Welcome to Corpus! This guide will get you up and running in minutes.
git clone https://github.com/yourusername/corpus-cli.git
cd corpus-cli
./install.sh # or install.ps1 on Windowsgit clone https://github.com/yourusername/corpus-cli.git
cd corpus-cli
make installThe installer will prompt you to configure. If you skipped it:
# Activate virtual environment first
source env/bin/activate # or env\Scripts\activate on Windows
# Run configuration wizard
corpus config setupYou'll need:
- A Google Gemini API key (get one at https://makersuite.google.com/app/apikey)
Let's index some documents:
# Index a single PDF
corpus index ~/Documents/research-paper.pdf
# Index a folder
corpus index ~/Documents/Research
# Index Python code
corpus index ~/Projects/my-app --pattern "*.py"Now the fun part - talk to your documents:
# Start interactive chat
corpus chat
# Ask a specific question
corpus ask "What are the main findings in the research?"
# Chat with specific documents
corpus chat --filter "research*.pdf"If you have D2 installed:
# Generate from description
corpus diagram "user authentication flow"
# Generate from your documents
corpus diagram --search "system architecture"corpus status # Check what's indexed
corpus list # List all documents
corpus update ~/Docs # Update with new files
corpus clear # Start fresh- Index related documents together - This gives better context for answers
- Use descriptive filenames - Makes filtering easier
- Ask specific questions - "What does section 3.2 say about X?" works better than "tell me about X"
- Read the full documentation:
corpus --help - Explore configuration options:
corpus config show - Set up document watching:
corpus watch ~/Documents
- Run
corpus --helpfor command details - Check configuration:
corpus config validate - View system info:
corpus info
Happy researching! 🎉