Section 2: Language Models (Overview)

Section 2: GPT Model (Overview)

Section 2: What Are Agents? (Overview)

Section 3: What Is Prompting? (Basic Overview)

Section 3: Building Better Prompt - Part 1

Section 3: Building Better Prompt - Part 2

Section 4: OpenAI Platform Overview

Section 4: OpenAI Platform - Add Credit Balance

Section 4: Important Note on OpenAI API Credit Balance

Section 4: Overview of Tokens

Section 4: Choosing a Model

Section 4: Chat in OpenAI Platform

Section 5 : Setup : Install Python & VSCode

Section 5 : Setup : Create Workspace & Virtual Environment - Part 1

Section 5 : Setup : Create Workspace & Virtual Environment - Part 2

Section 6: Using OpenAI Python SDK : Create an OpenAI API key

Section 6: Using OpenAI Python SDK : Load OpenAI Key in a Notebook

Section 6: Using OpenAI Python SDK : Demo 1: Generate a Text Response from your prompt

Section 6: Using OpenAI Python SDK : Demo 2: Using System Messages

Section 6: Using OpenAI Python SDK : Demo 3: Reusable Prompts

Section 6: Using OpenAI Python SDK : Demo 4: Building a Conversation

Section 7: [AI APP] : Command Line Chatbot - Helper Functions

Section 7: [AI APP] : Build a Command Line ChatBot

Section 7: [AI APP] : Streamlit Chatbot : Environment Setup

Section 7: [AI APP] : Streamlit Chatbot : UI & Model Communication

Section 7: [AI APP] : Streamlit Chatbot : Refining & Completing

Section 8: LangChain Basics : What Is LangChain? (Overview & Key Concepts)

Section 8: LangChain Basics : Why We Need RAG & LangChain (Concepts & Components)

Section 8: LangChain Basics : Install LangChain (Python Setup)

Section 9: LangChain Messages : Types of Messages in LangChain (Human, AI, System)

Section 9: LangChain Messages : Message Flow in a Conversation

Section 9: LangChain Messages : Building a Conversation with Message History

Section 9: LangChain Messages : Using System Message

Section 10: How Chaining Works

Section 10: Build your First Chain

Section 11 : Creating Dynamic Prompts with Templates : Introduction to Templates

Section 11 : Creating Dynamic Prompts with Templates : Using PromptTemplate

Section 11 : Creating Dynamic Prompts with Templates : Using ChatPromptTemplate

Section 12 : [AI APP] : Build the App UI with Streamlit

Section 12 : [AI APP] : Build the Core Application Logic

Section 12 : [AI APP] : Run and Test the Application

Section 13 : Structuring LLM Output : Introduction to Output Parsers

Section 13 : Structuring LLM Output : Using StrOutputParser (String Output)

Section 13 : Structuring LLM Output : Using CommaSeparatedListOutputParser (List Output)

Section 13 : Structuring LLM Output : Using JsonOutputParser (Dictionary Output)

Section 13 : Structuring LLM Output : Using PydanticOutputParser(User-defined Pydantic model)

Section 14: Building Chain with Runnables : Introduction to Runnables

Section 14: Building Chain with Runnables : Using RunnableLambda (Adding Custom Logic to a Chain)

Section 14: Building Chain with Runnables : RunnableSequence: Build a Step-by-Step Chain

Section 14: Building Chain with Runnables : RunnableParallel: Run Multiple Steps in parallel in a Chain

Section 14: Building Chain with Runnables : RunnablePassthrough: Pass Data without changing

Section 15 : [AI APP] Enhance InterviewPrepApp using Runnables : What we will build

Section 15 : [AI APP] Enhance InterviewPrepApp using Runnables : Update Streamlit UI

Section 15 : [AI APP] Enhance InterviewPrepApp using Runnables : Update Backend Code

Section 15 : [AI APP] Enhance InterviewPrepApp using Runnables : Test App

Section 16: AgenticAI with Agents : Understanding Agents

Section 16: AgenticAI with Agents : Runnable vs Agents

Section 17: Tools in Agentic AI : Agents and Tools

Section 17: Tools in Agentic AI : Simple Tool Example

Section 17: Tools in Agentic AI : Sequential Tool Calls

Section 17: Tools in Agentic AI : Structured Output

Section 17: Tools in Agentic AI : Structured Output Using Tools (ToolStrategy)

