aws-samples/serverless-rag-demo
Amazon Bedrock Foundation models with Amazon Opensearch Serverless as a Vector DB
This solution helps business users, researchers, or anyone needing to extract specific information from large collections of documents. It takes your documents (like reports, manuals, or research papers) and questions as input, then provides precise, context-aware answers, summaries, sentiment analysis, or even redacts sensitive information. It's ideal for professionals who need to quickly understand and interact with their specialized knowledge bases without sifting through pages manually.
215 stars.
Use this if you need to rapidly get answers from your specific business or research documents, want to automate document summarization, or perform tasks like sentiment analysis and PII redaction without managing complex AI infrastructure.
Not ideal if you do not have an AWS account, are uncomfortable with basic AWS service setup, or primarily need a general-purpose AI chatbot not specialized for your own documents.
Stars
215
Forks
69
Language
Python
License
MIT-0
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/aws-samples/serverless-rag-demo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
aws-samples/generative-ai-use-cases
Application implementation with business use cases for safely utilizing generative AI in...
aws-samples/amazon-bedrock-rag
Fully managed RAG solution implemented using Knowledge Bases for Amazon Bedrock
IBM/granite-workshop
Source code for the IBM Granite AI Model Workshop
aws-samples/rag-with-amazon-bedrock-and-opensearch
Opinionated sample on how to build and deploy a RAG application with Amazon Bedrock and OpenSearch
aws-samples/generative-bi-using-rag
A solution guidance for Generative BI using Amazon Bedrock, Amazon OpenSearch with RAG