---
id: apache-airflow-providers-qdrant
version: "1.5.6"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

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

License: permissive · Maintenance: active · Downloads: 202.1K/mo

## What it is and what it does

This is an Apache Airflow provider package that bridges Airflow workflows with Qdrant, a vector database. It allows you to build DAGs that interact with Qdrant for vector search, similarity matching, and other vector operations as part of larger data pipelines. The package wraps qdrant_client and integrates it with Airflow's task and hook system, so you can orchestrate vector operations alongside traditional data processing tasks.

The package requires Apache Airflow >=2.11.0, qdrant_client >=1.17.1, and the common-compat provider. It supports Python 3.10 through 3.14 and is actively maintained by the Apache Airflow project. Installation is straightforward via pip, and the package is production-stable (Development Status 5).

Use it for:

- Orchestrate vector embeddings generation and storage in Qdrant as part of a scheduled Airflow pipeline
- Build multi-step DAGs that query Qdrant for similarity search results and feed them into downstream tasks
- Manage vector database operations (indexing, updates, deletions) as scheduled or triggered Airflow tasks
- Integrate Qdrant vector operations with other Airflow providers for end-to-end ML data workflows

## Worth the install?

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

Integrates Qdrant vector database with Apache Airflow, enabling vector search and similarity operations within Airflow workflows and DAGs.

Yes, if you are already running Apache Airflow and need to incorporate Qdrant vector operations into your workflows. The package is production-stable, actively maintained, has no known vulnerabilities, and installs with low friction. Install only if you have Airflow >=2.11.0 and a use case that requires vector search within your DAGs.

## Install

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

## Installing apache-airflow-providers-qdrant

Before you install: Low friction install as a pure-Python wheel. Actively maintained with recent releases; requires Apache Airflow >=2.11.0 and qdrant_client >=1.17.1 as runtime dependencies.

License in practice: Apache-2.0 permissive license allows commercial and private use without restriction, typical for Apache Airflow ecosystem packages.

Quickstart:

pip install apache-airflow-providers-qdrant

from airflow.providers.qdrant.hooks.qdrant import QdrantHook

hook = QdrantHook(conn_id='qdrant_default')
# Use hook to interact with Qdrant in your DAG tasks

Requires Apache Airflow >=2.11.0 and qdrant_client >=1.17.1; Python 3.10 or later.

Verify before relying:

- What specific Qdrant operations (e.g., insert, search, delete) are exposed as Airflow operators or hooks
- Whether the provider includes pre-built task templates or only low-level client integration
- Performance characteristics or limits when handling large vector collections in Airflow workflows

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 202.1K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

airflow qdrant integration, vector database airflow provider, qdrant airflow tasks, airflow vector search, qdrant provider airflow, airflow dags vector operations, airflow-provider, vector-database, workflow-orchestration

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