If you read my previous article on Towards Data Science you’ll know I’m a bit of a Star Trek nerd. There’s only one thing I like more than Star Trek, and that’s building cool new stuff with AI. So I thought I’d combine the two yet again!

In this tutorial we’re going to build our own search engine to search all the lines from Star Trek: The Next Generation. We’ll be using Jina, a neural search framework which uses deep learning to power our NLP search, though we could easily use it for image, audio or video search if we wanted to.

We’ll cover:

  • Basic setup
  • Running a demo of our app (yes, even before we code it)
  • Using cookiecutter to create project and boilerplate code
  • Downloading our Star Trek dataset
  • Loading, indexing, and searching our dataset
  • A deeper look behind the scenes
  • What to do if things go wrong

If you’re new to AI or search, don’t worry. As long as you have some knowledge of Python and the command line you’ll be fine. If it helps, think of yourself as Lieutenant Commander Data Science.

Image for post

Via Giphy

#machine-learning #data-science #programming #artificial-intelligence #technology #deep learning

Build a BERT-based Semantic Search System…For Star Trek
4.40 GEEK