Skip to main content

Agentic Data Generation Toolkit is designed to provide an easy to use interface for both a human user as well as an Agent. The primary purpose of this Toolkit is to provide a framework for experimentation with Agents that generate data. The framework provides all the automation needed to excute a scenario while providing the user with both consistent measurements across scenarios as well as tracking and reporting of results.

Highlights

  • A “lab journal” which can be invoked through an experiment.

  • Reports saved to disk of both preview and results of an experiment.

  • extensible architecture. The framework is designed to be extensible on load and during execution.

Installation

To install adgtk please use the following command:

Via PyPi

To install the package, you can use pip:

pip install adgtk

Manual installation from source

If you wish to clone the repository and install the package manually, you can do so by following these steps:

  1. active your virtual environment.

  2. Download the project from https://github.com/fred78108/adgtk.

  3. from the root folder of adgtk, run the following command:

(.venv) $ python -m pip install -e .

This will let you modify your copy of adgtk and evaluate the results. This is useful for development of your own version of adgtk.

Usage

Command structure

ADGTK is designed to be run from the command line. The primary command is adgtk-mgr. This command is used to manage the toolkit. The command has a number of subcommands that are used to manage the toolkit.

adgtk-mgr [options]

Commands:
   project      : Project management (create, destroy)
   experiment   : Experiment operations (create, run, list, preview)
   factory      : List Factory or if include a group the group listing

options:
-h, --help            show a help message and exits
-f FILE, --file FILE  override the settings file with this file
--version             show program's version number and exit
--yaml                Use YAML format when creating the project settings file

Project
-------
   $ adgtk-mgr project create example1   Creates a new project called example1
   $ adgtk-mgr project destroy example1  deletes the example1 project

Experiment
----------
   $ adgtk-mgr experiment list           lists all available experiments
   $ adgtk-mgr experiment create         Starts a wizard to build an experiment
   $ adgtk-mgr experiment create exp1     Starts a wizard to build an experiment with the name exp1
   $ adgtk-mgr experiment run            via a menu select and run an experiment
   $ adgtk-mgr experiment run exp1       Run exp1

Factory
-------
   $ adgtk-mgr factory                   Lists available factory blueprints
   $ adgtk-mgr factory agent             Lists agent factory blueprints

Metadata

Release files for adgtk 0.2.0

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

Source distribution (sdist)

Source distribution for adgtk 0.2.0
File Size Uploaded Provenance
adgtk-0.2.0.tar.gz 100.7 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for adgtk 0.2.0
File Interpreter ABI Platform
adgtk-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 229.0 kB

Release files / adgtk-0.2.0.tar.gz

Download URL adgtk-0.2.0.tar.gz
Size 100.7 kB
Tags Source
SHA-256 checksum
How to use checksums
cc6cb31eeb421050c5653be2520d02048c8761cdaee69064e6597d05fb3d7cfb
BLAKE2b-256 checksum
How to use checksums
659dca42fc6f948c0538f702e7c3964e9e622c540b7ea2076fa776e9e8e33e11
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.12

Release files / adgtk-0.2.0-py3-none-any.whl

Download URL adgtk-0.2.0-py3-none-any.whl
Size 128.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4b5c85688b7b11c0185c2482e8d8163bae31b5a93ba7692e78bc87b714c7c459
BLAKE2b-256 checksum
How to use checksums
b8f0e3d34f2a218b5022eedfefc16ee4dd4b931ebe042dcfa3d21ba3f27a83c5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.12

Security for adgtk 0.2.0

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