Generative AI with Python –
Beginner Level
Duration: 4 Days (32 Hours)
Language: Python
Focus: Generative AI Foundations
Price Quote: 2.5 Lacs INR
Target Audience:
1st–2nd year college students
Beginners in AI / Python
No prior ML or AI knowledge required
Outcome:
Students understand how Generative AI works, can use LLMs via Python, and build GenAI
application.
####################### Course
Outline################################
Day 1 (8 Hours): Foundations of Python & AI Thinking
Session 1 (2 hrs): Python for AI Basics
Python fundamentals (variables, loops, functions)
Lists, dictionaries, JSON handling
Virtual environments & packages
Writing clean Python scripts
Session 2 (2 hrs): Introduction to Artificial Intelligence
What is AI, ML, DL, Generative AI
Difference between:
o Rule-based systems
o Machine Learning
o Generative AI
Real-world GenAI examples (education, chatbots, search)
Session 3 (2 hrs): Understanding Large Language Models (LLMs)
What is an LLM?
Tokens, prompts, responses
Prompt vs Completion
Limitations of LLMs (hallucination, bias)
Session 4 (2 hrs): First Hands-on with GenAI
Calling an LLM using Python (API-based)
Writing your first prompt
Prompt experimentation
Simple Q&A application
Day 2 (8 Hours): Prompt Engineering & Text Generation
Session 1 (2 hrs): Prompt Engineering Basics
Zero-shot, one-shot, few-shot prompting
Instruction prompts
System vs user prompts
Session 2 (2 hrs): Controlling LLM Output
Temperature, max tokens
Output formatting (JSON, bullet points)
Guardrails (what LLM should NOT do)
Session 3 (2 hrs): Python + LLM Integration
Building reusable Python functions
Handling API responses
Error handling
Session 4 (2 hrs): Mini Lab
Build a Text Generator / Study Assistant
Generate summaries, explanations, quizzes
Day 3 (8 Hours): Intro to Retrieval & Simple Apps
Session 1 (2 hrs): Why LLMs Need External Data
Knowledge cutoff problem
Introduction to Retrieval-Augmented Generation (RAG)
Session 2 (2 hrs): Basic Document Processing
Reading PDFs / text files
Chunking text
Simple similarity matching
Session 3 (2 hrs): Building a Basic RAG App
Query + document context
Answering from provided content only
Session 4 (2 hrs): UI & App Basics
Simple CLI or Streamlit UI
User input → LLM response flow
Day 4 (8 Hours): Capstone Project
Capstone Project (Full Day)
Project Example:
<To be discussed in the session>
Features:
Upload notes / syllabus
Ask questions
Get summaries & explanations
Quiz generation
Deliverables:
Python code
Prompt design
Demo presentation
Final output explanation
Bonus Package (Included with Course 1)
1. Interview Preparation Kit (Beginner Level)
Common GenAI interview questions (conceptual)
Python basics for AI interviews
How to explain LLMs in simple terms
Viva-style Q&A for college assessments
2. Real-Life Use Cases & Solution Blueprints
Each use case includes:
Problem statement
High-level architecture
Prompt strategy overview
3. Resume Helper Guide (Beginner)
How to list GenAI projects on resume
Beginner-friendly project descriptions
Keywords recruiters look for (entry-level)