Skip to content

Jupyter Notebooks

Overview

Jupyter Notebooks are an execution environment for Julia, Python and R code (hence, Ju-Py-te-R) in technical computing domains, but are especially popular with data scientists working on machine learning models. Jupyter blends the ability to present explanatory text and imagery with interactive code blocks. Jupyter notebooks can run on your own computer, or via a hoted service like Google Colab.

Get Started

Overview Prerequisites Links
Astra can be a little tricky to get started with when working inside a Jupyter notebook. This sample notebook shows how to connect to Astra, create a new database, download the secure connect bundle, and load and index data into tables. Finally, just because it's a notebook, we'll train a model and plot the test error from the sample dataset. Open in Colab Or, download the notebook.
Learn about Kaskada from this (non-runnable) notebook that provides an overview of using the Kaskada language to perform feature engineering for a popular Kaggle data set. None Open in Colab Or, download the notebook.
Learn about how to use the new vector similarity search functionality to find content related to a query, and then pass that to an LLM to see understand the RAG pattern works for AI powered chatbots. You will need an Astra account and a new database that supports vector similarity search. Open in Colab Or, download the notebook.
Learn about how to use the new vector similarity search functionality to find images based on natural language descriptions using CLIP. You will need an Astra account and a new database that supports vector similarity search. Open in Colab Or, download the notebook.

If you open the notebook in Colab, and would like to make changes to it, choose "Save a copy in Drive" from the File menu in Colab. Have fun!


Last update: 2023-07-13