Skip to content

Pixeltable notebooks and cookbooks

Updated

103 notebooks and recipes from the Pixeltable docs, grouped the way the docs group them: open a notebook in Google Colab and run it.

Start here

  • 10-Minute Tour

    Welcome to Pixeltable! In this tutorial, we'll survey how to create tables, populate them with data, and enhance them with built-in and user-defined transformations and AI operations.

    TutorialsOpen in Colab
  • Agentic Patterns

    Build the six architectural patterns of agentic AI (prompt chaining, routing, parallelization, tool use, evaluator-optimizer, orchestrator-worker) and the ReAct and planning strategies as Pixeltable tables and computed columns.

  • Object Detection in Videos

    Detect objects in a video frame by frame: Pixeltable extracts the frames, runs YOLOX models on them and reassembles the frames into a video. Compare detection models and evaluate them against ground truth.

103 of 103 notebooks shown

Tutorials 7

  • 10-Minute Tour

    Welcome to Pixeltable! In this tutorial, we'll survey how to create tables, populate them with data, and enhance them with built-in and user-defined transformations and AI operations.

    Updated Open in Colab
  • Computed Columns

    This guide introduces one of Pixeltable's most essential and powerful concepts: computed columns.

    Updated Open in Colab
  • UDFs in Pixeltable

    Pixeltable comes with a library of built-in functions and integrations, but sooner or later, you'll want to introduce some customized logic into your workflow.

    Updated Open in Colab
  • Embedding Indices

    Create an embedding index, query it with similarity search and keep it current as data changes. Covers several indexes on one column, custom embedding UDFs and precomputed embeddings.

    Updated Open in Colab
  • External Files

    In Pixeltable, all media data (videos, images, audio) resides in external files, and Pixeltable stores references to those.

    Updated Open in Colab

Core Operations 12

Cookbooks

Agents 9

Cookbooks

Text 6

Cookbooks

Images 15

Cookbooks

Audio 7

Cookbooks

Video 7

Cookbooks

Search & Embeddings 3

Cookbooks

Data Import/Export 11

Cookbooks

Providers 26

Integrations

Questions about the notebooks

Do I need an API key to run a notebook?

Only when the notebook calls a hosted model provider: it asks for the key in a cell before the first call. A notebook that runs its model on your own machine, such as the Whisper transcription cookbook, needs none.

How do these notebooks relate to building an app?

A notebook creates tables with pxt.create_table() so its cells run without a project. An app puts the same columns on a TableModel in app.py and creates the tables with pxt schema update. The example apps show that form.

Where do these notebooks come from?

They are the tutorials, cookbooks and provider guides on docs.pixeltable.com, taken from the release tag of the pixeltable repository. Each page shows when its file last changed and links the notebook on GitHub.

Can I run a notebook on my own machine?

Yes. Each page links the notebook file on GitHub, so you can open it in your own Jupyter environment instead of Colab.

Start building with Pixeltable

Install Pixeltable, then take any of these as a starting point.