[Day 148] Microsoft Azure hackathon Day 2

 Hello :)
Today is Day 148!


A quick summary of today:
  • attended day 2 of the Microsoft Azure hackathon in the Microsoft office in Seoul


Today ~ we tried. The 3rd challenge from yesterday - deploying an AI-powered chat app... well we could not do it today either. Turns out all the teams were facing the same issue and I was trying to fix errors on that 3rd task. The main issue was at the last step - deployment and people were getting some kind of os error. At some point I got that too, and after trying to fix it I started getting another error in regards to access (felt like I went a step back maybe haha). In the end ~~~ It was not possible, and the 4th challenge which was about testing the app from the 3rd challenge was not possible to complete either. 

Then I moved to the 5th one. Part of it was setting up an indexer that reads documents, then setting up a model that recognizes and read different parts of invoices (pics below)

Actually I realise now as I am writing that I did not take much pics while working today because we were just trying to get something finished while fixed tons of errors coming our way. Also from our team (3, including myself) noone had any Azure experience so we were diving into the deep by ourselves. After the model was trained and tested. We had to set up a 'pipeline with BPA'. BPA stands for business process automation but there was no such service on Azure and we just kept trying to see how to do a normal pipeline with data, the model and deployment. At this point the 5th and 6th challenges came together because they both involved deploying a model + pipeline but time was pushing so we were just looking at how to deploy a 'BPA pipeline' on Azure. I found some online tutorial about using Azure's Document intelligence and I was following it but I kept getting errors again haha. Another part of the challenge was to deploy an OpenAI service resource and contrary to the rest of the day - this actually worked without any problems haha. 

At the end of the 2 days ~ I learned a lot about Azure and its ecosystem - storage, models, AI service, access - and some issues someone might face when using it. 

As a goodbye, we were given some gifts too (pen, cup, tshirt of the hackathon)


Thank you to Microsoft Korea for inviting me :)


That is all for today!

See you tomorrow :) 

Popular posts from this blog

[Day 198] Transactions Data Streaming Pipeline Porject [v1 completed]

Image
 Hello :) Today is Day 198! A quick summary of today: data streaming pipeline project [v1 done] Here is a link to the project's repo. Well ... I did not know I can do it in a day (~14 hours) after yesterday's issues but here we are. Turns out in order to insert the full (~70 variables with nested/list structure), I need the proper pyspark schema. And yesterday I did not have that and that is why when I was reading data in the kafka producer I was getting NULL in the columns - my schema was wrong. Well today I not only fixed the schema for the 4 variables I had yesterday, but included *all* the variables that come from the Stripe API ~ 70 (for completeness).  When I run docker-compose, the data streams and is input into the postgres db (and is still running). Unfortunately, the free Stripe API for creating realistic transactions has a limit of 25, so every 3 seconds, 25 new transactions are sent to the db. It has been running half the day (since I got that set up) and as I am wr
Read more

[Day 107] Transforming natural language to charts

Image
 Hello :) Today is Day 107! A quick summary of today: created text2chart - transforming natural language to charts [ github ] [ webapp ] I am super sick, but in the around 3 hours of my fever not being high, I managed to study a bit. I was again thinking about creating some nlp project but was stuck on the idea of how to host a model. After looking around I found this article where they create a similar app called chat2vis  and they use codellama. I know codellama is an open source model that I can get from huggingface and I wondered, how did they host it. Turns out - they ask the user to input a huggingface api key, which then allows for querying and generating content. (AWESOME! this is applicable to some of the other PDF chat apps that I have, but I will look to make an app of them later).  My fever eased a bit, and I sat on my chair to do some work ^^ Here is a breakdown of the app. I used streamlit. Also, 2 default datasets during dev: Financial Statements of Major Companies(2009-
Read more

[Day 54] I became a backprop ninja! (woohoo)

Image
 Hello :) Today is Day 54! A quick summary of today: Read through cs231n's neural network lectures [1] [2] [3] Spent 8 hours going over Andrej Karpathy's backprop ninja tutorial After yesterday's confidence boost in doing backprop, I came in today with the intention of becoming of, as Andrej Karpathy calls it, a backprop ninja.  The cs231n NN lectures were the usual about how NN became to be, param initialization, activation functions, loss functions, regularization and optimizers. Nothing out of the ordinary, but still was good to reassure myself of that knowledge. But that was definitely not the main even of today. As I mentioned, I wanted to become (or at least attempt to become) a backprop ninja today. I have watched that particular tutorial twice, the 1st time I had no idea what is going on, the 2nd time I could follow, and now it was the 3rd time - and now, I wanted to participate and actually see the why and the how of the things we have to do, when we do manual back
Read more