Airflow-Ai-Sdk

Visit Tool

airflow-ai-sdk is an AI Agents & Automation tool that allows users to call LLMs and orchestrate AI agent calls directly within Apache Airflow pipelines. It simplifies LLM workflows using decorator-based tasks.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is airflow-ai-sdk?

airflow-ai-sdk is a Python SDK designed to seamlessly integrate Large Language Models (LLMs) and AI Agents into Apache Airflow workflows. It empowers users to define tasks that call LLMs, orchestrate multi-step AI reasoning with custom tools, and automatically parse and validate LLM outputs using type hints. The SDK supports all models available in the Pydantic AI library, including OpenAI, Anthropic, and Gemini. Key features include `@task.llm` for general LLM calls, `@task.agent` for orchestrating AI agents, `@task.llm_branch` for dynamic DAG control flow based on LLM output, and `@task.embed` for creating vector embeddings. This SDK is ideal for developers looking to leverage mature orchestration tooling like Airflow for robust, production-ready LLM and agent-based pipelines.

Best used for

Ideal for developers who need to integrate large language models into existing data pipelines, orchestrate complex AI agent workflows, and automate output parsing. Especially valuable for building robust, production-grade LLM applications within a familiar orchestration framework like Apache Airflow.

Common actions

orchestrate LLM workflows

integrate AI agents

automate AI tasks

manage LLM outputs

control DAG flow

collaborationopen-sourceworkflowsdeepfakelow-code/no-codeautomated workflowface swappinggithub copilot"AI Agents"

Capabilities

Key features

LLM tasks with decorators
Agent tasks orchestration
Automatic output parsing
Branching based on LLM
Pydantic AI model support
Embedding tasks

Target Audience

developer

Integrations

apache-airflowopenaianthropicgoogle-gemini

Pricing & Plans

Open Source

Free

FAQs

What are the core functionalities of airflow-ai-sdk?

The SDK allows users to define tasks for calling LLMs, orchestrate multi-step AI agents, and automatically parse LLM outputs. It also supports dynamic branching in DAGs based on LLM results and creating vector embeddings, all within Apache Airflow.

Which LLM models are supported by airflow-ai-sdk?

airflow-ai-sdk supports all models available through the Pydantic AI library. This includes popular models from providers such as OpenAI, Anthropic, and Google Gemini, offering flexibility in model choice for your workflows.

How does airflow-ai-sdk simplify LLM integration into Airflow?

It simplifies integration by using decorator-based tasks like `@task.llm` and `@task.agent`, which allow users to define LLM and agent calls directly within their Airflow DAGs. This approach streamlines the creation and orchestration of AI workflows.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI General-Purpose Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Also listed in

This tool also appears in

Coding & Development › Code Assistants Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce