AI Task Documentation

AI Task Documentation

Welcome to the AI Task documentation. This site provides comprehensive information about the AI Task framework, a Python package for creating, managing, and executing AI workflows.

Getting Started

If you’re new to AI Task, start with the Installation guide followed by the Quick Start guide.

Working Directory Requirements

All AI Task commands, especially ai-partitur, MUST be executed from the project root directory to ensure proper path resolution. This is the base directory containing your partitur/, instruction/, and other directories.

# CORRECT: Run from project root directory
cd /path/to/project_root
ai-partitur profile_document 30727

# INCORRECT: Will cause path resolution errors
cd /path/to/project_root/partitur
ai-partitur profile_document 30727

Documentation Sections

  • User Guide: A high-level overview of AI Task for users who want to create and execute AI workflows.
  • AI Task in a Nutshell: A concise reference of key concepts and commands.
  • Quick Start: Get up and running with AI Task in minutes.
  • Core Concepts: Learn about the fundamental concepts of AI Task.
  • Architecture: Understand the internal architecture of AI Task.
  • Functions: Discover the built-in functions and how to create custom functions.
  • Partitur Guide: Learn how to create and use partitur files.
  • Quick Reference: A quick reference guide for common tasks.
  • Terminology: A glossary of terms used in AI Task.

Command Reference

The primary way to execute AI Task workflows is through the ai-partitur command-line interface:

# Standard command format (preferred)
ai-partitur <partitur_name> <profile_id>

# Examples
ai-partitur inqua_objektiv 30727
ai-partitur profile_document 34611

# File-specific usage (only when necessary)
ai-partitur --file partitur/specialized_workflow.ai workflow_name profile_id

# Processing multiple profiles
for profile_id in 30727 34611 32101; do
    ai-partitur profile_document $profile_id
done

Project Structure

AI Task expects a standard project structure:

project_root/
├── partitur/          # Contains all partitur files
├── instruction/       # Contains all template files
├── function/          # Contains custom functions
├── profile/           # Contains all profile data
└── diagnostic/        # Contains logs and error tracking

Advanced Topics

Once you’re familiar with the basics, explore these advanced topics:

  • Productions: Learn about organizing your AI workflows.
  • LLM Integration: Details on integrating with large language models.
  • API Reference: Complete API documentation for developers.
  • Development: Information for developers who want to contribute to AI Task.
  • Examples: Examples of AI Task in action.

Troubleshooting

If you encounter issues with AI Task:

  1. Working Directory: Verify you’re running from the project root directory
  2. Path Resolution: Ensure all paths in partitur files are relative to the project root
  3. Function Directory: For function-based partitur files, verify the function_dir setting
  4. File Existence: Check that all referenced files exist
  5. Fallback Method: Try the direct Python approach for more control

For more detailed troubleshooting, refer to the Troubleshooting section.