RAG Assistant with Streamlit (Google Gemini Powered)

📌 Overview

This project is a Retrieval-Augmented Generation (RAG) Assistant built with Streamlit and powered by Google Gemini.
It allows users to query documents and receive context-aware answers, making it useful for research assistance, document analysis, and learning support.

🎯 Features

• 📂 Upload and process local documents (JSON in this version).
• 🔍 Retrieve relevant context using embeddings.
• 💬 Generate AI-powered answers with Google Gemini.
• 🌐 Simple and interactive Streamlit interface.
• ⚡ Lightweight and easy to run locally.

👥 Target Audience

• Students and researchers who need quick answers from large documents.
• Developers exploring RAG implementations with LangChain and Gemini.
• Professionals who want a simple assistant for document Q&A.

🛠️ Prerequisites

• Python 3.9+
• Google API Key for Gemini

⚙️ Installation

1. Clone the repository:

   git clone https://github.com/ashuuu2409/rag-assistant.git
   cd rag-assistant

2. Create a virtual environment:

   python -m venv venv
   venv\Scripts\activate        # Windows
   source venv/bin/activate     # Mac/Linux

3. Install dependencies:

   pip install -r requirements.txt

4. Set your API key:

   setx GOOGLE_API_KEY "your_api_key_here"        # Windows
   export GOOGLE_API_KEY="your_api_key_here"      # Mac/Linux

🚀 Usage

Run the Streamlit app:

streamlit run project1.py

This will launch a web interface where you can upload a document and start asking questions.

📂 Project Structure

rag-assistant/
│── project1.py         # Main RAG + Streamlit code
│── requirements.txt    # Dependencies
│── README.md           # Documentation
│── LICENSE             # License file

📜 License

This project is licensed under the MIT License.
© 2025 Ashutosh Rajpal

---