Skip to main content

A tool for collecting and documenting code for LLM context

Project description

Viterbo

A tool for collecting and documenting code files for LLM context.

Overview

Viterbo helps collect source code files from various languages and compile them into a readable format for inclusion in LLM prompts. It scans directories for code files, extracts structured information like docstrings and comments, and generates comprehensive documentation in text or markdown format.

Features

  • Multi-language support: Python, C/C++, R, JavaScript, TypeScript, and many other languages
  • Directory tree visualization: Shows the structure of your codebase
  • Documentation extraction: Extracts docstrings, comments, and code structure
  • Output formats: Generate documentation in plain text or markdown
  • README inclusion: Optionally include README.md files in the documentation
  • Line numbering: Add line numbers to code for easy reference
  • Organized output: Collects code with clear section headers showing file paths

Installation

# Install with Poetry
poetry install

# Or using pip
pip install viterbo

Usage

Command Line

# Basic usage (Python files only)
viterbo source_directory output_file [--include-docstrings] [--add-line-numbers]

# Enhanced usage with multi-language support
viterbo /path/to/source output.txt --extensions .py .cpp .h .R

# Include README.md files
viterbo /path/to/source output.txt --include-readme

# Extract and include docstrings/comments
viterbo /path/to/source output.txt --include-docstrings

# Add line numbers to code
viterbo /path/to/source output.txt --add-line-numbers

# Generate markdown output
viterbo /path/to/source output.md --format md

Python API

from viterbo import document_files

# Document Python and C++ files in markdown format
document_files(
    source_dir="/path/to/source",
    output_file="output.md",
    file_extensions=[".py", ".cpp", ".h"],
    include_readme=True,
    include_docstrings=True,
    add_line_numbers=True,
    output_format="md"
)

# For backward compatibility, the original function is still available
from viterbo import document_python_files

document_python_files(
    source_dir="/path/to/source",
    output_file="output.txt",
    include_docstrings=True,
    add_line_numbers=True
)

Output Examples

Text Output

# Code Documentation
# Generated on: 2025-05-01 10:21:33
# Source: /path/to/source

# Directory Structure:
/path/to/source/
├── README.md
├── src/
│   ├── main.py
│   └── utils.py
└── tests/
    └── test_main.py
...

Markdown Output

The markdown output includes syntax highlighting and better formatting for documentation.

Development

# Clone the repository
git clone https://github.com/pboerr/viterbo.git
cd viterbo

# Install development dependencies
poetry install

# Running tests
poetry run pytest

# Building the package
poetry build

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

viterbo-0.2.0.tar.gz (14.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

viterbo-0.2.0-py3-none-any.whl (19.0 kB view details)

Uploaded Python 3

File details

Details for the file viterbo-0.2.0.tar.gz.

File metadata

  • Download URL: viterbo-0.2.0.tar.gz
  • Upload date:
  • Size: 14.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.3 Linux/6.11.0-24-generic

File hashes

Hashes for viterbo-0.2.0.tar.gz
Algorithm Hash digest
SHA256 7b283117dc362d03fc16c1e2e316779a2647520d6a1b431d8f0f2597ac2dd312
MD5 641c0cc9f651584f3d0ca4529f351a2d
BLAKE2b-256 51d5f40acf294dcb57ad6570c950cea7bb5ca7883c951aace72179b54e148aa6

See more details on using hashes here.

File details

Details for the file viterbo-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: viterbo-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 19.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.3 Linux/6.11.0-24-generic

File hashes

Hashes for viterbo-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fa8461a6cb63c828ff8f7a0a2b562b5642e0c9a6e7acfa080b2b9fd6f5534cbb
MD5 12ba2176bff60cb709fc0ea22e6599f6
BLAKE2b-256 b57ddb07d9ea6b9e59f905394e488db3547c7c1e4011c65e673467cd6e1220be

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page