Skip to main content
1

Check or install Python

Make sure you have Python 3.11 or higher installed. Check your version or install Python.
2

(Optional) Use or set up a Python virtual environment

A virtual environment is a per-project Python sandbox. It isolates a project’s Python interpreter and packages from your other projects and system-wide Python setup. Unstructured recommends a virtual environment, but it is not required.Popular options include uv (recommended), poetry, venv, and conda.
3

Install or upgrade the Python SDK

If you are using a virtual environment, replace pip install and pip show as follows with your provider’s related command.
To install, run this command:
If you already have it, upgrade it with this command:
To check if you already have it, run this command:
4

Get your Unstructured API URL and API key

Follow one of these procedures, depending on your Unstructured product. If you are not sure, start with Transform. It is the quickest way for individuals to get started.If your organization has purchased Unstructured Business, follow one of the Business procedures instead. If you are not sure which one to use, ask your Unstructured account administrator, or contact Unstructured Sales.
  1. Go to https://transform.unstructured.io and sign in. If you are new, click Register.
  2. Click API Keys.
  3. Copy API URL and paste this value into a secure location. Do the same with API Key.
The Python SDK code examples throughout the documentation use the following environment variables:
  • UNSTRUCTURED_API_URL, representing your API URL.
  • UNSTRUCTURED_API_KEY, representing your API key.
To set these variables, see your system’s documentation.

Next steps

Unstructured Transform quickstart

Use Unstructured Transform with Python to turn local input files into structured data.

Unstructured Pipelines operations local files quickstart

(Unstructured Business users only) Use Unstructured Pipelines with Python to turn local input files into structured data.

Unstructured Pipelines operations remote files quickstart

(Unstructured Business users only) Use Unstructured Pipelines with Python to turn input files stored remotely in Dropbox into structured data, delivering the results to a remote Pinecone serverless index.

API reference

Get the full API reference, along with code snippets for Python.

Cookbooks and samples

Get complete notebooks and end-to-end code applications for Python.