Skip to main content

GitHub top language License: AGPL v3 Downloads PyPI - Version

Penelopa: AI-driven Codebase Modifier

Penelopa is an innovative tool designed to leverage OpenAI's GPT models for intelligent and automated codebase modifications. It comprehends and executes code changes based on natural language task descriptions, bringing a new level of efficiency to code maintenance.

Penelopa

Installation

Install Penelopa easily using pip:

pip install penelopa

Usage

Run Penelopa from the command line with various options:

penelopa --task=<task description> 
         --gpt_key=<OpenAI GPT key>
         --config_path=<path to config> 
         --logging=<True/False> 
         --project=<project name> 
         --path=<project path> 
         --model=<GPT model> 
         --temperature=<float> 
         --top_p=<float> 
         --max_tokens=<int> 
         --gitignore=<True/False> 
         --listing=<path to listing file> 
         --updated_listing=<True/False> 
         --assistant_id=<assistant id>

Arguments

  • --config_path: Path to the YAML configuration file.
  • --logging: Enable verbose logging (True/False).
  • --project: Name of the project for contextual understanding.
  • --path: Path to the project directory.
  • --task: Description of the task for the AI to understand and perform.
  • --gpt_key: API key for OpenAI services.
  • --model: OpenAI GPT model to use.
  • --temperature: Level of creativity for AI responses.
  • --top_p: Diversity of AI responses.
  • --max_tokens: Maximum word count for AI responses.
  • --gitignore: Consider .gitignore rules (True/False).
  • --listing: Path to project file listing for context.
  • --updated_listing: Flag to update the listing file (True/False).
  • --assistant_id: Identifier for the AI assistant instance.

Contributing

Your contributions are welcome! Feel free to create issue requests to enhance Penelopa's functionalities.

License

This project is licensed under the GNU Affero General Public License v3.0.

Metadata

Release files for penelopa 0.0.30

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for penelopa 0.0.30
File Size Uploaded Provenance Actions
penelopa-0.0.30.tar.gz 10.5 kB Without provenance Details for penelopa-0.0.30.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for penelopa 0.0.30
File Interpreter ABI Platform Actions
penelopa-0.0.30-py3-none-any.whl Python 3 none any Details for penelopa-0.0.30-py3-none-any.whl

Total release size: 21.1 kB

Release files / penelopa-0.0.30.tar.gz

Download URL penelopa-0.0.30.tar.gz
Size 10.5 kB
Tags Source
SHA-256 checksum
How to use checksums
c3fd8dda9926ebd27d3df55e292621fb3c169e81ea1f86b9020bc12d07aa6087
BLAKE2b-256 checksum
How to use checksums
f9fdafc8d9ab77c1edc51659f6ba0486391e494700f1d5fa69d1c1c45040096c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.8.3

Release files / penelopa-0.0.30-py3-none-any.whl

Download URL penelopa-0.0.30-py3-none-any.whl
Size 10.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3dc3db71d17b85b2a63c5701f9ee4a1c0e3f9d71299e7dd661f29831a8b47f9e
BLAKE2b-256 checksum
How to use checksums
7116b3671931a2bd42d9502a8e78ad090c17a21c194f1306446eb70e67beff72
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.8.3

Security for penelopa 0.0.30

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page