Skip to content

README.md

Latest commit

 

History

History
75 lines (49 loc) · 1.64 KB

README.md

File metadata and controls

75 lines (49 loc) · 1.64 KB

📄 Suraj RAG Project (Gemini + Streamlit)

A simple Retrieval-Augmented Generation (RAG) project using Google Gemini LLM + Streamlit UI.
This app lets you upload PDFs, create embeddings, and ask questions to get intelligent answers.

✨ Features

  • 📂 Upload PDF files
  • 📝 Extract and process text
  • 🧠 Build vector embeddings with FAISS
  • 🔍 Ask questions and get answers from Gemini LLM
  • 🌐 Easy-to-use Streamlit interface

🚀 Installation & Run

1️⃣ Clone Repository

git clone https://github.com/your-username/RAG_Model_PDF.git
cd RAG_Model_PDF

2️⃣ Setup Environment
python3 -m venv .venv
source .venv/bin/activate   # Linux/Mac
.venv\Scripts\activate      # Windows

3️⃣ Install Requirements
pip install -r requirements.txt

4️⃣ Configure API Key

Create a .env file in project root:

GOOGLE_API_KEY=your_api_key_here

5️⃣ Run the App
streamlit run app.py


Open 👉 http://localhost:8501

📂 Project Structure
RAG_Model_PDF/
│── app.py                 # Main Streamlit app
│── requirements.txt        # Dependencies
│── README.md               # Documentation
│── utils/
│   ├── index_builder.py    # FAISS index creation
│   ├── rag_qa_engine.py    # RAG QA logic
│── .env                    # (Your API key here)
│── .venv/                  # Virtual environment

🛠️ Requirements

Python 3.11+

Streamlit

LangChain

FAISS

Sentence Transformers

Google Generative AI

📌 Example Usage

Upload sample.pdf

Ask: "What is this document about?"

Get instant answers powered by RAG + Gemini 🚀# RAG_Model_PDF