Howto

AI-powered PDF search in your browser with Python

Build a PDF search engine in a Colab notebook with Jina AI

Have you ever been searching through a stack of files and just can’t find the right keywords to get what you’re looking for? Staring at a screen and wracking your brain at 3am for the right word ain’t fun, take it from me.

How about trying to search through a stack of PDFs? That gets even harder since all that nice plain text is wrapped up in a gnarly format. Good luck grepping those!

In the past few months we’ve posted a few times about how to build a PDF search engine using Python. Now we want to make it even easier by letting you do it all in your browser.

In this notebook you’ll learn how to use DocArray, Jina and Jina Hub to search through textual PDFs of Wikipedia articles. You don’t have to write any code yourself, but feel free to go wild and modify what’s already there!