Item-Item based collaborative filtering using a BERT based Recommendation model — Encoder-based Self-Attention transformers are very good at predicting the next character for a Natural Language Generation task. In the case of language, these models predict the next character as they can attend to know the importance of tokens/characters around the given characters. In a similar manner, why can’t we apply…

Part 2 — DynamoDB with AWS Lambda and FastAPI with Github Actions integration — Introduction In Part 1, we went through a hands-on guide on how to use AWS Lambda to deploy web applications built using FastAPI. In this blog, we will create two tables using AWS DynamoDB and develop API endpoints to create and get data from the tables. Creating Tables We will be creating two…

Part 1 — Deploying FastAPI application on AWS Lambda — Introduction In Part 1 of this blog, we will go through setting up AWS SAM, creating a Lambda, and adding FastAPI API endpoints. You might have heard a lot about serverless functions and their advantages so in this blog we won’t be going into the explanation of, what are serverless functions…

For calling independent async functions in parallel — Both FastAPI and Flask are web frameworks (well Flask is a “microframework”) to build APIs with Python. Based on your needs you might have used any of these from time to time. But for different applications, it can become quite a headache to decide which one to go for. …

Exploring the Power of Positive Reinforcement with Reinforcement Learning and AI-Language Generation — Introduction I have been meaning to write this blog for a long time but found the time to write it today, it’s never too late! Probably this is the right time as well. If you are reading this blog, then you might already have come across and maybe even use ChatGPT…

A hands-on guide to serving model inference using sockets — A Socket specifies a network address and port via which the application can communicate to the process on the network. Sockets are low-level programming interfaces that are commonly used for developing real-time, bi-directional communication between applications. How are Sockets different from REST APIs? REST and Sockets are both used to create networked applications. REST (Representational State Transfer)…

Brief data analysis of 2021 Kaggle ML & DS Survey data — “Data is the new oil”, they said and there are a lot of frameworks, tools, and instrumentations schemes required to employ this new oil to convert it into a valuable fuel to reach the finish line. These data come in multiple formats images, videos, text, audio, etc… and one can…

Adding themes to your web application made easy — The ability to change themes in different websites have always fascinated me. I always used to wonder how can a single click of a button change the whole theme of the website, I was aware of the logic mode === "light" lightTheme : darkTheme but was unaware of the inner…

Develop a text generation API — In the blog, Generating storylines using a T5 Transformer we saw how we can fine-tune a Sequence2Sequence (Text-To-Text) Transformer (T5) to generate storylines/plots by providing inputs like genre, director, cast, and ethnicity. In this blog, we will check out how we can use that trained T5 Model for inference. …