Micro Learning - PDF Quiz Generator

A terminal application that uses spaCy + Ollama to analyze PDFs and create intelligent True/False quizzes with structured data extraction.

Installation

1. Install Python dependencies:

pip install -r requirements.txt

2. Download spaCy model for English (recommended):

python -m spacy download en_core_web_trf

Alternatives (if space is limited):

python -m spacy download en_core_web_md   # Good accuracy
python -m spacy download en_core_web_sm   # Fast but basic

3. Install Ollama:

# macOS
brew install ollama

# Linux
curl -fsSL https://ollama.ai/install.sh | sh

# Windows
# Download from https://ollama.ai/download

4. Install Ollama Python package:

pip install ollama

5. Download Ollama model:

ollama pull llama2

Usage

1. Place your PDF file in the pdfs/ folder

2. Start Ollama service (in a separate terminal):

ollama serve

3. Run the application (in another terminal):

python main.py

4. Follow the instructions to select PDF and answer questions

Important Notes:

• Keep ollama serve running while using the application
• The first run may take longer as models are loaded
• If AI is not available, the system will use rule-based questions as fallback

Features

• Structured Data Extraction: spaCy extracts entities, relationships, and facts from PDFs
• AI-Powered Questions: Ollama generates intelligent questions from structured data
• Hybrid Approach: Combines rule-based extraction with AI generation for best results
• Fallback System: Works even without AI (rule-based questions as backup)
• Interactive Quiz: Elegant terminal interface with immediate feedback
• Educational Quality: Questions test understanding, not just memorization
• Multi-Model Support: Automatically selects best available spaCy model (trf > md > sm)

System Requirements

• Python 3.8+
• 4GB+ RAM (for Ollama models)
• Internet connection (for initial model downloads)
• macOS/Linux/Windows (Ollama support)