Module 1: Development Environment Setup

• 1.1 Introduction to AI Development Environment
• 1.2 Code Editors
• 1.3 Python Installation
• 1.4 Jupyter Notebook Setup
• 1.5 PyCharm Setup
• 1.6 VS Code Setup
• 1.7 Virtual Environments
• 1.8 Package Management (pip)
• 1.9 Environment Variables (.env)
• 1.10 Essential VS Code Extensions
• 1.11 Project Structure

Module 2: Introduction to AI and Computing

• 2.1 Instructions
• 2.2 Instruction Execution Cycle
• 2.3 Capabilities of Computers
• 2.4 Intelligence as a Service (AIaaS)

Module 3: Introduction to Artificial Intelligence

• 3.1 What is Artificial Intelligence (AI)?
• 3.2 Types of Artificial Intelligence (Based on Capability)
• 3.3 Types of Artificial Intelligence (Based on Functionality)
• 3.4 AI vs Machine Learning vs Deep Learning
• 3.5 Applications of Artificial Intelligence
• 3.6 Advantages and Limitations of AI
• 3.7 Future of AI

Module 4: Introduction to Machine Learning

• 4.1 What is Machine Learning?
• 4.2 Types of Machine Learning
• 4.3 Supervised vs Unsupervised Learning
• 4.4 Machine Learning Workflow
• 4.5 Applications of Machine Learning

Module 5: Introduction to Neural Networks

• 5.1 What is a Neural Network?
• 5.2 Artificial Neural Network (ANN)
• 5.3 How an ANN Works
• 5.4 Applications of Neural Networks
• 5.5 Neural Networks vs Traditional Programming

Module 6: Introduction to Deep Learning

• 6.1 What is Deep Learning?
• 6.2 How Deep Learning Works
• 6.3 Applications of Deep Learning
• 6.4 What is Multimodality?
• 6.5 Applications of Multimodal AI
• 6.6 Deep Learning in Generative AI

Module 7: Generative AI & Large Language Models (LLMs)

• 7.1 Introduction to Generative AI
• 7.2 Large Language Models (LLMs)
• 7.3 GPT Family & Evolution
• 7.4 LLM Processing Pipeline
• 7.5 Tokenization
• 7.6 Vocabulary
• 7.7 Special / Reserved Tokens
• 7.8 Context Window
• 7.9 Next Token Prediction
• 7.10 De-Tokenization
• 7.11 LLM Inference
• 7.12 Applications of LLMs

Module 8: Transformer Architecture & Embeddings

• 8.1 Introduction to Transformer Architecture
• 8.2 Encoder vs Decoder Architecture
• 8.3 Transformer Processing Pipeline
• 8.4 Vector Embeddings
• 8.5 Embedding Matrix
• 8.6 Embedding Dimensions
• 8.7 Similarity in Vector Space
• 8.8 Cosine Similarity
• 8.9 Types of Embeddings
• 8.10 Positional Encoding
• 8.11 Self-Attention
• 8.12 Multi-Head Attention
• 8.13 Feed Forward Network (FFN)
• 8.14 Residual Connections & Layer Normalization
• 8.15 Output Layer
• 8.16 Transformer Processing Flow
• 8.17 Attention Visualization

Module 9: Working with Large Language Models (LLMs)

• 9.1 Open Source vs Closed Source LLMs
• 9.2 Popular LLM Providers
• 9.3 Connecting to LLM Models
• 9.4 OpenAI-Compatible APIs
• 9.5 LLM Generation Controls
• 9.6 How LLMs are Trained
• 9.7 Training vs Inference
• 9.8 Backpropagation (Concept)
• 9.9 Types of AI Models Based on Input & Output
• 9.10 Working with Files in LLM Applications

Module 10: Prompt Engineering

• 10.1 Introduction to Prompt Engineering
• 10.2 Common Ways to Format Prompts
• 10.3 Types of Prompts
• 10.4 Prompt Styles
• 10.5 Guardrails
• 10.6 Output Formatting
• 10.7 Constraints Prompting
• 10.8 Step-by-Step Task Decomposition
• 10.9 Prompt Chaining
• 10.10 Prompt Engineering Best Practices
• 10.11 Content & Code Generation
• 10.12 Data Extraction
• 10.13 Prompt Injection
• 10.14 JSON Response Generation

Module 11: Self-Hosted LLMs with Ollama

• 11.1 Introduction to Self-Hosted LLMs
• 11.2 Introduction to Ollama
• 11.3 Installing Ollama
• 11.4 Working with Ollama
• 11.5 Popular Ollama Models
• 11.6 Using Ollama from Python
• 11.7 OpenAI-Compatible API with Ollama

Module 12: Building an LLM as a Service with Flask

• 12.1 Introduction to LLM as a Service
• 12.2 Setting Up the Flask Project
• 12.3 Flask Templates (Jinja2)
• 12.4 Creating the Chat Interface
• 12.5 Building LLM API Endpoints
• 12.6 Connecting an LLM
• 12.7 Sending Prompts to the LLM
• 12.8 Testing the Application
• 12.9 Deploying the Flask Application
• 12.10 Consuming the API from React

Module 13: LLM Service Testing with Postman & Bruno

• 13.1 Introduction to API Testing
• 13.2 Introduction to Postman
• 13.3 Introduction to Bruno
• 13.4 Returning JSON Data
• 13.5 Creating a POST Request
• 13.6 Testing APIs
• 13.7 Error Handling

Module 14: Building LLM Services with FastAPI

• 14.1 Introduction to FastAPI
• 14.2 Setting Up a FastAPI Project
• 14.3 Introduction to Pydantic
• 14.4 Creating Your First API
• 14.5 Building an LLM Chat Service
• 14.6 Connecting an LLM
• 14.7 Request Validation with Pydantic
• 14.8 Error Handling
• 14.9 Interactive API Documentation
• 14.10 Testing the APIs

