In this guide, we will build an LLM Chatbot that uses Retrieval Augmented Generation to answer questions about a particular blog or a list of blogs. We use LlamaIndex to chunck the blog text and build index, and then provide this context from the blog chunks along with the prompt to the GPT-4 model to build the chatbot.
By the end of this session, you will have an interactive web application deployed that helps answer questions from the blog.
For prerequisites, environment setup, step-by-step guide and instructions, please refer to the QuickStart Guide.