Skip to content

Python Package for creating a well-defined prompts integrated with specified code snippet.

License

Notifications You must be signed in to change notification settings

baselhusam/damj

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

background

Damj Logo

Damj

damj is a tool for creating comprehensive prompts for language models by combining project files and applying custom processing options.

PyPI

Introduction

damj is designed to help developers create effective prompts for large language models (LLMs) such as ChatGPT. By combining different project files and applying customizable processing options, damj simplifies the process of generating prompts tailored to specific project contexts.

Features

  • Combine multiple project files into a single prompt.
  • Apply customizable processing options to include/exclude comments, imports, and docstrings for python scripts.
  • Support for processing Jupyter notebooks and including cell outputs.
  • Easy integration and usage within Python projects.

Installation

From PyPI

You can install the latest release from PyPI:

pip install damj

From Source

git clone https://github.com/baselhusam/damj.git
cd damj
pip install .

Usage

Basic Example

import os
from damj import Damj

cwd = os.getcwd()
damj = Damj(cwd)

damj.project_info(
    project_overview="This is a sample project.",
    add_project_structure=True,
)

prompt = damj.create_prompt(
    question="What is the purpose of this project?",
)

print(prompt)

Output:

# Project Overview
This is a sample project.


# Project Structure
|   ├── LICENSE
|   ├── README.md
|   ├── pyproject.toml
|   ├── requirements.txt
├── assets/
|   ├── background.png
|   ├── logo.png
├── damj/
|   ├── __init__.py
|   ├── damj.py
|   ├── utils.py



# Question
What is the purpose of this project?

Another Detailed Exmaple

import os
from damj import Damj

cwd = os.getcwd()

damj = Damj(
    cwd=cwd,
    whitelist_files=["*.py"],
    blacklist_files=[".venv", "__pycache__"],
    snippet_marker="```"
)

damj.project_info(
    project_overview="This is a sample project.",
    add_project_structure=True,
    add_files_content=True,
    py_options={
        "add_imports": True,
        "add_comments": True,
        "add_docstrings": False,
        "ipynb_output": False
    }
)

prompt = damj.create_prompt(
    question="What is the purpose of this project?",
    copy_to_clipboard=True,
    to_markdown=False
)

print(prompt)

Use damj Utils Components

damj also provides several utility functions that can be used independently. These utilities include functions to get the project structure, get file content, and more.

Get Project Structure

The get_project_structure function generates a markdown representation of the directory structure, excluding blacklisted files and directories.

from damj.utils import get_project_structure

# Get the project structure excluding .venv and __pycache__ directories
cwd = os.getcwd()
blacklist = [".venv", "__pycache__"]
project_structure = get_project_structure(cwd, blacklist)
print(project_structure)

Get File Content

The get_file_content function retrieves the content of a file, applying the specified py_options.

from damj.utils import get_file_content

py_options = {
    "add_comments": True,
    "add_imports": True,
    "add_docstrings": False,
    "ipynb_output": False
}

# Get the content of a Python file with the specified options
file_content = get_file_content("example.py", py_options)
print(file_content)

License

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


Contributors

Basel Mather (baselmathar@gmail.com)


Contributing

Contributions are welcome! Please fork the repository and open a pull request with your changes.

About

Python Package for creating a well-defined prompts integrated with specified code snippet.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages