.. taskgen documentation master file, created by
   sphinx-quickstart on Thu Sep 12 12:52:27 2024.
   You can adapt this file completely to your liking, but it should at least
   contain the root `toctree` directive.

Installation
------------

.. code-block:: shell

   pip install taskgen-ai

Sponsors
--------

Taskgen is a community-driven open-source initiative that thrives on the generous contributions of our sponsors,
enabling us to pursue innovative developments.

A huge thank you to our current sponsors:

.. raw:: html

    <div style="display: flex; justify-content: center; align-items: center; gap: 8px;">
      <div>
        <a href="https://simbian.ai/" title="SimbianAI - Fully Autonomous Security for Intelligent Defense!">
            <img src="https://avatars.githubusercontent.com/u/132088052?s=200&v=4" alt="SimbianAI" style="border-radius: 10px; width: auto; max-height: 150px;" />
        </a>
        <p style="text-align: center;">SimbianAI</p>
      </div>
    </div>
    

We invite organizations and individuals to join our sponsorship program.
By becoming a sponsor, you can play a pivotal role in our project's growth.

Minimal Example
---------------

At a minimum, make sure you have installed ``taskgen-ai``.

First, create a file named ``app.py`` with the following contents:

.. code-block:: python

  # Set up API key and do the necessary imports
  from taskgen import *
  import os

  # this is only if you use OpenAI as your LLM
  os.environ['OPENAI_API_KEY'] = '<YOUR API KEY HERE>'

  def llm(system_prompt: str, user_prompt: str) -> str:
    ''' Here, we use OpenAI for illustration, you can change it to your own LLM '''
    # ensure your LLM imports are all within this function
    from openai import OpenAI
    
    # define your own LLM here
    client = OpenAI()
    response = client.chat.completions.create(
        model='gpt-4o-mini',
        temperature = 0,
        messages=[
            {"role": "system", "content": system_prompt},
            {"role": "user", "content": user_prompt}
        ]
    )
    return response.choices[0].message.content

  # Verify that llm function is working
  llm(system_prompt = 'You are a classifier to classify the sentiment of a sentence', 
  user_prompt = 'It is a beautiful and sunny day')


Then, run the following command:

.. code-block:: shell

    python app.py

Now you can see your output in the terminal.

.. code-block:: shell

    Positive


Taskgen Tutorials
==================

.. toctree::
   :maxdepth: 2

   tutorials/index

Usage Reference
==============

.. toctree::
   :maxdepth: 2

   usage/index

Taskgen Reference
==================

.. toctree::
   :maxdepth: 2

   taskgen/index

Community and Contributing
==========================

.. toctree::
   :maxdepth: 2

   about/index