GenAI conversation summarization using Amazon S3, Amazon SQS, AWS Lambda, and Amazon Bedrock

Amazon S3 → Amazon SQS → AWS Lambda → Amazon Bedrock → Amazon S3

Summarize a conversation transcription using Amazon S3 events, Amazon SQS, AWS Lambda and Amazon Bedrock. Ideal for conversation summaries.

This pattern creates an Amazon S3 bucket that sends 'OBJECT_CREATED' events to an SQS queue.
An AWS Lambda function receives the messages from the queue and invokes Amazon Bedrock to extract a summary and sentiment from the file.
The result is stored in a different S3 bucket for consumption.
This setup is particularly useful for obtaining a summary of conversations between customers and support associates.

< Back to all patterns

GitHub icon Download this pattern (.zip)

GitHub icon View this pattern on GitHub


Clone repo

git clone https://github.com/aws-samples/serverless-patterns/cd serverless-patterns/s3-sqs-lambda-bedrock-s3-cdk-python

Deploy

cdk deploy


Testing

See the GitHub repo for detailed testing instructions.

Cleanup

Delete the stack: cdk destroy.

Created by:

Dinesh Balaaji Prabakaran

Dinesh Balaaji Prabakaran

I am a Senior Technical Account Manager with AWS, I specialize in architecting and developing serverless, event-driven solutions on AWS. AWS Storage Technical Field Community member.

Follow on LinkedIn