🦾 Agentic RAG with Redis, AWS Bedrock, and LlamaIndex

Overview

This demo demonstrates the integration of Redis, Amazon Bedrock, and LlamaIndex for creating a customer support chatbot specifically tailored for Chevy vehicles. The system is powered by an "agentic RAG" architecture.

Key Components

• Redis: A versatile db within the architecture, Redis functions as the document store, ingestion cache, vector store, chat history store, and semantic cache.
• Amazon Bedrock: Provides foundation models and embeddings models through the Bedrock API.
• LlamaIndex: 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
• LlamaIndex Documentation
• LlamaIndex <> Redis Integration
• Amazon Bedrock Console