Direct AI Powered By Quality Thought

Command line applications (CLI) These applications process the commands and arguments # windows ping google.com # linux ping -c 4 google.com Any command line application will generally have arguments Arguments are of two types positional arguments: position matters keyword arguments: this argument has a key and a value short form -<char>: Examples are -a test… Continue reading Python Classroom notes 21/Jul/2026

Vector Database retrieval techniques Dense: Preference to meaning Sparse: Keyword based search Hybrid/FUSE: Combine dense and sparse and define weights Example Ensure the following packages are installed uv add langchain-chroma rank_bm25 chromadb langchain-community Refer Here for the changes done

Project-Idea: Customer Churn Signalling Agent Problem statement You know your best customers, The one who ordered 12 times last year, left 5 star-reviews, referreed their friends Then one day – they just stopped No complaints, They simply opened a competitors app instead, You never saw it coming. But the data did. What we want to… Continue reading Gen-AI Developer Classroom notes 19/Jul/2026

Access modifiers Instead fo strict keywords like public, private, protected Python uses naming conventions to indicate the scope of variables and methods By default, all the members in python class are public The reason python doesn’t force the rules is We are all consenting adults here Conventions | Access Level | Convention | Accessibility |… Continue reading Python Classroom notes 16/Jul/2026

Recursive character splitting Refer Here for the sample which explains how recursive chunking works try by having one seperator and then the second Refer Here for the adopted fix for the ncert book Refer Here for clean up Vector Storage Challanges: Source Document Updates Explore different index creation options Explore different retrieval mechanisms Embedding storage… Continue reading Gen-AI Developer Classroom notes 16/Jul/2026

Expection Handling Refer Here for exception handling Prompt: Give me best practices for python exception handling to be followed Prompt: Give me a tabular data of built in execption in python and when it is raised or when should i use this kind of exception (raise or throw) Pattern: Adapter When should i use this… Continue reading Python Classroom notes 15/Jul/2026

Section Aware chunking NCERT book is organized as per chapter pdf sections span across pages To solve this we need to split the entire chapter text into sections And lets have some chunk length (1000) with overlap of (150) We need to Perform Recursive Splitting First split by sections (for this we need to use… Continue reading Gen-AI Developer Classroom notes 15/Jul/2026

some useful prompts You are an expert in design patterns I will give the name of the pattern and implementation language Give me what problem is solved by this pattern Give me simple illustrations with relatable examples from popular apps like amazon, bookmyshow as they are easier to understand Creational: Factory and Behavioral: Strategy Refer… Continue reading Python Classroom notes 13/Jul/2026

Dealing with images in RAG Broadly two approaches Capture the meaning of the image embedd the image Multi modal RAG Getting Caption of a Image Refer Here for the right caption.

Dealing with images in RAG Broadly two approaches Capture the meaning of the image embedd the image Multi modal RAG Getting Caption of a Image Refer Here for the right caption.

Design Patterns In programming languages we have two terms Patterns: Solutions to known problems This gives you the right way of implementation for an existing problem which is already solved by someone AntiPatterns Never follow this Design Patterns: Refer Here Design Patterns are classified into Creational Patterns Structural Patterns Behavioral Patterns Problem I have a… Continue reading Python Classroom notes 11/Jul/2026

RAG – Productionization To productionize the RAG we need to dive deeper on chunking vector stores RAG scoring (measure to ensure the results are good enough) Gaurdrails Variety of data text images Idea – CBSE Teacher Look at the mathematics book Refer Here We need to extract text and images from pdf and ensure they… Continue reading Gen-AI Developer Classroom notes 11/Jul/2026

Building RAG with Relational Databases Building RAGs on structured data is all about understanding schema converting natural language => Query form Database: Relational SQLDatabaseToolkit: Refer Here for class reference doc NOSQL: Mongodb Refer Here for the changes done to build a dominos simulator.

Duck Typing Duck typing in python Type Hinting Python is dynamically typed language Type hinting improves readability IDE to give better suggestions frameworks like FastAPI, Pydantic rely on this Prompt: You are an expert in Python I’m trying to learn python. Give me possibilites of using type hinting Explain each possibility with a simple example… Continue reading Python Classroom notes 09/Jul/2026

First RAG Lets build a simple RAG Refer Here for the changes done to build our first simple RAG

OOP contd IN python everything is derived from object Operator Overloading Refer Here Figuring out functionality of any class Go through methods and members in class defintions Class Methods and Static Methods When we deal with methods inside a class we have instance methods class methods static methods When we deal with members or attributes… Continue reading Python Classroom notes 07/Jul/2026

Embeddings Embedding embed the meaning in the form of the vector (a mathematical point) Early idea of Embedding was done by a library called as Word2Vec Embedding will have the whole vocabulary Prompt IN simple timeline viewer show me evolution of embeddings from word2vec quoting significant milestones Embedding models Opensource embedding models Embedding models as… Continue reading Gen-AI Developer Classroom notes 07/Jul/2026

Composition This depicts the has-a relationship Lets do a simple example Refer Here for notebook and Refer Here for calculator example.

Chunking or Splitting IN RAG we deal with two models large language model (llm) embedding model Embedding models convert text into vector which we store in vector database. For effective retrieval, it better if we chunk or split the document into multiple chunks. chunk in langchain will be document. For chunking Refer Here Chunking stragies… Continue reading Gen-AI Developer Classroom notes 06/Jul/2026

Scenario We are implementing a file parser This parser needs to read a file and give back the content For now lets assume the content is always text The text is categorized into Markdown HTML Plain html Wiki Text Abstraction helps in defining contracts Refer Here Refer Here for the changes added Terms: Abstraction MethodTemplate… Continue reading Python Classroom notes 04/Jul/2026