https://github.com/riolaf05/aws-cdk-ts-bedrock-rag-agent-platform

AWS Bedrock setup with CDK, also includes a Streamlit page to retrieve information through a chat-like interface
https://github.com/riolaf05/aws-cdk-ts-bedrock-rag-agent-platform

aws aws-bedrock aws-lambda bedrock cdk generative-ai infrastructure-as-code python rag retrieval-augmented-generation streamlit

Last synced: 13 days ago
JSON representation

AWS Bedrock setup with CDK, also includes a Streamlit page to retrieve information through a chat-like interface

• Host: GitHub
• URL: https://github.com/riolaf05/aws-cdk-ts-bedrock-rag-agent-platform
• Owner: riolaf05
• Created: 2024-06-21T11:50:30.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-06-21T14:44:10.000Z (8 months ago)
• Last Synced: 2024-11-20T19:44:45.918Z (2 months ago)
• Topics: aws, aws-bedrock, aws-lambda, bedrock, cdk, generative-ai, infrastructure-as-code, python, rag, retrieval-augmented-generation, streamlit
• Language: JavaScript
• Homepage:
• Size: 91.8 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Welcome to your CDK JavaScript project

## Useful commands

* `npm run test`         perform the jest unit tests

* `npx cdk deploy`       deploy this stack to your default AWS account/region

* `npx cdk diff`         compare deployed stack with current state

* `npx cdk synth`        emits the synthesized CloudFormation template

# Architecture

![Alt text](./architecture.jpg "architecture")

# Prerequisites

* AWS Cli

* NPM 

```console

curl -o- https://raw.githubusercontent.com/creationix/nvm/v0.33.8/install.sh | bash

nvm install node npm

npm i

```

Tested with 

NodeJS v22.3.0

npm 10.8.1

* CDK 

* Docker 

* Access to `amazon.titan-embed-text-v1` e `anthropic.claude-instant-v1` model on Bedrock

# Getting started

1. `cdk build`

2. `aws s3 sync data s3://resumeaistack-b7-kdx14wcvfzst^Cedrockragbucketdfd7a7c7-kdx14wcvfzst`

3. update .env file in `streamlit/`

4. `strealit run streamlit/main.py`

# Clean 

1. `cdk destroy`

# References

* [Easy Serverless RAG with Knowledge Base for Amazon Bedrock](https://community.aws/content/2bi5tqITxIperTzMsD3ohYbPIA4/easy-rag-with-amazon-bedrock-knowledge-base)

* [Implementing RAG App Using Knowledge Base from Amazon Bedrock and Streamlit](https://medium.com/@saikatm.courses/implementing-rag-app-using-knowledge-base-from-amazon-bedrock-and-streamlit-e52f8300f01d)