LLMOps: Deploying RaG Application with Qdrant, Langchain, and OpenAI

This repository contains the code and resources for deploying a Retrieval-Augmented Generation (RaG) application using Qdrant, Langchain, and OpenAI technologies. The project demonstrates how to integrate these tools to build a robust and scalable application for information retrieval and generation.

Features

• Document Preprocessing: Load and preprocess documents for indexing.
• Document Indexing: Store documents in Qdrant for efficient retrieval.
• Question Retrieval: Use Langchain and OpenAI to retrieve and generate answers from indexed documents.

Getting Started

Prerequisites

• Python 3.7+
• Uvicorn (for running the FastAPI application)
• FastAPI
• Qdrant
• Langchain
• OpenAI

Installation

1. Clone the repository:

   git clone https://github.com/Saba-Gul/LLMOps-Deploying-RaG-Application-With-Qdrant-Langchain-OpenAI.git
   cd LLMOps-Deploying-RaG-Application-With-Qdrant-Langchain-OpenAI