Skip to main content

A simple context builder and converter toolkit

Project description

ContextMaker

License Python

Feature to enrich the CMBAgents: Multi-Agent System for Science, Made by Cosmologists, Powered by AG2.

Acknowledgments

This project uses the CAMB code developed by Antony Lewis and collaborators. Please see the CAMB website and documentation for more information.


Installation

Install ContextMaker from PyPI:

python3 -m venv context_env
source context_env/bin/activate
pip install contextmaker

Usage

From the Command Line

ContextMaker automatically finds libraries on your system and generates complete documentation with function signatures and docstrings.

# Convert a library's documentation (automatic search)
contextmaker library_name

# Example: convert pixell documentation
contextmaker pixell

# Example: convert numpy documentation
contextmaker numpy

Advanced Usage

# Specify custom output path
contextmaker pixell --output ~/Documents/my_docs

# Specify manual input path (overrides automatic search)
contextmaker pixell --input_path /path/to/library/source

Output

  • Default location: ~/your_context_library/library_name.txt
  • Content: Complete documentation with function signatures, docstrings, examples, and API references
  • Format: Clean text optimized for AI agent ingestion

From a Python Script

You can also use ContextMaker programmatically in your Python scripts:

import contextmaker

# Minimal usage (automatic search, default output path)
contextmaker.convert("pixell")

# With custom output path
contextmaker.convert("pixell", output_path="/tmp")

# With manual input path
contextmaker.convert("pixell", input_path="/path/to/pixell/source")

This will generate a text file with the complete documentation, just like the CLI.


Supported Inputs

  • Sphinx documentation (conf.py + .rst) - Complete documentation with signatures
  • Markdown README files (README.md)
  • Jupyter notebooks (.ipynb)
  • Python source files with docstrings (auto-generated docs if no user docs)

Library Requirements

For complete documentation extraction, the library should have:

  • A docs/ or doc/ directory containing conf.py and index.rst
  • Source code accessible for docstring extraction

If only the installed package is found (without Sphinx docs), ContextMaker will extract available docstrings from the source code.


Troubleshooting

Library not found

# Use manual path
contextmaker pixell --input_path /path/to/pixell/repo

No documentation detected

  • Ensure the library has a docs/ or doc/ directory with conf.py and index.rst
  • Clone the official repository if using an installed package

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

contextmaker-1.3.0.tar.gz (19.2 kB view details)

Uploaded Source

Built Distribution

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

contextmaker-1.3.0-py3-none-any.whl (20.9 kB view details)

Uploaded Python 3

File details

Details for the file contextmaker-1.3.0.tar.gz.

File metadata

  • Download URL: contextmaker-1.3.0.tar.gz
  • Upload date:
  • Size: 19.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.4

File hashes

Hashes for contextmaker-1.3.0.tar.gz
Algorithm Hash digest
SHA256 95516c2affd26b40b46db0f2773266e960416ae2e43476726099739da70cc40f
MD5 a112993ff8a1d4c0ca9157d6efce2af0
BLAKE2b-256 f557995161c5aeeaf88a13a14301a3a5e6e82b0cbc66f3ce867770744d45833e

See more details on using hashes here.

File details

Details for the file contextmaker-1.3.0-py3-none-any.whl.

File metadata

  • Download URL: contextmaker-1.3.0-py3-none-any.whl
  • Upload date:
  • Size: 20.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.4

File hashes

Hashes for contextmaker-1.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6199f06e30d733aae1da6a362052bd3470260a3defd0ed61dcbd67cb0afc479a
MD5 76d7c92b31abdab8a8e41e0e7dd4116b
BLAKE2b-256 3a4f7a1aeae01d61d31e8ec45a19fd8ddced2de37ad588dccdfd87dad80d1ecf

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