Ravi Shankar Rai

Aug 16, 2024 | medium.com | Ravi Shankar Rai

In this post we’ll go over an extension of the typical app to chat with a PDF using RAG. Here we will specifically take in two PDFs, and compare them using a custom prompt. We’ll also configure it to let the user decide if they only want to chat with one or both documents. Credits to Krish Naik for the original idea: https://www.youtube.com/watch?v=0LE5XrxGvbo&t=1065s. Also, see my GitHub repo for the code, and note that I used Python 3.12 in this case: https://github.com/RavinderRai/aws-llm-app.

Aug 10, 2024 | medium.com | Ravi Shankar Rai

In this post we will go over the basics of training a model with AWS. This is the fundamentals of and end-to-end project, where we will take data from an S3 bucket, clean it with AWS Glue, then run a small training pipeline to train a model on our dataset. The problem here is predicting engagement levels of gamers, for which we can find the data thanks to Kaggle: Game Behavior Dataset.

Jul 31, 2024 | medium.com | Ravi Shankar Rai

This post is a description of a mini-project on a FastAPI app that let's you generate music from just text alone. It takes lyrics as text input and will generate music based off of that, but it goes beyond that a bit by first letting you generate lyrics by describing the type of music you'd like to listen to. Credits go to Anytime AI for the original project, and this is just a modified/extended version of it.

Apr 8, 2024 | mdpi.com | Sowmya Mekala |Ravi Shankar Rai |Samantha Reed |Bill Bowen

All articles published by MDPI are made immediately available worldwide under an open access license. No specialpermission is required to reuse all or part of the article published by MDPI, including figures and tables. Forarticles published under an open access Creative Common CC BY license, any part of the article may be reused withoutpermission provided that the original article is clearly cited. For more information, please refer tohttps://www.mdpi.com/openaccess.