc. or its affiliates. All Rights Reserved. + +SPDX-License-Identifier: MIT-0# Bedrock and DynamoDB Integration + +This project demonstrates an AWS SAM (Serverless Application Model) application that integrates Amazon Bedrock with Amazon DynamoDB. It creates a Lambda function that processes queries using Bedrock's Claude 3 Haiku model and stores the results in a DynamoDB table. From here to the end seems to be significant duplication of earlier sections. I would remove this content.

________________________________ In lambda-bedrock-dynamodb-sam/template.yaml<#2511 (comment)>:

@@ -0,0 +1,78 @@

+AWSTemplateFormatVersion: '2010-09-09' +Transform: AWS::Serverless-2016-10-31 +Description: > + Sam for Bedrock and Dynamodb pattern ⬇️ Suggested change - Sam for Bedrock and Dynamodb pattern + Sam for Bedrock and Dynamodb pattern (uksb-1tthgi812) (tag:lambda-bedrock-dynamodb-sam)

________________________________ In lambda-bedrock-dynamodb-sam/template.yaml<#2511 (comment)>:

+ KeyType: HASH

+ ProvisionedThroughput: + ReadCapacityUnits: 1 + WriteCapacityUnits: 1 + + # Creates Lambda function + + InvokeBedrock: + Type: AWS::Serverless::Function # More info about Function Resource: https://github.com/awslabs/serverless-application-model/blob/master/versions/2016-10-31.md#awsserverlessfunction + Properties: + FunctionName: lambda-processor + CodeUri: src/ + Handler: app.lambda_handler + Environment: + Variables: + table_name: !Ref Outputtable add a variable for model name so users can easily test different models. — Reply to this email directly, view it on GitHub<#2511 (review)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/BM3MT6YJ7NNQZSBQTNVAE5L2DSHVDAVCNFSM6AAAAABRYNW5IOVHI2DSMVQWIX3LMV43YUDVNRWFEZLROVSXG5CSMV3GSZLXHMZDINZTGI3TEMZZG4>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[ellisms]

Thanks @Monalisu. I'll add this to the publishing queue.