Skip to main content

A tool to turn a git repository into context for LLMs.

Project description

SlimContext

SlimContext is a powerful tool designed to extract project structure and generate context for LLM models, offering seamless integration with Git repositories and directories.

Features

  • Git Repository Integration: Extract context directly from Git repositories.
  • Directory Traversal: Supports context generation from a directory of files.
  • File with Imports: Supports context generation from a file with locally imported modules.
  • Customizable Context Levels: Generate either full or slim context based on your needs.
  • Token Counting: Calculate token usage for popular LLM models like gpt-4 and gpt-3.5-turbo.
  • Flexible Output Options: Save context to a file or output it to stdout.

Installation

To install SlimContext, use the following command:

pip install slimcontext

Or install directly from GitLab:

pip install git+https://gitlab.com/notorious-community/slimcontext.git

Usage

SlimContext can be run via the command line:

slimcontext --repo-path /path/to/your/git/repo

Options

  • --repo-path, -p: Path to the Git repository. Defaults to the current directory if not provided.
  • --directory, -d: Path to a directory to gather files from. Takes priority over --repo-path.
  • --file, -f: Path to a file to generate context for. Takes priority over --repo-path and -directory.
  • --context-level, -c: Level of context to generate (full or slim). Default is full.
  • --output, -o: Path to save the output file. Defaults to stdout if not provided.
  • --token-model, -t: Model name for token counting (gpt-4, gpt-3.5-turbo, or none). Default is gpt-4.
  • --verbose, -v: Increase verbosity (use -v for INFO and -vv for DEBUG).

Example

slimcontext -d /path/to/directory -c slim -o output.txt -t gpt-4 -v

This command generates a slim context from the specified directory, counts tokens using gpt-4, and saves the result to output.txt.

Directory Support

SlimContext supports extracting context directly from directories:

  • Use --directory to specify the directory.
  • All files within the directory (and subdirectories) will be processed.

Example:

slimcontext --directory /path/to/files -c full -o context.txt

File Support

SlimContext supports extracting context directly from file and modules imported in that file:

  • Use --file to specify the direcfiletory.
  • All local modules loaded in the file will also be included in the output.

Example:

slimcontext --file /path/to/file.py -c full -o context.txt

Logging

Use the -v or -vv flags to control verbosity:

  • -v: INFO level logs.
  • -vv: DEBUG level logs.

Development

Setting Up the Development Environment

  1. Clone the Repository:

    git clone https://gitlab.com/notorious-community/slimcontext.git
    cd slimcontext
    
  2. Install Dependencies:

    Ensure you have poetry installed. Then run:

    poetry install
    

Running Tests

The package includes a comprehensive test suite using pytest.

poetry run pytest

Linting and Formatting

Ensure code quality and consistency with ruff.

poetry run ruff check .

Running Nox Sessions

Automate development tasks across multiple Python environments using nox.

nox -s tests

Project Structure

slimcontext/
├── slimcontext/
│   ├── main.py
│   ├── managers/  # Houses various managers for languages.
│   ├── parsers/  # Houses the code to parse and extract key context by language.
│   └── utils/  # Various utilities used across code base.
├── tests/ 
├── gitlab-ci.yml
├── CHANGELOG
├── LICENSE
├── noxfile.py
├── pyproject.toml
└── README.md

Contributions

Contributions are welcome! Whether it's reporting bugs, suggesting features, or submitting pull requests, your help is appreciated. Please follow these steps to contribute:

  1. Fork the Repository:

    Click the "Fork" button at the top right of the repository page.

  2. Clone Your Fork:

    git clone https://gitlab.com/your-username/slimcontext.git
    cd slimcontext
    
  3. Create a New Branch:

    git checkout -b feature/your-feature-name
    
  4. Make Your Changes:

    Implement your feature or bug fix.

  5. Commit Your Changes:

    git commit -m "Title of your changes" -m "Describe **Why** you made this change."
    
  6. Push to Your Fork:

    git push origin feature/your-feature-name
    
  7. Create a Merge Request:

    Go to the original repository and create a merge request from your fork.

Please ensure all tests pass and adhere to the project's coding standards before submitting your merge request.

License

This project is licensed under the MIT License. See the LICENSE file for details.


Copyright (c) 2024 Neil Schneider

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

slimcontext-0.6.0.tar.gz (23.2 kB view details)

Uploaded Source

Built Distribution

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

slimcontext-0.6.0-py3-none-any.whl (32.7 kB view details)

Uploaded Python 3

File details

Details for the file slimcontext-0.6.0.tar.gz.

File metadata

  • Download URL: slimcontext-0.6.0.tar.gz
  • Upload date:
  • Size: 23.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: poetry/2.1.1 CPython/3.12.9 Linux/5.15.154+

File hashes

Hashes for slimcontext-0.6.0.tar.gz
Algorithm Hash digest
SHA256 23a4a31272ff580fdcbd57d4530e8418a589c92d555d33e5c553229e3017a195
MD5 1b35728d8d6a045b5f9f8c1d1b779c2d
BLAKE2b-256 464e1d8f23226ae26387637c744608721f5e72c95f71a97d8a217f265fc7103d

See more details on using hashes here.

File details

Details for the file slimcontext-0.6.0-py3-none-any.whl.

File metadata

  • Download URL: slimcontext-0.6.0-py3-none-any.whl
  • Upload date:
  • Size: 32.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: poetry/2.1.1 CPython/3.12.9 Linux/5.15.154+

File hashes

Hashes for slimcontext-0.6.0-py3-none-any.whl
Algorithm Hash digest
SHA256 79430c8ee62db86b4883592e9780c9c5e460df62a728b33013c011826ece2fa2
MD5 70bcf6852a340e3c07474a5700d1213f
BLAKE2b-256 84d7823f803ad1267081b9b55f1931e3c5800ce30c65a826f5652903b0666a25

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