Business RAG Assistant

Overview

Business RAG Assistant is an AI-powered application designed for companies to provide accurate internal information based on user queries. The system uses Retrieval-Augmented Generation (RAG) to retrieve relevant company data from a vector database and generate intelligent responses using an LLM.

This project is useful for answering questions like:

• Company details
• Management information (CEO, Manager, etc.)
• Salary structure
• Internal policies and general company knowledge

How It Works

1. Company data is stored in Qdrant vector store.
2. When a user asks a question, relevant data is retrieved from Qdrant.
3. The retrieved data is analyzed using DeepSeek LLM API.
4. A clear and accurate response is generated for the user.

Privacy & Security

To maintain privacy and security:

• API keys and URLs are NOT exposed in the codebase.
• Sensitive information is managed using environment variables and configuration files.

Environment Variables (.env)

Create a .env file in the root directory and add your LLM API keys there.

DEEPSEEK_API_KEY=your_api_key_here

Configuration (config.json)

The config.json file is used to store:

• Qdrant API key
• Qdrant URL

This file allows easy configuration without modifying core code.

Vector Store Setup

• The notebook vector_store_setup.ipynb is provided.
• Use it to:
• Upload your data to Qdrant
• Create embeddings
• Store and retrieve vectors efficiently

Project Structure

business-rag-assistant/
│
├── Images/
│   ├── Screenshot 2026-01-03 211644.png
│   ├── Screenshot 2026-01-03 214912.png
│   └── Screenshot 2026-01-03 215256.png
│
├── Code/
│   └── vector_store_setup.ipynb
├── README.md
├── app.py
├── config.json
├── index.html
├── requirements.txt

Installation & Setup

1. Clone the Repository

git clone https://github.com/AzeemAIDev/business-rag-assistant.git
cd business-rag-assistant

2. Install Dependencies

pip install -r requirements.txt

3. Run Backend Server

uvicorn app:app --port 8000

4. Run Frontend

• Right-click on index.html
• Select Open with Live Server

Technologies Used

• Python
• FastAPI
• Qdrant Vector Database
• DeepSeek LLM API
• Retrieval-Augmented Generation (RAG)

Author

Azeem
ML Engineer & AI Learner
https://github.com/AzeemAIDev