Section 17: Tools in Agentic AI : Structured Output Using Model Features (ProviderStrategy)

Section 17: Tools in Agentic AI : Using Built-in Web Search Tool (Part 1)

Section 17: Tools in Agentic AI : Using Built-in Web Search Tool (Part 2)

Section 17: Tools in Agentic AI : What is a Toolkit

Section 17: Tools in Agentic AI : Using a Toolkit for database operations

Section 18 : [AI APP] - Enhancing the Interview App with AI Agents : What we will build

Section 18 : [AI APP] - Enhancing the Interview App : Extend Existing Project Structure

Section 18 : [AI APP] - Enhancing the Interview App : Enhancing UI: Display Questions with Streamlit

Section 18 : [AI APP] - Enhancing the Interview App : Adding Custom Tools to the Application

Section 18 : [AI APP] - Enhancing the Interview App : Implementing Agent Logic (Create & Invoke)

Section 18 : [AI APP] - Enhancing the Interview App : Integrating Agent with Existing UI

Section 18 : [AI APP] - Enhancing the Interview App : Displaying LLM Analysis in the App

Section 18 : [AI APP] - Enhancing the Interview App : Testing the Enhanced Application

Section 19: Streaming Responses : Introduction to Streaming

Section 19: Streaming Responses : Agent Progress Streaming (Step-by-Step Execution)

Section 19: Streaming Responses : Streaming LLM Tokens in Real Time

Section 19: Streaming Responses : Custom Streaming (Emit Updates from Tools during Execution)

Section 20 : Middleware in Agent : Introduction to Middleware in LangChainic AI

Section 20 : Middleware in Agentic AI: Logging with Middleware

Section 20 : Middleware in Agentic AI: Logging with Middleware : Demo

Section 20 : Middleware in Agentic AI: Handling Tool Errors with Middleware

Section 20 : Middleware in Agentic AI: Handling Tool Errors with Middleware : Demo

Section 20 : Middleware in Agentic AI: Handlers (Continuing Model & Tool Execution)

Section 20 : Middleware in Agentic AI: Static vs Dynamic System Prompts (Runtime Prompt Control)

Section 20 : Middleware in Agentic AI: Static vs Dynamic System Prompts : Demo

Section 20 : Middleware in Agentic AI: Static vs Dynamic Model Selection (Runtime Model Selection & Routing)

Section 20 : Middleware in Agentic AI: Static Model - Demo

Section 20 : Middleware in Agentic AI: Dynamic Model Selection: Demo

Section 21 : Memory management with Pre-Built Middleware : Introduction

Section 21 : Memory management with Pre-Built Middleware : Managing Multi-Turn Conversations with Checkpointers I

Section 21 : Memory management with Pre-Built Middleware : Managing Multi-Turn Conversations with Checkpointers II

Section 21 : Memory management with Pre-Built Middleware : Problem: Message Growth in Multi-Turn Conversations

Section 21 : Memory management with Pre-Built Middleware : Solutions: Managing Conversation Memory Efficiently

Section 21 : Memory management with Pre-Built Middleware : Summarization Middleware

Section 22 : Guardrails : Introduction

Section 22 : Guardrails : Detecting Sensitive Information (PII Detection)

Section 22 : Guardrails : PII Detection: Demo

Section 22 : Guardrails : Human-in-the-Loop: Adding Human Oversight

Section 22 : Guardrails : Human In The Loop: Demo

Section 22 : Guardrails : Building Custom Guardrails

Section 22 : Guardrails : Custom Guardrails: Content Filtering - Demo

Section 23 : RAG Fundamentals : Overview of RAG (Retrieval-Augmented Generation)

Section 23 : RAG Fundamentals : Loading Documents with Document Loaders: Demo

Section 23 : RAG Fundamentals : Text Splitting: Breaking Documents into Chunks

Section 23 : RAG Fundamentals : Text Splitting - Demo

Section 23 : RAG Fundamentals : Understanding Embeddings

Section 23 : RAG Fundamentals : Generating Embeddings with an Embedding Model - Demo

Section 23 : RAG Fundamentals : Why Embeddings Matter for Retrieval?

