Build a RAG Document Chatbot using Llama LLM Models

Overview

A Retrieval-Augmented Generation (RAG) chatbot powered by the Ollama platform, designed to deliver precise and context-aware responses by combining document retrieval with generative AI. The system efficiently indexes and retrieves relevant documents, seamlessly integrating them into AI-generated conversational responses, making it an ideal solution for knowledge management and customer support applications.

Architecture

Install the Requirements

pip3 install -r requirements

Run the Flask Application

python3 app.py

Usage

Create a new Session

Open the sessions created

Upload and Process the document

Wait until the document finished process

Start Chat with your document