Skip to main content

A CLI utility for aggregating file contents

Project description

Code Promptify

Code-Promptify is a command-line utility for aggregating code repository contents into a single string based on include and exclude patterns. It also provides metadata information, such as token count and billable characters. It is designed to help you prepare prompts for large language models (LLMs). The output is written to a file and also copied to your clipboard automatically.

Note: To count tokens, this tool uses the OpenAI tiktoken tokenizer library and should give you accurate results for most GPT models. For other models (Gemini, Llama, Mistral, etc.) the token count may not be 100% precise but it will be a good approximation. That is because the exact token count depends on the specific tokenizer used by the model, which differs among models.

See example_output.md for what the output looks like for this repo when running with default settings.

Example metadata output:

Field Value
Tokenizer openai/tiktoken
Token Count 4763
Character Count 15695

Files included: └── . ├── README.md ├── build │ └── lib │ └── promptify │ ├── init.py │ └── main.py ├── example_output.md ├── output.md ├── promptify │ └── init.py └── requirements.txt

Features

  • Aggregate file contents based on include and exclude patterns (glob strings)
  • Automatically ignores virtual environment files
  • Automatically ignores files with API_KEY substring present
  • Option to ignore empty files
  • Output results to the clipboard automatically
  • Optionally output results to a file

Installation using PIP

To install promptify, simply run:

pip install code-promptify

Installation from Source

To install Promptify, follow these steps:

  1. Clone the repository:

    git clone https://github.com/vmehmeri/promptify.git
    cd promptify
    
  2. Install the package and its dependencies:

    pip install -e . -r requirements.txt
    

Usage

After installation, you can run Promptify using the following command:

promptify [args]

Arguments

  • --include: File patterns to include (default: ["*.py", "*.html", "*.js", "*.css", "*.json", "*.yaml", "*.txt", "*.md"])
  • --exclude: File patterns to exclude (default: ["*.pyc", "*egg-info*", "*tmp*"])
  • --output: File to write the output to (Optional. Output will be automatically written to a file called output.promptify if clipboard copy fails)
  • --ignore-empty: Flag to Ignore empty files (default: False)

Examples

  1. Use default settings:

    promptify
    
  2. Include only Python and JavaScript files:

    promptify --include "*.py" "*.js"
    
  3. Exclude test files and ignore empty files:

    promptify --exclude "*test*" --ignore-empty
    
  4. Include all Python files except any inside a specific directory:

    promptify --include "*.py" --exclude "*config/*" 
    

Output

See example_output.md

Dependencies

  • pyperclip
  • tabulate
  • token-count

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

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

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

code_promptify-0.4.0.tar.gz (5.5 kB view details)

Uploaded Source

Built Distribution

code_promptify-0.4.0-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

Details for the file code_promptify-0.4.0.tar.gz.

File metadata

  • Download URL: code_promptify-0.4.0.tar.gz
  • Upload date:
  • Size: 5.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.4

File hashes

Hashes for code_promptify-0.4.0.tar.gz
Algorithm Hash digest
SHA256 8bca2fe941820bac4a95858f898185b3f84b5cda88f015dfa02c5b1441552736
MD5 2a62e33d5d7955b55c342f4aae621886
BLAKE2b-256 6492b6318287447563c5c2c6927bb5106ba10a5b6d3891e4c2750c325dfb62a9

See more details on using hashes here.

File details

Details for the file code_promptify-0.4.0-py3-none-any.whl.

File metadata

File hashes

Hashes for code_promptify-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d89224260b475ee8f629940ddfd8b5acffa43d365bcf33e41dee09ce6221e535
MD5 9cca76b3174d712a5809a7376b549393
BLAKE2b-256 4dc787bbef19b6af2467ff4c763ed8db046f922a7b6590f76eb77d4d557d03ca

See more details on using hashes here.

Supported by

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