Section 23 : RAG Fundamentals : Introduction to Vector Stores

Section 23 : RAG Fundamentals : Vector Store Demo

Section 23 : RAG Fundamentals : Semantic Search: Retrieving Relevant Documents

Section 23 : RAG Fundamentals : Search Strategies: Similarity, Similarity Score Threshold & MMR

Section 23 : RAG Fundamentals : Similarity Search & Similarity Score Threshold - Demo

Section 23 : RAG Fundamentals : MMR Search - Demo

Section 24: Building RAG Systems : RAG Pipeline

Section 24: Building RAG Systems : RAG Implementation Approaches (Chain vs Agentic RAG)

Section 24: Building RAG Systems : Building a RAG Chain (Step-by-Step Demo) - Part 1 : RA

Section 24: Building RAG Systems : Building a RAG Chain (Step-by-Step Demo) - Part 2

Section 24: Building RAG Systems : Using Agentic RAG for Retrieval & Reasoning

Section 25 : [AI RAG APP] - Chat with PDF App : Building the Streamlit UI

Section 25 : [AI RAG APP] - Chat with PDF App : Loading PDFs into a Vector Store

Section 25 : [AI RAG APP] - Chat with PDF App : Creating Helper Functions for RAG

Section 25 : [AI RAG APP] - Chat with PDF App : Connecting the UI with RAG Logic (Streamlit + Backend)

Section 25 : [AI RAG APP] - Chat with PDF App : Testing the Chat with PDF Application

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : What We’ll Build

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Build the App UI with Streamlit – Part 1

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Build the App UI with Streamlit – Part 2

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Implement the Backend for Lesson Generation

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Integrate Lesson Generation with the UI

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Test Lesson Generation

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Use a Tool to execute Python Code

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Backend Code to create the Agent - I

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Backend Code to create the Agent - II

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Backend Code to Invoke the Agent with Learner Submitted Code

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Integrate Code Execution with UI

Section 26 : [Agentic AI APP] [V1] PyPracticeAI : Test the Application

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : What We’ll Build

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Chat UI Demo

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Walkthrough of the Chat UI Streamlit Code

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Problem: Challenge Solution Disappears

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Fix: Challenge Solution Disappears

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Understanding Context for Tutor Chat

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Update the Streamlit Code with Interaction State F

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Conversation Id

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Create the Context Injection Middleware - Part 1

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat :Create the Context Injection Middleware - Part 2

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Backend Code to create Tutor Agent

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Backend Code to Invoke the Tutor Agent

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Integrate with the Streamlit App

Section 27: [Agentic AI APP ] [V2] - PyPracticeAI : Tutor Chat : Test the App

Section 28: [Agentic AI APP ] [V3] - PyPracticeAI : Summarization Middleware : What We’ll Build

Section 28: [Agentic AI APP ] [V3] - PyPracticeAI : Summarization Middleware : Create Summarization Middleware

Section 28: [Agentic AI APP ] [V3] - PyPracticeAI : Summarization Middleware : Associate Middleware with Agent

Section 28: [Agentic AI APP ] [V3] - PyPracticeAI : Summarization Middleware : Logging Middleware with Agent

Section 28: [Agentic AI APP ] [V3] - PyPracticeAI : Summarization Middleware : Test

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : What We’ll Build

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Build the App UI with Streamlit – Part 1

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Build the App UI with Streamlit – Part 2

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Build the App UI with Streamlit – Part 3

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Create Tool & Protect with HITL middleware

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Backend Code: Create the Access Agent

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Backend Code: Invoke the Access Agent

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Implement Tool Execution - Part 1

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Implement Tool Execution - Part 2

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Integrate the Access Agent with the Streamlit App

Section 29: [Agentic AI APP ] [V4] - PyPracticeAI : HITL : Test the Application