GenAI chatbot with multi-agents and RAG using Amazon Bedrock¶

Many websites contain large amounts of information, making it challenging for users to find specific answers quickly. This project aims to develop an assistant powered by LLMs capable of answering user queries based on the content of a specific website. The process involves retrieving relevant information from the target website's pages (e.g., via scraping) and utilizing an LLM to understand the user's question and synthesize an accurate answer from the retrieved content. A key focus will be the implementation of multi-agent collaboration, utilizing advanced cloud capabilities such as the multi-agent collaboration capability for Amazon Bedrock (https://aws.amazon.com/blogs/aws/introducing-multi-agent-collaboration-capability-for-amazon-bedrock/) to decompose complex queries into specialized tasks. The ultimate goal is to create a functional prototype demonstrating improved information access and user experience (e.g. ReactJS UI https://ai-sdk.dev/).

Keywords: Multi-agent Systems, RAG, Amazon Bedrock, Cloud Computing Prerequisite for the project: background in Python and Cloud Infrastructure