aws-samples/genai-quickstart-pocs

This repository contains sample code demonstrating various use cases leveraging Amazon Bedrock and Generative AI. Each sample is a separate project with its own directory, and includes a basic Streamlit frontend to help users quickly set up a proof of concept.

What it solves

This repository provides a collection of proof-of-concept (POC) implementations demonstrating how to integrate Amazon Bedrock and Generative AI into various real-world business use cases. It helps developers quickly prototype and validate AI capabilities without building from scratch.

How it works

Each sample is a standalone Python project with a Streamlit frontend. These projects leverage Amazon Bedrock to access various LLMs and multimodal models, integrating with other AWS services like Amazon Athena, RDS, Redshift, OpenSearch Serverless, and Kendra for data retrieval, and Amazon Transcribe for audio/video processing.

Who it’s for

Developers and architects looking to build Generative AI applications on AWS, specifically those needing concrete examples of how to implement RAG, multimodal analysis, and automated document processing.

Highlights

  • Data Querying: Natural language interfaces for relational databases (Athena, RDS, Redshift).
  • RAG Implementations: Multiple patterns using Bedrock Knowledge Bases, LangChain, Kendra, and OpenSearch Serverless.
  • Multimodal Capabilities: Image analysis, alt-text generation for PDFs, and image generation with safety guardrails.
  • Document Intelligence: Intelligent Document Processing (IDP) for extraction, summarization, and comparison of documents.
  • Specialized Tools: A PowerPoint generator, a video chapter creator, and a model evaluation data preparation tool.

Related

  • Project
    aws-samples/generative-ai-use-cases

    A well-architected AWS application framework providing a suite of generative AI use cases, RAG capabilities, and a no-code builder for business operations.

  • Project
    aws-samples/bedrock-chat

    A multilingual generative AI platform powered by Amazon Bedrock that enables the creation, sharing, and management of custom RAG-enabled bots and AI agents.

  • Project
    awslabs/amazon-bedrock-agent-samples

    A collection of reference implementations and best practices for building single and multi-agent AI assistants using Amazon Bedrock Agents.

  • Project
    aws-solutions/generative-ai-application-builder-on-aws

    A web-based management dashboard for deploying and experimenting with customizable Generative AI use cases on AWS, supporting RAG-enabled chatbots and AI agents.

  • Project
    aws-samples/amazon-bedrock-serverless-prompt-chaining

    A collection of examples and techniques for building scalable, serverless generative AI applications using prompt chaining with AWS Step Functions and Amazon Bedrock Flows.