Module 15: Hugging Face & Open-Source LLMs

• 15.1 Introduction to Hugging Face
• 15.2 GitHub vs Hugging Face
• 15.3 Creating a Hugging Face Account
• 15.4 Hugging Face Architecture
• 15.5 Important Hugging Face Libraries
• 15.6 Types of AI Models
• 15.7 Model Parameters
• 15.8 Popular Model Sizes
• 15.9 Model Weight Formats
• 15.10 Model Size Calculation
• 15.11 Model Licenses
• 15.12 Installing Transformers
• 15.13 Hugging Face Pipelines
• 15.14 Tokenizers
• 15.15 AutoTokenizer
• 15.16 Downloading Models from Hugging Face
• 15.17 Hugging Face Datasets
• 15.18 Multi-modal LLMs in Hugging Face
• 15.19 Hugging Face Spaces

Module 16: Advanced LLM Features

• 16.1 Advanced LLM Capabilities
• 16.2 JSON Output
• 16.3 Structured Output
• 16.4 Streaming Responses
• 16.5 Vision Models (Multimodal AI)
• 16.6 Function Calling
• 16.7 Vision + Function Calling

Module 17: Agentic AI

• 17.1 Agent Workflow
• 17.2 Planning
• 17.3 Reasoning
• 17.4 Observation
• 17.5 Adding Tools to AI Agents
• 17.6 Manual Tool Calling (Rule-Based)
• 17.7 AI Agent Tool Calling (LLM-Based)
• 17.8 AI Agent with Multiple Tools
• 17.9 System Prompts for AI Agents
• 17.10 Building AI Agents
• Module 18: LangChain

18.1 Introduction to LangChain

• 18.2 Installing LangChain
• 18.3 Chat Models
• 18.4 Prompt Templates
• 18.5 Output Parsers
• 18.6 Chains
• 18.7 Tools
• 18.8 LangChain Agents
• 18.9 ReAct Agent (Introduction)
• 18.10 Conversation Memory
• 18.11 Document Loaders
• 18.12 Text Splitters
• 18.13 Callbacks

Module 19: Memory in AI Agents

• 19.1 Introduction to Memory
• 19.2 Context Window
• 19.3 Types of Memory
• 19.4 Conversation Memory
• 19.5 Persistent Memory
• 19.6 Checkpoints
• 19.7 Memory Storage Options
• 19.8 Session Memory
• 19.9 Implementing Memory

Module 20: Retrieval-Augmented Generation (RAG)

• 20.1 Introduction to RAG
• 20.2 Problem Statements
• 20.3 RAG Architecture
• 20.4 Phases of RAG
• 20.5 Document Loaders
• 20.6 Text Chunking
• 20.7 Query Rewriting
• 20.8 Embedding Models
• 20.9 Retriever
• 20.10 Building a Complete RAG Application
• 20.11 Hybrid Search

Module 21: Vector Databases

• 21.1 Introduction to Vector Databases
• 21.2 Vector Database Architecture
• 21.3 Popular Vector Databases
• 21.4 Similarity Search
• 21.5 CRUD Operations
• 21.6 Metadata Filtering
• 21.7 Choosing the Right Vector Database

Module 22: LangGraph

• 22.1 Introduction to LangGraph
• 22.2 LangGraph Architecture
• 22.3 Installing LangGraph
• 22.4 Understanding State
• 22.5 Nodes
• 22.6 Edges
• 22.7 Conditional Edges
• 22.8 State
• 22.9 Building Your First Graph
• 22.10 Conditional Routing
• 22.11 Integrating LLMs
• 22.12 Tool Calling in LangGraph
• 22.13 Memory & Checkpoints
• 22.14 Human-in-the-Loop

Module 23: Model Context Protocol (MCP)

• 23.1 Introduction to MCP
• 23.2 Understanding the MCP Architecture
• 23.3 MCP Components
• 23.4 MCP Communication
• 23.5 Building an MCP Server
• 23.6 Building an MCP Client
• 23.7 MCP Transport Mechanisms
• 23.8 Creating MCP Tools
• 23.9 Working with MCP Resources
• 23.10 MCP Prompts
• 23.11 Integrating MCP with AI Agents

Module 24: Multi-Agent Systems

• 24.1 Introduction to Multi-Agent Systems
• 24.2 Multi-Agent Architecture
• 24.3 Types of AI Agents
• 24.4 Agent Communication
• 24.5 Task Planning
• 24.6 Agent Collaboration Patterns
• 24.7 Memory in Multi-Agent Systems
• 24.8 Tool Sharing
• 24.9 Building Multi-Agent Systems
• 24.10 Multi-Agent Frameworks
• 24.11 Supervisor Agent

Module 25: AI Evaluation

• 25.1 Evaluating LLM Responses
• 25.2 Hallucinations
• 25.3 Ground Truth
• 25.4 Precision
• 25.5 Recall
• 25.6 Latency
• 25.7 Cost Optimization
• 25.8 Prompt Evaluation
• 25.9 RAG Evaluation
• 25.10 Agent Evaluation

Module 26: Deployment & Production AI Applications

• 26.1 FastAPI Deployment
• 26.2 Docker
• 26.3 Docker Compose
• 26.4 Nginx
• 26.5 HTTPS
• 26.6 Environment Variables
• 26.7 Logging
• 26.8 Monitoring
• 26.9 Authentication
• 26.10 Production Best Practices
• 26.11 Deploying AI Agents
• 26.12 End-to-End Projects