maxbaluev/dspygen

A Ruby on Rails style framework for the DSPy (Demonstrate, Search, Predict) project for Language Models like GPT, BERT, and LLama.

DSPyGen: Streamlining AI Development

DSPyGen, influenced by the efficiency and modularity of Ruby on Rails, is a powerful command-line interface (CLI) designed to revolutionize AI development by leveraging DSPy modules. This tool simplifies the process of creating, developing, and deploying language model (LM) pipelines, embodying the Ruby on Rails philosophy of "Convention over Configuration" for AI projects.

Custom GPT

DSPyGen 2024.2.26

Features

• Quick Initialization: Set up your DSPyGen project in seconds, echoing Ruby on Rails' ease of starting new projects.
• Modular Approach: Inspired by Ruby on Rails' modular design, DSPyGen allows for the easy generation and enhancement of DSPy modules.
• Intuitive Command Structure: With user-friendly commands, managing your AI development workflow becomes as straightforward as web development with Ruby on Rails.
• Embedded Chatbot Assistance: For guidance and support, DSPyGen includes a chatbot, making it easier to navigate through your development process.

Getting Started

Ensure Python is installed on your system. Install DSPyGen via pip:

pip install dspygen

Enhance your experience with shell completion by using the --install-completion option.

Using

Python package: to add and install this package as a dependency of your project, run poetry add dspygen.

Python CLI: to view this app's CLI commands once it's installed, run dspygen --help.

Python application: to serve this REST API, run docker compose up app and open localhost:8888 in your browser. Within the Dev Container, this is equivalent to running poe api.

Usage Overview

dspygen [OPTIONS] COMMAND [ARGS]...

Global Options

• --install-completion: Adds shell completion.
• --show-completion: Displays the shell completion script.
• --help: Brings up the help message.

Core Commands

• command: Adds or creates new subcommands in a Ruby on Rails-inspired CLI structure.
• help: Accesses a supportive chatbot for quick assistance.
• init: Initializes a DSPyGen project, setting up a structured environment similar to Ruby on Rails.
• module: Manages DSPy modules, enabling easy modifications or the creation of new ones.

Command Details

Managing Commands

• Add a Command: Extend functionality seamlessly, reminiscent of Ruby on Rails plugins.

  dspygen command add [existing_command] [new_command]

• New Command Module: Start new functionalities with ease.

  dspygen command new [new_command_name]

Modules Management

• New Module Generation: Create new DSPy modules to extend your project's capabilities.

  dspygen module new 'text -> summary'

Project Structure

Following a clear and organized structure influenced by Ruby on Rails, DSPyGen projects are easy to navigate:

.
├── src
│   ├── dspygen
│   │   ├── modules
│   │   └── subcommands
│   └── typetemp
└── tests

Help and Documentation

For detailed command information or assistance, use:

dspygen [command] --help

Contributing

We welcome contributions to DSPyGen, whether it's new features, improvements, or bug fixes. Feel free to fork the repository, make changes, and submit a pull request.

License

DSPyGen is open-source, licensed under the MIT License.

Adopting DSPyGen for your AI projects not only simplifies the development process but also incorporates the structured, efficient approach pioneered by Ruby on Rails into the realm of AI and machine learning.

Contributing

Prerequisites

1. Set up Git to use SSH

1. Generate an SSH key and add the SSH key to your GitHub account.
2. Configure SSH to automatically load your SSH keys:

   cat << EOF >> ~/.ssh/config
   Host *
     AddKeysToAgent yes
     IgnoreUnknown UseKeychain
     UseKeychain yes
   EOF

2. Install Docker

1. Install Docker Desktop.
   • Enable Use Docker Compose V2 in Docker Desktop's preferences window.
   • Linux only:
     • Export your user's user id and group id so that files created in the Dev Container are owned by your user:

       cat << EOF >> ~/.bashrc
       export UID=$(id --user)
       export GID=$(id --group)
       EOF

3. Install VS Code or PyCharm

1. Install VS Code and VS Code's Dev Containers extension. Alternatively, install PyCharm.
2. Optional: install a Nerd Font such as FiraCode Nerd Font and configure VS Code or configure PyCharm to use it.

Development environments

The following development environments are supported:

1. ⭐️ GitHub Codespaces: click on Code and select Create codespace to start a Dev Container with GitHub Codespaces.
2. ⭐️ Dev Container (with container volume): click on Open in Dev Containers to clone this repository in a container volume and create a Dev Container with VS Code.
3. Dev Container: clone this repository, open it with VS Code, and run Ctrl/⌘ + ⇧ + P → Dev Containers: Reopen in Container.
4. PyCharm: clone this repository, open it with PyCharm, and configure Docker Compose as a remote interpreter with the dev service.
5. Terminal: clone this repository, open it with your terminal, and run docker compose up --detach dev to start a Dev Container in the background, and then run docker compose exec dev zsh to open a shell prompt in the Dev Container.

Developing

• Run poe from within the development environment to print a list of Poe the Poet tasks available to run on this project.
• Run poetry add {package} from within the development environment to install a run time dependency and add it to pyproject.toml and poetry.lock. Add --group test or --group dev to install a CI or development dependency, respectively.
• Run poetry update from within the development environment to upgrade all dependencies to the latest versions allowed by pyproject.toml.