Build a movie recommendation app with Tensorflow and pgvector

What's in the Workshop Recipe?

We'll work together to build a movie recommendation system from start to finish, utilizing NodeJS, TensorFlow, and PostgreSQL’s extension pgvector. We'll guide you through the process of creating the vector embeddings using TensorFlow right on your laptop. Additionally, we'll leverage pg-promise to efficiently handle bulk row inserts, and we'll explore the usage of Next.js for a full-stack project. By the end of the workshop, you'll have a fully functional project that generates movie recommendations.

This workshop is particularly useful for those who are intrigued by contextual search and usage of AI, but might find themselves overwhelmed by the complexities of getting started.

Related resource in our developer center: TensorFlow, PostgreSQL®, pgvector & Next.js: building a movie recommender

Prepare for a Brain Upgrade

You will learn:

• How to turn a movie plot into an embedding using TensorFlow
• How to setup pgvector in PostgreSQL
• How to import movie data into PostgreSQL, with embeddings for the plot descriptions
• How to search for closest matching plots to a query
• How to create a web app with Next.js
• And finally, how to make it look nice as well!
  

Prerequisities

• Web browser
• A GitHub account. Here’s the GitHub repository we’ll be using

You’ll also need

• An Aiven account, using our free trial

We will lead you through setting that up in the workshop, if you don’t already have one.