---
id: apache-airflow-providers-openai
version: "1.8.2"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# apache-airflow-providers-openai — Provider package apache-airflow-providers-openai for Apache Airflow

License: permissive · Maintenance: active · Downloads: 389.3K/mo

## What it is and what it does

This is an Apache Airflow provider package that bridges Airflow DAGs and the OpenAI API. It allows you to define workflow tasks that call OpenAI services—such as text generation and embeddings—as native Airflow operators, making it straightforward to incorporate AI-powered steps into data pipelines and orchestration workflows.

The package depends on apache-airflow (>=2.11.0), apache-airflow-providers-common-compat (>=1.12.0), and openai (>=2.37.0). It supports Python 3.10 through 3.14 and is maintained as part of the Apache Airflow project, with active development and recent releases. Installation is low-friction—a simple pip install on top of an existing Airflow environment.

Use it for:

- Build Airflow DAGs that call OpenAI for text summarization or content generation as part of a larger data pipeline.
- Embed OpenAI API calls into scheduled workflows to generate embeddings for documents or data records.
- Orchestrate multi-step AI workflows where OpenAI tasks are one step among many in a complex DAG.
- Integrate OpenAI capabilities into existing Airflow monitoring and data processing infrastructure.
- Create dynamic workflows that combine Airflow's scheduling with OpenAI's language models for batch processing.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates OpenAI APIs into Apache Airflow workflows, enabling text generation, embeddings, and other AI-powered tasks directly within DAGs.

Yes, if you run Apache Airflow and need to call OpenAI APIs from DAGs. The package is actively maintained, has no known vulnerabilities, carries a permissive license, and integrates cleanly with Airflow's operator model. Install friction is low. Not relevant if you don't use Airflow or don't need OpenAI integration.

## Install

pip install apache-airflow-providers-openai
uv add apache-airflow-providers-openai
poetry add apache-airflow-providers-openai

## Installing apache-airflow-providers-openai

Before you install: Low install friction; pure Python wheel. Requires Apache Airflow >=2.11.0, apache-airflow-providers-common-compat >=1.12.0, and openai >=2.37.0. Package is actively maintained with a release 6 days old.

License in practice: Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most production environments.

Quickstart:

pip install apache-airflow-providers-openai

from airflow.providers.openai.operators.openai import OpenAIOperator
from airflow import DAG

with DAG('openai_dag') as dag:
    task = OpenAIOperator(task_id='call_openai')

Requires Apache Airflow >=2.11.0 and Python >=3.10; OpenAI API credentials must be configured in Airflow connections.

Verify before relying:

- Specific operators and hooks available beyond the basic OpenAI integration.
- Whether the package supports all OpenAI API endpoints or a subset.
- Performance characteristics and rate-limiting behavior when used at scale.

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 389.3K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

airflow openai integration, airflow ai tasks, openai provider airflow, airflow text generation, airflow embeddings, airflow llm workflows, openai dag operators, airflow-provider, openai-integration, workflow-orchestration

[View on SkillFed](https://skillfed.io/packages/apache-airflow-providers-openai) · [View on PyPI](https://pypi.org/project/apache-airflow-providers-openai/)