https://github.com/redis-developer/agentic-rag

Complete example of how to build an Agentic RAG architecture with Redis, AWS Bedrock, and LlamaIndex.
https://github.com/redis-developer/agentic-rag

agents ai21labs amazon-bedrock amazon-titan genai-chatbot llama-index rag redis testcontainers vector-search

Last synced: 7 days ago
JSON representation

Complete example of how to build an Agentic RAG architecture with Redis, AWS Bedrock, and LlamaIndex.

• Host: GitHub
• URL: https://github.com/redis-developer/agentic-rag
• Owner: redis-developer
• License: mit
• Created: 2024-04-23T16:25:54.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-12-05T14:50:06.000Z (about 2 months ago)
• Last Synced: 2025-01-08T13:17:05.920Z (14 days ago)
• Topics: agents, ai21labs, amazon-bedrock, amazon-titan, genai-chatbot, llama-index, rag, redis, testcontainers, vector-search
• Language: Jupyter Notebook
• Homepage: https://redis.io/solutions/vector-database
• Size: 2.27 MB
• Stars: 82
• Watchers: 5
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• redis-ai-resources - Agentic RAG
• redis-ai-resources - Agentic RAG

README

        
🦾 Agentic RAG with Redis, AWS Bedrock, and LlamaIndex


## Overview

This demo demonstrates the integration of [Redis](https://redis.io), [Amazon Bedrock](https://aws.amazon.com/bedrock/), and [LlamaIndex](https://docs.llamaindex.ai/en/stable/) for creating a **customer support chatbot** specifically tailored for Chevy vehicles. The system is powered by an "agentic RAG" architecture.

## Key Components



  

  

  



- **[Redis](https://redis.io)**: A versatile db within the architecture, Redis functions as the document store, ingestion cache, vector store, chat history store, and semantic cache.

- **[Amazon Bedrock](https://aws.amazon.com/bedrock/)**: Provides foundation models and embeddings models through the Bedrock API.

- **[LlamaIndex](https://docs.llamaindex.ai/en/stable/)**: Acts as the central framework that ties together the entire system, enabling seamless integration with various services and tools to enhance functionality.

## Getting Started

Launch this notebook in a Google Colab environment for a hands-on experience:



  Open in Colab



## Architecture Diagram

 This architecture highlights document ingestion and inference with the AI agent.



  



## Additional Resources

For further reading and resources related to the technologies and approaches used in this project, consider the following links:

- [Redis Documentation](https://redis.io/docs/)

- [LlamaIndex Documentation](https://docs.llamaindex.ai/en/stable/)

- [LlamaIndex <> Redis Integration](https://docs.llamaindex.ai/en/latest/examples/vector_stores/RedisIndexDemo/)

- [Amazon Bedrock Console](https://aws.amazon.com/bedrock/)