Building an Intelligent QA/Chatbot with LangChain and Open Source LLMs

This project developed a web-application Q/A chatbot that enables users to interact with Large Language models (LLMs) through a collection format. The system implemented a Retrieval Augmented Generation (RAG) pipeline to provide context-specific responses based on either user-uploaded documents (.txt, .html, and .zip formats) or user uploaded URLs. The application features secure user authentication, multiple- instances of chat/document contexts through collections, document up- load, and standard LLM chatbot functionalities, including the ability to switch between LLMs. This report will give readers an understanding of how the application was designed and developed; how to install and use the application; how to continue development of the application; lessons learned during development; and future plans for the project.