GenAI with Python Syllabus

GenAI with Python

Complete Professional Course Syllabus

Total Duration: 60 Hours

Recorded Sessions

MCQ Tests

Interview Q&A

Practical Code Sharing

Use Case Development

Access All MCQ Tests at https://ittechgenie.com/TopicSelection

Python Foundation

Comprehensive Python programming, data structures, OOP, and development methodologies

Generative AI

Deep dive into LLMs, prompt engineering, vector databases, and AI application development

Vector Databases

Hands-on with Chroma DB, FAISS, Pinecone, and semantic search implementation

Assessment

MCQs and Interview Questions provided for each module to test your understanding

Part 1: Python Foundations

Module 1

Python Orientation & Development Practices

4 Hours

Topics Covered

Evolution of Python and its ecosystem
Interpreter vs Compiler
REPL, Jupyter Notebook, and IDE workflow
SDLC models: Waterfall, Agile
Agile concepts: Scrum roles, ceremonies, sprints
Story pointing & backlog overview
Git overview and repository management
Branching, merging, conflict handling

MCQs (10) Interview Qs (5) Code Examples

Module 2

Core Python Programming

5 Hours

Topics Covered

Python syntax and indentation
Writing & executing Python scripts
Variables and memory model
Data types: Numeric, String, List, Tuple
Sets, Dictionaries, Boolean, Binary, None
User input and formatting output
Namespaces and scopes

MCQs (15) Interview Qs (6) Code Examples

Module 3

Program Flow & Data Handling

6 Hours

Topics Covered

Conditional statements
for/while loops
Iteration patterns
Range operations
Working with collections
Manipulating lists, sets, dictionaries
Type casting and comparisons

MCQs (12) Interview Qs (5) Code Examples

Module 4

Functions & Object-Oriented Programming

8 Hours

Topics Covered

Defining functions
Lambda expressions
Higher-order functions
Modules and imports
Working with arrays
OOP concepts: Classes, Inheritance, Polymorphism
Iterators & generators
Date & time operations

MCQs (15) Interview Qs (7) Code Examples

Module 5

Advanced Python Utilities & Testing

10 Hours

Topics Covered

Exception handling: try/except, custom exceptions
Logging in applications
Regular expressions
JSON & data parsing
Python Packaging (pip, __init__.py)
Introduction to data analysis libraries: NumPy, Pandas, Matplotlib
Collections module: Counter, NamedTuple, OrderedDict
Unit Testing with Pytest

MCQs (20) Interview Qs (8) Code Examples Use Case: Data Analysis App

Part 2: Foundations of AI & Generative AI

Module 6

Introduction to Artificial Intelligence

6 Hours

Topics Covered

What is AI? AI vs ML vs DL comparison
Evolution of generative systems
Applications of AI in industries
Introduction to Large Language Models (LLMs)
Popular LLM families: GPT, Claude 3, Gemini, Llama, Mistral
Open-source ecosystems
On-device AI and tools like Ollama
Responsible AI & Ethical considerations
LLM safety and security practices

MCQs (15) Interview Qs (6) Code Examples Use Case: AI Chatbot

Module 7

Prompt Engineering Essentials

8 Hours

Topics Covered

Structure of LLM communication: System, user, assistant roles
Zero-shot prompting
Few-shot prompting
Chain-of-Thought prompting
Instruction tuning & guidelines
Handling hallucinations
Constraints & LLM parameters
Safety & responsible usage
Prompt evaluation techniques

MCQs (18) Interview Qs (7) Code Examples Use Case: Document Q&A System

Part 3: Vector Databases, Embeddings & Semantic Search

Module 8

Embeddings & Vector Concepts

10 Hours

Topics Covered

What are embeddings?
How text converts to vectors
Use cases of embeddings
Generating embeddings with HuggingFace
Introduction to vector databases
ChromaDB environment setup
Creating collections
Storing embeddings and metadata
Performing vector search
Indexing strategies
Overview of other Vector DBs: FAISS, Pinecone, Weaviate
Multi-modal embeddings

MCQs (20) Interview Qs (8) Code Examples Use Case: Semantic Search Engine

Module 9

Managing Vector Databases

6 Hours

Topics Covered

Indexing and vector storage models
Partitioning strategies
Upsert operations
Metadata creation & filtering
Handling large-scale vector data
Choosing distance metrics (cosine, euclidean, dot-product)

MCQs (15) Interview Qs (6) Code Examples Use Case: Recommendation System

Module 10

Semantic Search

8 Hours

Topics Covered

Difference between keyword search & semantic search
Data preprocessing
Named Entity Recognition (NER)
Batch embedding creation
Metadata enrichment
Query pipelines
Evaluating semantic search quality
Hybrid search (keyword + vector)

MCQs (18) Interview Qs (7) Code Examples Use Case: Legal Document Search

Part 4: RAG, LangChain & Agents

Module 11

RAG Architecture & LangChain

12 Hours

Topics Covered

Understanding Retrieval-Augmented Generation
RAG components (retriever, LLM, memory, scorer)
Advanced search optimisation
Document loaders & transformers
Multi-query retrieval
Context compression
Building RAG pipelines with LangChain
Quick UIs using Streamlit and Gradio
Prompt templates
Response parsing
Serialization & chaining logic

MCQs (25) Interview Qs (10) Code Examples Use Case: Research Assistant

Module 12

Advanced Chains, Memory and Agent Systems

10 Hours

Topics Covered

Multi-step chains & routing
Memory management strategies
Long-term context retention
Tool usage with agents
Multi-agent workflows
LangSmith integration
Debugging & tracing pipeline behavior
Collaboration between agents

MCQs (20) Interview Qs (8) Code Examples Use Case: Autonomous AI Assistant

Module 13

LangSmith & LangGraph Fundamentals

10 Hours

Topics Covered

LangSmith platform overview
Project monitoring dashboards
Tracing workflows
Evaluating LLM outputs
Configuring evaluators
Experiment tracking
LangGraph: Graph-based agent orchestration
Nodes, edges and workflow design
Typed state management
Conditional routing
Checkpointing & persistence
Async vs Sync execution

MCQs (22) Interview Qs (9) Code Examples Use Case: Workflow Management System

Module 14

LangGraph – Practical Implementations

12 Hours

Topics Covered

Defining state using Pydantic/TypedDict
Building functional nodes
Adding logic branches and static edges
Integrating LLMs & tools
Developing multi-agent systems
Human-in-the-loop patterns
Error handling & retry logic
Visualizing LangGraph flows

MCQs (20) Interview Qs (8) Code Examples Use Case: Enterprise AI Orchestrator

Part 5: Capstone Projects & Assessments

Course Features & Assessment Structure

Course Delivery

~60 Hours Live Online Sessions with Recorded Access

MCQ Tests

10–25 questions per module covering all topics

Interview Preparation

5–10 interview questions with answers per module

Hands-on Practice

Real-time code sharing and practical implementation

Project Development

End-to-end use case projects for portfolio building

Labs & Assignments

Hands-on coding labs for LLMs, Vector DB, RAG, LangChain