Mastering Generative AI and Agentic AI with Python Training

Curriculum:

Module 1: Introduction

• Overview of Generative AI and Agentic AI
• Industry applications and trends
• Understanding the AI lifecycle

Module 2: Introduction to Coding World with Python

• Python setup and environment configuration
• Python basics: syntax, variables, and expressions
• Interactive Python exercises

Module 3: Data Types in Python

• Numeric, string, list, tuple, set, dictionary
• Type conversions and operations
• Practical exercises on data handling

Module 4: Conditionals in Python

• if, elif, else statements
• Nested conditions and logical operators
• Practical problem-solving exercises

Module 5: Loops in Python

• for and while loops
• Loop control statements: break, continue, pass
• Iterating over collections

Module 6: Functions in Python

• Defining and calling functions
• Arguments, return values, and scope
• Lambda functions and functional programming basics

Module 7: Comprehensions in Python

• List, dictionary, set, and generator comprehensions
• Practical examples for efficient code writing

Module 8: Generators and Decorators in Python

• Generator functions and yield
• Decorators: syntax, applications, and examples

Module 9: Object-Oriented Programming in Python

• Classes, objects, and methods
• Inheritance, polymorphism, encapsulation
• Real-world OOP examples

Module 10: File and Exception Handling in Python

• Reading/writing files
• Handling exceptions with try-except
• Custom exception handling

Module 11: MultiThreading, Multiprocessing, GIL in Python

• Thread-based and process-based concurrency
• Global Interpreter Lock (GIL) explanation
• Practical examples for parallelism

Module 12: Asyncio in Python

• Async and await syntax
• Asynchronous programming concepts
• Building async workflows

Module 13: All That You Should Know About Pydantic

• Data validation and parsing
• Pydantic models and use-cases in AI pipelines

Module 14: Core Foundations of Generative AI

• Introduction to generative models
• Overview of Transformers, Diffusion, and LLMs
• Use cases in NLP, vision, and multi-modal AI

Module 15: API Setup & Integration

• REST and GraphQL APIs
• Integrating LLMs with APIs
• Security and authentication

Module 16: Advanced Prompt Engineering Techniques

• Designing effective prompts for LLMs
• Prompt tuning, context management, and chains

Module 17: Prompt Serialization & Instruction Formats

• Structured prompt templates
• Serialization for workflow integration

Module 18: Local LLM Deployment & API Integration

• Running LLMs locally
• Connecting LLMs to custom applications

Module 19: Running LLMs via Hugging Face Hub

• Hugging Face Hub overview
• Model selection and deployment
• Integration with Python

Module 20: Building AI Agents and Agentic Workflows

• Introduction to agentic AI
• Designing agent workflows
• Automating tasks with AI agents

Module 21: Building Chat with PDF Project using RAG (Retrieval-Augmented Generation)

• Understanding RAG pipelines
• Integrating PDF data sources
• Chatbot implementation

Module 22: Scalable RAG with Async Queues & Distributed Workers

• Scaling RAG workflows
• Async queues and task distribution

Module 23: Multi-Modal Agents

• Combining text, image, and audio inputs
• Multi-modal AI agent implementation

Module 24: Building Agentic Workflows with LangGraph

• LangGraph introduction
• Workflow design and execution

Module 25: Checkpointing Workflows in LangGraph with MongoDB

• Workflow persistence
• Using MongoDB for checkpoints

Module 26: The Memory Layer - Building Short, Long, and Semantic Memory in AI Agents

• Memory design in AI agents
• Implementing memory layers

Module 27: Graph Memory and Knowledge Graphs in AI Agents

• Knowledge graph integration
• Enhancing agent reasoning capabilities

Module 28: Conversational Agentic AI with Voice Agents and Chained Patterns

• Voice-enabled AI agents
• Chaining patterns for dynamic interactions

Module 29: Model Context Protocol (MCP)

• Context-aware AI design
• MCP principles and implementation

Module 30: Git – Additional Learning

• Version control fundamentals
• Best practices for AI projects

Module 31: Mastering Docker for Developers – From Basics to CLI and Dockerfile

• Docker fundamentals
• Building and running containers for AI applications

Module 32: Agent SDK

• Using SDKs to build agentic AI solutions
• Integration with existing pipelines

Module 33: Farewell & Next Steps

• Recap of key learnings
• Project showcase and certification guidance