Researcho

AI-Powered Research Assistant

Generate reports, literature reviews, chat with documents, and create presentations — all powered by local AI.

---

🌟 Features

📝 Quick Report Generation

Generate detailed technical reports on any topic with AI assistance:

• Structured academic format (Title, Abstract, Introduction, Methodology, Analysis, Conclusion)
• Automatic citation formatting
• Download as PDF or DOCX

📚 Literature Review

Search ArXiv for academic papers and generate comprehensive literature reviews:

• Automatic paper discovery from ArXiv database
• AI-synthesized summaries of research papers
• Research gap identification
• Cohesive academic writing style

💬 RAG Chat Interface

Upload multiple PDF/DOCX documents and have intelligent conversations:

• Multi-document support (like NotebookLM)
• Context-aware responses based on your documents
• Real-time WebSocket chat
• Document management (add/remove documents)

🎯 Presentation Generator

Create PowerPoint presentations from research papers:

• Automatic slide generation with key points
• Editable slide preview before download
• Custom title and bullet point editing
• Direct PPTX download

---

🛠️ Tech Stack

Backend

Technology	Purpose
FastAPI	Modern Python web framework
Ollama	Local LLM (qwen3-vl:2b multimodal)
LangChain	LLM orchestration and RAG
FAISS	Vector store for embeddings
HuggingFace	Local embeddings (sentence-transformers)
ArXiv API	Academic paper retrieval
python-pptx	PowerPoint generation
ReportLab	PDF generation

Frontend

Technology	Purpose
React 19	UI library
Vite 7	Build tool and dev server
React Router v7	Client-side routing
Vanilla CSS	Custom styling

---

📦 Prerequisites

Before you begin, ensure you have the following installed:

• Python 3.12+ - Download Python
• Node.js 18+ - Download Node.js
• Ollama - Download Ollama

---

🚀 Quick Start

1. Clone the Repository

git clone <your-repo-url>
cd MyPro

2. Set Up Ollama

# Install Ollama from https://ollama.ai

# Pull the required model
ollama pull qwen3-vl:2b

# Start Ollama server (if not running as a service)
ollama serve

3. Set Up the Backend

# Navigate to backend
cd backend

# Create virtual environment
python -m venv venv

# Activate virtual environment
# Windows:
.\venv\Scripts\activate
# Linux/macOS:
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Start the backend server
python mainback.py

The backend API will be available at http://localhost:8000

4. Set Up the Frontend

# Open a new terminal and navigate to frontend
cd frontend

# Install dependencies
npm install

# Configure environment (optional)
cp .env.example .env
# Edit .env to set: VITE_API_URL=http://localhost:8000

# Start the development server
npm run dev

The frontend will be available at http://localhost:5173

---

📁 Project Structure

MyPro/
├── backend/                    # FastAPI Backend
│   ├── mainback.py            # Main application file
│   ├── requirements.txt       # Python dependencies
│   ├── pyproject.toml         # Project configuration
│   ├── .env.example           # Environment template
│   └── README.md              # Backend documentation
│
├── frontend/                   # React Frontend
│   ├── public/
│   │   └── researcho.png      # App favicon/logo
│   ├── src/
│   │   ├── components/        # Reusable UI components
│   │   │   ├── Header.jsx
│   │   │   ├── LoadingSpinner.jsx
│   │   │   ├── Toast.jsx
│   │   │   └── ToastContainer.jsx
│   │   ├── contexts/          # React context providers
│   │   │   └── AppContext.jsx
│   │   ├── hooks/             # Custom React hooks
│   │   ├── sections/          # Page components
│   │   │   ├── Home.jsx       # Landing page
│   │   │   ├── Report.jsx     # Report generation
│   │   │   ├── Review.jsx     # Literature review
│   │   │   ├── RAG.jsx        # Document chat
│   │   │   └── PPTX.jsx       # Presentation generator
│   │   ├── App.jsx            # Main app component
│   │   ├── App.css
│   │   ├── index.css          # Global styles
│   │   └── main.jsx           # Entry point
│   ├── index.html
│   ├── package.json
│   ├── vite.config.js
│   └── README.md              # Frontend documentation
│
└── README.md                   # This file

---

🔗 API Reference

Base URL

http://localhost:8000

Endpoints

Health Check

Method	Endpoint	Description
GET	/	API info and endpoints
GET	/api/health	Health check

Report Generation

Method	Endpoint	Description
POST	/api/generate/report	Generate technical report

// Request Body
{ "content": "Your research topic" }

Literature Review

Method	Endpoint	Description
POST	/api/generate/review	Generate literature review

// Request Body
{ "content": "Your research topic" }

RAG Chat

Method	Endpoint	Description
POST	/api/upload/pdf	Upload PDF/DOCX files
POST	/api/chat	Chat with documents
WebSocket	/api/chat/ws	Real-time chat
GET	/api/documents	List documents
DELETE	/api/documents/{id}	Delete document
DELETE	/api/documents	Clear all documents

// Chat Request Body
{ "message": "Your question" }

Presentation

Method	Endpoint	Description
POST	/api/generate/pptx	Generate from file upload
POST	/api/generate/pptx/from-id	Generate from stored file
GET	/api/pptx/download/{id}	Download PPTX
POST	/api/pptx/update	Update slides

Downloads

Method	Endpoint	Description
POST	/api/download/docx	Download as DOCX
POST	/api/download/pdf	Download as PDF

---

⚙️ Configuration

Backend Configuration

Changing the LLM Model (backend/mainback.py):

llm = ChatOllama(model="qwen3-vl:2b")  # Default

# Alternatives:
# llm = ChatOllama(model="llama3:8b")
# llm = ChatOllama(model="mistral:7b")
# llm = ChatOllama(model="gemma2:9b")

CORS Settings (for production):

app.add_middleware(
    CORSMiddleware,
    allow_origins=["https://yourdomain.com"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

Frontend Configuration

API URL (frontend/.env):

VITE_API_URL=http://localhost:8000

---

📝 Available Scripts

Backend

Command	Description
python mainback.py	Start dev server
uvicorn mainback:app --reload	Start with auto-reload
uvicorn mainback:app --workers 4	Production mode

Frontend

Command	Description
npm run dev	Start dev server
npm run build	Build for production
npm run preview	Preview production build
npm run lint	Run ESLint

---

📖 API Documentation

When the backend is running, interactive API documentation is available at:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

---

🌐 Browser Support

Browser	Minimum Version
Chrome	90+
Firefox	90+
Safari	14+
Edge	90+

---

🤝 Contributing

1. Fork the repository
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

This project is licensed under the MIT License.

---

Researcho - AI-powered research assistance made simple.

Made with ❤️ for researchers everywhere.