I'm a data science enthusiast eager to keep myself updated on all new technologies. Featurethon is a 14-day learning challenge to develop a JINA AI-based application conducted by Featurepreneur. I'll be updating my progress on this blog.

DAY 0 - 24/10/21

Orientation was conducted through zoom meetings organized by the Featurepreneur team. Here I was challenged to develop a Jina AI-based application.

Time spent = 1 Hour

DAY 1 - 25/10/21

Learning - Differences between Symbolic search and Neural search

A symbolic search tells a machine a set of rules to understand what data is what, Whereas a neural search does the same thing with a pre-trained neural network. This means that there is no need to write every little rule, saving time and headaches for the developers, and the system trains itself to get better as it goes along.JINA is an easier way to build scalable and sustainable neural search systems on the cloud.

Advantages of Jina: 1)Easy to implement 2)offers anything-to-anything search.

Time spent = 2.5 Hours

DAY 2 - 26/10/21

Learning - What's a cross-modal search and a Multi-model search .

cross-modal search is like searching for matching titles for given paragraph text. a PDF file has images and text together most of the time, In this case, we have a file with multi-modality: text and images.

I also installed Jina, which was pretty easy.

Time spent = 2 Hours

DAY 3 - 27/10/21

Learning - Successfully ran hello world programs from Jina AI docs

The three fundamental concepts in Jina are Document, Executor, and Flow.

*The document is the basic data type in Jina;

*An executor is how Jina processes Documents;

*Flow is how Jina streamlines and scales Executors.

Started to collect data for our own dataset using Selenium and Beatifulsoup.