Skip to main content
Version: 3.3-unstable

Installation

See how to quickly install Haystack with pip, uv, or conda.

Package Installation​

Use pip to install the Haystack PyPI package:

shell
pip install haystack-ai

Alternatively, you can use uv to install Haystack:

shell
uv pip install haystack-ai

Or add it as a dependency to your project:

shell
uv add haystack-ai

You can also use conda to install the Haystack conda package:

shell
conda install conda-forge::haystack-ai

Optional Dependencies​

Some components in Haystack rely on additional optional dependencies. To keep the installation lightweight, these are not included by default – only the essentials are installed. If you use a feature that requires an optional dependency that hasn't been installed, Haystack will raise an error that instructs you to install missing dependencies, for example:

shell
ImportError: "Haystack failed to import the optional dependency 'pypdf'. Run 'pip install pypdf'.
Ready to scale with confidence?

Rather than self-hosting, Haystack Enterprise Platform runs your pipelines for you: build them visually in the Pipeline Builder, publish pipeline YAML through the REST API, or bring your own custom Python components. You get zero-downtime deploys, managed scaling, and built-in tracing out of the box. See the Quick Start Guide to get a pipeline running in minutes.

Contributing to Haystack​

If you would like to contribute to the Haystack, check our Contributor Guidelines first and follow the instructions here to set up your development environment.