Skip to main content



This collection of notebooks demonstrates some of the interesting things you can do with the Wellcome Collection API, and how to make the most of it. The notebooks are written in Python, and use the Jupyter notebook format.

This kind of documentation is intended for people who might benefit from practical examples, rather than exhaustive technical specs (check out the API reference if you're looking for that kind of thing). For example, you might be familiar with Python (or a similar scripting language), but haven't used an open data API before. Or you might be familiar with the cultural heritage sector but haven't used this sort of data in a programming context before.

The examples here aren't exhaustive, and should just serve as inspiration for your own explorations. Each notebook introduces a concept or technique, and then provides a set of exercises to push you further. The hope is that you'll eventually abandon these notebooks and start writing your own code!

If you have an idea for a notebook that you think might be useful or interesting to others, please open an issue or submit a pull request!

Table of contents

  1. Exploring wellcome collections apis
  2. Extracting more data for local analysis
  3. Connecting the apis together
  4. Building graphs of visually similar images
  5. Working with snapshots of the api
  6. Visualising the collection on a map
  7. Building an image classifier
  8. Extracting features from text
  9. Building a recommender system for subjects