The extraction happens based on a schema of nodes and edges. So, let's say you have 2 docs that have related data on a company, then they both will be connected. We use Entity resolution to combine them.

So you need a pre-defined schema? and then when uploading, you assign which schema to use?

Yes manually assigned for now. Future versions will have detection based on docs

Quit my job few months back and working on an unstructured data to Knowledge Graph building tool - https://graphora.io. The goal is to make Knowledge Graph building and maintenance easier.

This looks really cool. There's something about your menu at the top, though, perhaps it could use debouncing? I feel like I click it just as it's automatically opening, which causes it to close.

Thank you for reporting. I fixed it :)

Jeremy and Rachel are very active on Twitter. I learn a lot from their tweets too! Thanks!!

Thanks Jeremy and Rachel for the excellent materials. I am a beginner with ML and initially tried to start with fast.ai part-1. I struggled initially as I preferred to know some basics. So, I looked for a beginner friendly course and ended up with Udacity's AI programming with Python. It gives a pretty decent overview on the basics. Now, I am very excited to take up the fast.ai part-1 & part-2 courses.

This is very inspirational. Thanks and congrats!

I second this. No doubt the effort is laudable. The funding comes from Swachh Bharat cess though. But I too see quite a lot of PR around this. This scheme was the one among the first to project Modi as a modern day Indian saviour. The very first effort to bring even opponents together.

I don't think there is a fixed pattern in raising a creative child. Every child is different. Instilling creativity is not like a program running under specific conditions.

Too bad! Interviewees are not guinea pigs! High time that interviewers realize this.