50+ days of Machine Learning

 Hello :) Today is Day 87! A quick summary of today: after a lot of thought and considerations I finally registered for one of Stanford's AI professional program courses - XCS224W   Went over fresh published by deeplearning.ai -  JavaScript RAG Web Apps with LlamaIndex Maybe 2 weeks ago I did the application for Stanford's AI professional program, and since I got accepted I have been thinking about taking one of the courses. ML with Graphs is one of primary interest to me because of its application in financial fraud, but more than that - it is a lot of money (thankfully my parents support me taking such high level education courses). Yes the quality, it is top notch, but besides Stanford's AI professional certificate program which includes the below courses (to get the certificate I need to complete 3) I was heavily considering MITx MicroMasters in Statistics and Data Science . Online there are a lot of reviews of it being very hard, requiring a lot of hours, and this real

 Hello :) Today is Day 86! A quick summary of today: Coded, planned, recorded and posted a video tutorial making a chat with your pdf rag system for free All code + colab link + pdf used is on this github repo Well, after waking up today, I definitely did not expect to plan, execute and upload an almost 1hr tutorial on youtube.  I was looking around chat with your PDF videos, to see what I can improve in my pdf_rag_from_scratch  but I saw that most of the videos require an OpenAI api key, and I did not like that, given the availability of so many free resources and models.  And I found this great resource from huggingface  - Building A RAG System with Gemma, MongoDB and Open Source Model. Instead of a pdf, they were using some dataframe for films, so I decided to improve upon that, and make the code preprocess a pdf, embed it, upload to mongodb, load gemma, create a prompt and chat with the pdf (kind of a combination of the tutorial + my pdf_rag_from_scratch).  The code itself is not