🤖 Multi-Document RAG Chatbot (Streamlit + Gemini)

This is a Streamlit-based RAG (Retrieval-Augmented Generation) chatbot that allows users to upload documents and chat with them using Google Gemini models and LangChain.

Users can:

• Upload different document types
• Ask questions from the document
• Save chat history
• Continue previous chats with the same document

---

🚀 Features

• 📂 Upload multiple file formats:
  • PDF
  • DOCX
  • TXT
  • CSV
  • PPT / PPTX
  • Images (PNG, JPG, JPEG) with OCR using Gemini Vision
• 💬 Chat with document using RAG
• 🧠 Uses vector database (Chroma)
• 🕒 Chat history with separate folders per chat
• 🔁 Continue previous chats
• 🎨 Professional Streamlit UI

---

🧱 Project Structure

project_folder/
│
├── app.py            # Streamlit UI
├── rag_engine.py     # Document processing and RAG logic
├── utils.py          # Chat history save/load utilities
├── chat_history/     # Auto-created chat folders
├── .env              # API keys
└── README.md

---

🔧 Requirements

• Python 3.9+
• Google Gemini API Key

📦 Install Dependencies

## 🛠️ Installation

Install the required packages:

```bash
pip install streamlit langchain chromadb python-dotenv langchain-google-genai unstructured

🔐 Environment Setup

1. Create a .env file in the project root:

GOOGLE_API_KEY=your_api_key_here

2. Set the embedding model in config.py (if used):

EMBEDDING_MODEL = "models/embedding-001"

🚀 Running the App

Run this command in your project folder:

streamlit run app.py

Then open this link in your browser:

http://localhost:8501