Course overview
This professional programme is designed for students, freshers, working professionals, and developers who want to understand Generative AI and create practical AI-powered applications. It progresses from Python, AI, machine learning, and NLP fundamentals to LLM applications, RAG, agents, and deployment.
LevelBeginner to advanced
Duration3–4 months
Learning modeOnline or offline
Programming languagePython
ForStudents, developers, and professionals
Final outcomeBuild and deploy AI-powered applications
Complete course syllabus
Explore the modules and the practical work included in the programme.
Module 1: Introduction to Artificial Intelligence
- What is Artificial Intelligence?
- History and evolution of AI
- Types of Artificial Intelligence
- AI vs. Machine Learning
- Machine Learning vs. Deep Learning
- What is Generative AI?
- Traditional AI vs. Generative AI
- Real-world applications of Generative AI
- Advantages and limitations of AI
Practical: Explore popular AI tools and their applications.
Module 2: Python Programming for Generative AI
- Python fundamentals, variables, and data types
- Conditional statements, loops, and functions
- Lists, tuples, sets, and dictionaries
- File handling and exception handling
- Object-oriented programming
- Modules, packages, and virtual environments
- Working with APIs
- NumPy and Pandas basics
Practical: Build a Python-based chatbot and API integration program.
Module 3: Machine Learning & Deep Learning Fundamentals
- Introduction to Machine Learning
- Supervised, unsupervised, and reinforcement learning
- Training and testing datasets
- Data preprocessing
- Neural networks and deep learning
- Activation functions
- Model training and evaluation
- Introduction to TensorFlow and PyTorch
Practical: Build a basic machine learning prediction model.
Module 4: Natural Language Processing (NLP)
- Introduction to NLP and text preprocessing
- Tokenization
- Stemming and lemmatization
- Stop words
- Word embeddings and TF-IDF
- Semantic similarity
- Introduction to Transformers
- Attention mechanism
Practical: Create a text classification and sentiment analysis application.
Module 5: Large Language Models (LLMs)
- What is an LLM and how LLMs work
- GPT and Transformer architecture overview
- Tokens and tokenization
- Context windows
- Temperature and Top-P
- Hallucinations in AI
- Fine-tuning fundamentals
- Open-source vs. closed-source LLMs
- Introduction to GPT, Gemini, Claude, and Llama
Practical: Build a basic LLM-powered chatbot.
Module 6: Prompt Engineering
- Introduction to Prompt Engineering
- Zero-shot, one-shot, and few-shot prompting
- Role-based prompting
- Chain-of-thought prompting
- Context-based prompting
- System and user prompts
- Structured output (JSON)
- Prompt optimization, testing, and evaluation
Practical: Create prompts for content writing, coding, data analysis, and customer support.
Module 7: Generative AI Tools & Applications
- ChatGPT, Google Gemini, Claude, Microsoft Copilot, and Perplexity AI
- Canva AI
- AI image generation
- AI video generation
- AI presentation generation
- AI voice and audio generation
- AI coding assistants
Practical: Generate text, images, presentations, videos, and marketing content using AI tools.
Module 8: Working with LLM APIs
- Introduction to APIs
- API keys and authentication
- OpenAI API and Gemini API integration
- Sending prompts through APIs
- Receiving and processing responses
- Streaming responses
- Conversation history and chat completion
- Error handling and rate limits
Practical: Create an AI chatbot using Python and an LLM API.
Module 9: LangChain Framework
- Introduction to LangChain and its architecture
- Models and chat models
- Prompt templates
- Output parsers
- Chains
- Memory management
- Document loaders and text splitters
- Retrievers
- Tools and agents
Practical: Build a chatbot using LangChain.
Module 10: Embeddings & Vector Databases
- Embeddings and text embeddings
- Semantic search
- Vector similarity and cosine similarity
- Introduction to vector databases
- ChromaDB, FAISS, and Pinecone
- Vector storage and retrieval
Practical: Build a semantic search application.
Module 11: Retrieval-Augmented Generation (RAG)
- Introduction to RAG and why it is required
- RAG architecture
- Document ingestion and chunking
- Embedding generation
- Vector database integration
- Retrieval techniques and context retrieval
- Answer generation
- RAG evaluation
Practical: Build a PDF question-answering chatbot.
Module 12: Fine-Tuning & Model Customization
- Introduction to fine-tuning
- Prompt Engineering vs. fine-tuning
- Preparing and formatting training datasets
- Model customization and transfer learning
- LoRA and QLoRA
- Hugging Face basics
- Model evaluation
Practical: Customize an open-source language model using a suitable fine-tuning workflow.
Module 13: AI Agents & Agentic AI
- Introduction to AI agents
- Generative AI vs. Agentic AI
- Agent architecture
- Planning and reasoning
- Tool calling and function calling
- Short-term and long-term memory
- Multi-agent systems
- Workflow automation and human-in-the-loop
- Introduction to LangGraph
- Agent evaluation and safety
Practical: Build an AI research agent and an automated email assistant.
Module 14: Generative AI Full Stack Development
- AI application architecture
- Python with FastAPI
- React.js frontend integration
- Node.js integration concepts
- MongoDB database integration
- Authentication and authorization
- Connecting LLM APIs
- Chat history management
- File uploads and document processing
- Streaming AI responses
- Deployment, hosting, and AI application security
Practical: Develop and deploy a complete AI-powered web application.
Module 15: Deployment & Real-World Projects
- Deploying AI applications
- Cloud hosting fundamentals
- Environment variables and API security
- Docker basics
- Git and GitHub
- Performance optimization
- Monitoring and logging
- Cost optimization
- Responsible AI
- Data privacy and security
Live projects
Apply your learning through guided projects from beginner to advanced levels.
Project 1: AI Chatbot
Create a chatbot using Python, React.js, and an LLM API.
Beginner
Project 2: PDF AI Assistant
Upload PDF documents and ask questions using RAG technology.
Intermediate
Project 3: AI Image Generator
Generate images from text prompts using image generation APIs.
Intermediate
Project 4: AI Research Agent
Build an AI agent that searches, collects, and summarizes information.
Advanced
Project 5: AI Customer Support System
Create an AI-powered customer support platform with chat history, document knowledge, and automated responses.
Advanced