OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Amazon Bedrock Rag

Amazon Bedrock Rag is a JavaScript AWS sample repository for a managed retrieval-augmented generation question-and-answer application. It connects S3 documents and crawled website content to Amazon Bedrock Knowledge Bases, with Amazon OpenSearch Serverless used for vector storage.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Amazon Bedrock Rag — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the sample when you want to explore a managed AWS RAG workflow that ingests S3 documents and website content for chatbot retrieval.

Who it is for

  • Developers exploring an AWS implementation of retrieval-augmented generation.
  • Teams prototyping question-answering over documents and published website content.

Documented uses

  • Ground language-model answers in an external document collection.
  • Add website content as a retrievable knowledge source.
  • Prototype a cloud-hosted Q&A chatbot using Amazon Bedrock Knowledge Bases.
Before you choose

Requirements & limits

The documented deployment requires configured AWS CLI and CDK access and a Bedrock-supported region. The README notes a minimum charge of four OpenSearch Serverless OCUs at all times.

  • Knowledge Bases handles ingestion, retrieval and prompt augmentation, while the sample configures S3 and web-crawler data sources.
  • Website content is not available to the chatbot until the web-crawler source has been manually synchronized.
  • The README identifies Anthropic Claude as the default generation model and Amazon Titan Embeddings for the knowledge base.
  • The sample uses Amazon OpenSearch Serverless for vector storage and documents a minimum ongoing charge of four OCUs.
  • The repository is licensed under MIT-0.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare and deploy the backend

Deploy the sample backend to AWS and record the API URL and document bucket for later use.

Before you start

  • AWS CLI installed and configured
  • AWS CDK installed and bootstrapped
  • An Amazon Bedrock-supported AWS region
  • A client IP address in CIDR format for the API access context

Steps

  1. Clone the repository and install dependencies from its backend folder with npm install.

  2. From the backend folder, deploy with CDK and set the allowedip context to the client IP in CIDR format.

  3. Record the BackendStack.APIGatewayUrl and BackendStack.DocsBucketName outputs.

Expected outcome

The backend is deployed and the API Gateway URL and S3 document bucket name are available for subsequent setup.

Guide limitations

  • This guide covers the backend deployment stage, not a complete frontend launch or end-to-end run.
  • The sample documents a minimum ongoing charge of four OCUs for Amazon OpenSearch Serverless.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
aws-samples/amazon-bedrock-rag · Official homepage title · retained in its source language
How we review sourcesSuggest a correction