Skip to main content

TaskFlowAI is a lightweight python framework for building LLM based pipelines and multi-agent teams

Project description

TaskFlowAI: Flexible Framework for LLM-Driven Pipelines and Multi-Agent Teams

TaskFlowAI is a lightweight and flexible framework designed for creating AI-driven task pipelines and workflows. It provides developers with a streamlined approach to building agentic systems without unnecessary abstractions or cognitive overhead.

Key Features

TaskFlowAI offers a modular architecture that is easy to extend and integrate into existing projects. It provides flexible workflow design capabilities, ranging from deterministic pipelines to fully autonomous agent teams. The framework supports advanced tool assignment and usage, allowing for dynamic tool assignment and self-determined tool use by agents.

One of the standout features of TaskFlowAI is its diverse language model support, including integration with OpenAI, Anthropic, OpenRouter, and local models. It also comes with a comprehensive toolset that includes web interaction, file operations, embeddings generation, and more. Transparency and observability are prioritized through detailed logging and state exposure.

TaskFlowAI is designed with minimal dependencies, featuring a lightweight core with optional integrations. It also incorporates best practices such as structured prompt engineering and robust error handling.

Core Components

The framework is built around several core components. Tasks serve as discrete units of work, while Agents act as personas that perform tasks and can be assigned tools. Tools are wrappers around external services or specific functionalities. Language Model Interfaces provide a consistent interface for various LLM providers, ensuring seamless integration across different AI models.

Getting Started

  1. Install TaskFlowAI: pip install taskflowai
  2. Import necessary components:
    from taskflowai import Task, Agent, OllamaModels
    
  3. Create your workflows by defining tasks, agents, and tools

Examples

TaskFlowAI supports various use cases, from a simple agent system to complex multi-agent teams. Check out the documentation for detailed examples and usage patterns at taskflowai.org.

TaskFlowAI empowers developers to build sophisticated AI applications that can handle a wide range of tasks efficiently and effectively. Whether you're creating a simple chatbot or a complex multi-agent system, TaskFlowAI provides the building blocks and extensibility to bring your ideas to life.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

taskflowai-0.1.6.tar.gz (36.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

taskflowai-0.1.6-py3-none-any.whl (35.2 kB view details)

Uploaded Python 3

File details

Details for the file taskflowai-0.1.6.tar.gz.

File metadata

  • Download URL: taskflowai-0.1.6.tar.gz
  • Upload date:
  • Size: 36.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.2

File hashes

Hashes for taskflowai-0.1.6.tar.gz
Algorithm Hash digest
SHA256 c199338781d0142efcf117793851cb27e6dd00ffcd8e17d73cceeedb61de5976
MD5 453fd9e643d4814b1ee6b5c208732728
BLAKE2b-256 383cc4f3ecd9546643c43efbd50d2985ad91dd50d4a8718e5f101c5e1ea07c05

See more details on using hashes here.

File details

Details for the file taskflowai-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: taskflowai-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 35.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.2

File hashes

Hashes for taskflowai-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 05f34d42e53e3c7da4b3c7a3a9bf3dad7357653f40853b1558e95279fe7f8872
MD5 c7774c6e70d6bc21b40a3435f76752b4
BLAKE2b-256 b40bfbfff0d5ca4951f0806a6f2a9134ededc796f46d4a6d335ff658603b5a6e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page