📚 Doctype.io

AI-Powered Document Intelligence Platform

Transform your documents into conversations. Upload PDFs and get instant, accurate answers powered by advanced RAG technology.

Features • Quick Start • Demo • API Docs • Contributing

---

✨ Features

🎯 Core Capabilities 📄 Smart PDF Processing - Upload and parse documents instantly 🤖 AI-Powered Q&A - Natural language queries with context-aware responses 🧠 RAG Architecture - Retrieval-Augmented Generation for accurate answers 💾 Vector Storage - Efficient document embeddings with Upstash

🔧 Technical Features 🔐 Secure Authentication - Powered by Clerk ⚡ Real-time Processing - Fast document ingestion and retrieval 📊 Interactive API Docs - Built-in Swagger UI 🎨 Modern UI - Smooth animations with Framer Motion

---

🏗️ Architecture

graph LR
    A[User] --> B[React Frontend]
    B --> C[FastAPI Backend]
    C --> D[LangChain RAG]
    D --> E[Google Gemini]
    D --> F[Upstash Vector DB]
    C --> G[Clerk Auth]

Loading

---

🛠️ Tech Stack

Backend Technologies

Technology	Purpose
	High-performance API framework
	RAG orchestration & chains
	Embeddings & chat completions
	Serverless vector database
	PDF parsing & extraction

Frontend Technologies

Technology	Purpose
	UI framework
	Type-safe development
	Utility-first CSS
	Animation library
	Authentication & user management

---

🚀 Quick Start

Prerequisites

• Python 3.8+
• Node.js 16+
• npm or yarn

⚙️ Backend Setup

# Navigate to backend directory
cd backend

# Create and activate virtual environment
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Configure environment variables
cp .env.example .env
# Edit .env with your API keys (see Environment Variables section)

# Start the server
uvicorn app.main:app --reload

🌐 Backend runs on: http://127.0.0.1:8000

🎨 Frontend Setup

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Configure environment variables
cp .env.example .env
# Edit .env with your Clerk key

# Start development server
npm start

🌐 Frontend runs on: http://localhost:3000

---

🔑 Environment Variables

Backend Configuration (.env)

# Google AI
GOOGLE_API_KEY=your_google_api_key_here

# Upstash Vector Database
UPSTASH_VECTOR_REST_URL=your_upstash_url_here
UPSTASH_VECTOR_REST_TOKEN=your_upstash_token_here

# Clerk Authentication
CLERK_SECRET_KEY=your_clerk_secret_key_here

# CORS
FRONTEND_URL=http://localhost:3000

🔗 Get Your API Keys:

• Google AI Studio - For Gemini API access
• Upstash Console - For vector database
• Clerk Dashboard - For authentication

Frontend Configuration (.env)

# API Configuration
REACT_APP_API_URL=http://127.0.0.1:8000

# Clerk Authentication
REACT_APP_CLERK_PUBLISHABLE_KEY=your_clerk_publishable_key_here

---

🎯 Usage

1. 🔐 Sign In - Authenticate using Clerk
2. 📤 Upload PDF - Drop your document or click to upload
3. 💬 Ask Questions - Type your questions in natural language
4. ✨ Get Answers - Receive AI-powered responses with context

---

📡 API Documentation

Interactive API documentation is automatically generated and available at:

🔗 Swagger UI: http://127.0.0.1:8000/docs

Main Endpoints

Method	Endpoint	Description
GET	/	Health check & API status
POST	/ingest	Upload and process PDF documents
POST	/chat	Query documents with natural language

Example Request

curl -X POST "http://127.0.0.1:8000/chat" \
  -H "Content-Type: application/json" \
  -d '{
    "question": "What is the main topic of this document?",
    "session_id": "user123"
  }'

---

⚠️ Rate Limits

Google’s free tier includes the following limits:

Limit Type	Value
Daily Requests	1,500
Requests per Minute	15

The system includes built-in rate limiting and automatic retry logic to handle these limits gracefully.

---

🗺️ Roadmap

• Support for multiple document formats (DOCX, TXT, etc.)
• Multi-document querying
• Export conversation history
• Custom AI model selection
• Advanced search filters
• Document summarization
• Mobile app

---

🤝 Contributing

Contributions are what make the open-source community amazing! Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

📄 License

Distributed under the MIT License. See LICENSE for more information.

---

🙏 Acknowledgments

Special thanks to these amazing technologies:

• Google Generative AI - Powerful embeddings and chat models
• Upstash - Serverless vector database
• LangChain - RAG framework and orchestration
• Clerk - User authentication and management
• FastAPI - Modern Python web framework
• React - Frontend library

---

⭐ Star this repo if you find it helpful!

Made with ❤️ by noturbob

Report Bug • Request Feature