Gen AI Course
in Chennai

Gen AI Path

Comprehensive Gen AI curriculum: LLMs, prompt engineering, RAG systems, fine-tuning, and building intelligent AI applications with hands-on projects

Installing Python, VS Code, Jupyter Notebook (Setup, Fundamentals)

Install Python, VS Code, Jupyter; virtual environments (venv/conda); Hello World program; variables, data types, and operators.

Control Flow Statements ( Conditionals , Loops)

Conditionals (if/else/match), loops (for, while), and string manipulation for program control and iteration.

Functions in Python (Functions, Recursion)

Defining and calling functions, arguments, return values, default and keyword arguments, lambda functions, and recursion techniques.

Data Structures (Collections, Comprehensions)

Lists, tuples, sets, dictionaries with indexing, slicing, operations, comprehensions; practice with student grades manager and word frequency counter.

File Handling (I/O Operations, Formats)

Reading and writing text files, working with CSV and JSON files, with open() usage, and logging basics for applications.

Exceptions (Error Handling, Robustness)

Try/except/finally for error handling, else cases in exceptions, and raising exceptions for robust, fault-tolerant code.

Python Libraries & APIs (Package Management, REST APIs)

Installing packages with pip, using requests library, REST API basics, calling public APIs (weather, crypto), parsing JSON, and API error handling.

Foundation of LLM (Large Language Models, Training Concepts)

What is a Large Language Model, how LLMs are trained (tokens, datasets, parameters), capabilities (generation, summarization, translation, reasoning), limitations (bias, hallucinations, context length).

Generative AI Concepts (AI Evolution, Transformers)

Difference between traditional AI and Generative AI, transformer architecture and attention mechanisms, common LLM tasks, token understanding, LLM strengths and weaknesses

Getting Started with OpenAI API (OpenAI Setup, Authentication)

Setting up OpenAI account, generating and securing API keys with .env file, installing openai Python library, and making first API calls.

Prompt Engineering (Techniques, Best Practices)

What is prompt engineering, rules of effective prompting, zero-shot and few-shot prompting, priming, context setting, tone, persona, avoiding hallucinations, formatting outputs, common pitfalls.

Advanced Prompts with Python (Dynamic Generation, Automation)

Using variables in prompts, f-strings and .format() methods, batch prompt generation, and building flexible, reusable prompt systems with Python.

Prompt Templates (Reusability, Modularity)

Reusable templates with Python dictionaries, modularity in prompt design, and prompt chaining basics for complex workflows and multi-step processes.

Chain-of-Thought Prompting (Reasoning Steps, Accuracy Improvement)

Breaking down reasoning into steps, chain-of-thought prompting vs direct prompts, improving model accuracy through step-by-step logic and intermediate reasoning.

Retrieval-Augmented Generation (RAG) (Context Extension, Vector Databases)

Why RAG matters, overcoming model memory limits, vector databases (ChromaDB, FAISS), embeddings, document search, and building knowledge bases for AI systems.

Working with JSON Outputs (Structured Data, Parsing & Validation)

Getting structured responses from LLMs, parsing and validating JSON outputs, and handling errors with malformed or unexpected responses.

Capstone Project: Building a Chatbot (Project, Deployment)

Chatbot architecture overview, single-turn chatbot with GPT, adding session-based memory, conversation history management, and deploying a functional chatbot application.