Generative AI

A hands-on Generative AI course focused on building real-world AI applications, not just prompts. Learn how LLMs work, build RAG systems, create AI agents with LangGraph, integrate tools, apply guardrails, track tokens and cost, and deploy GenAI apps using FastAPI, Docker, and Kubernetes. Perfect for engineers who want production-ready GenAI skills.

About the course

This Generative AI course is a practical, engineering-focused program designed to take learners from LLM fundamentals to real-world GenAI system building. The course goes beyond prompt writing and focuses on how GenAI actually works in production environments. Participants start by understanding LLMs, transformers, embeddings, tokenization, and next-token prediction, building a strong mental model of how modern AI systems function. From there, the course moves into hands-on development, covering OpenAI APIs, tool calling, system prompts, context handling, and multi-turn conversations. A major focus of the program is Retrieval-Augmented Generation (RAG). Students learn how to ingest PDFs and structured data, perform chunking, generate embeddings, store them in vector databases, and retrieve relevant context accurately. Advanced topics such as cross-document references, metadata filtering, citation handling, and hallucination reduction are covered in depth. The course also dives into agentic workflows, where learners build AI agents using LangGraph, design node-based decision flows, integrate tools, apply guardrails (PII detection, input/output validation), and implement human-in-the-loop systems. Real-world examples include interview-prep agents, research agents, and automation workflows. Production readiness is a key theme. Students learn cost tracking, token monitoring, Prometheus/Grafana integration, API observability, and deployment patterns using Docker, FastAPI, and Kubernetes. By the end of the course, learners will have built end-to-end GenAI applications that are scalable, observable, and suitable for enterprise use cases. This course is ideal for DevOps engineers, software developers, cloud professionals, and architects who want to move beyond theory and build, deploy, and operate GenAI systems confidently.

Course details

What's included

Course content

Python Basics

  • Python Installation & Environment Setup (Anaconda / venv)
  • Variables, Data Types (str, int, float, bool, list, tuple, dict, set)
  • Basic Operators and Expressions
  • Control Flow: if-else, for, while loops
  • Functions & Return Values
  • Lab: Write a Python script to take a sentence and count words, characters, and vowels.

Working with Libraries

  • Installing and Importing Libraries (pip, conda)
  • Using Popular Libraries (numpy, pandas, matplotlib)
  • Reading Documentation & Examples
  • Lab: Install numpy and pandas, create a DataFrame from a list of dictionaries, anddisplay basic statistics.

File Handling & Data Processing

  • Reading & Writing Text Files
  • Working with CSV and JSON
  • Handling Exceptions (try-except)
  • Lab: Read a CSV file of text prompts and write the first 10 prompts to a new text file.

Introduction to Generative AI

  • What is Generative AI?
  • Use Cases of Generative AI
  • Understanding Tokenization
  • Understanding Vector Databases
  • Lab: Using a tokenizer

System Prompts for Generative AI

  • Understanding Zero Shot Prompting
  • Lab: Interacting with OpenAI using Zero Shot Prompting
  • Understanding Few Shot Prompting
  • Lab: Interacting with OpenAI using Few Shot Prompting
  • Understanding Chain-of-Thought Prompting
  • Lab: Interacting with OpenAI using CoT Prompting
  • Understanding Persona Based Prompting
  • Lab: Interacting with OpenAI using Persona Based Prompting

Combining LLMs with Custom Scripts

  • Understanding Custom Scripting for LLMs
  • Advantages & Disadvantages of Scripting with LLMs
  • Lab: Writing Scripts for LLMs
  • Lab: Connecting OpenAI to Custom Scripts

Retrieval-Augmented Generation (RAG)

  • Understanding the Need of RAG
  • Understanding RAG
  • Understanding Qdrant Vector DB
  • Understanding Langchain
  • Lab: Creating a RAG Pipeline Project
  • Lab: Deploy RAG on Kubernetes using a Microservice architecture

Retrieval-Augmented Generation in Enterprises

  • Understanding RAG issues in Scalability
  • Discussing Possible RAG Solutions in Enterprise
  • Lab: Deploying Async RAG Using a Queue Service

LangGraph for Agentic AI

  • Introduction to LangGraph
  • LangGraph vs N8N Comparsion
  • Understandings Nodes & Edges for Agentic AI
  • Lab: Creating a Simple Agentic AI
  • Lab: Creating a Multi Step Agentic AI

Advanced LangGraph for Agentic AI

  • Understanding Agentic AI Memory Issues
  • Understanding Checkpointing in Agentic AI
  • Using MongoDB for Checkpointing
  • Lab: Creating Agentic AI Workflow with MongoDB Checkpointing

Memory for Customer Facing AI

  • Understanding Contextual Limitations
  • Understanding how Recommendations Systems Work
  • Need of Memory in Customer Facing Apps
  • Lab: Deploying AI Chatbot with Neo4J

Model Context Protocol (MCP)

  • Understanding how AI Applications Communicate
  • Understanding MCP Benefits
  • Lab: Creating an MCP Server
  • Lab: Creating an MCP Client

AI Voice Agents & Enterprise Usage

  • Understanding AI Voice Usage Scenarios
  • Understanding Text-to-Speech (TTS)
  • Understanding Speech-to-Text ( STT)
  • Lab: Creating a meetings Note Taker AI Software

AI GuardRails and Cost Tracking

  • Understanding the need of GuardRails in AI Prompts
  • Lab: Creating manual Guard Rails using Regular Expressions in Python
  • Lab: Using LLM as a judge via Guard Rails Hub
  • Understanding Cost Tracking Requirements for LLM calls
  • Lab: Visualising Token Usage and Costs using Prometheus and Grafana

AI Deployments on AWS

  • Understanding AWS AI Services
  • Comparing Python RAG Deployment with AWS Bedrock
  • Lab: Deploying a RAG App on AWS using Bedrock
  • Lab: Testing AI RAG Application using AWS Console
  • Lab: Testing AI RAG Application using AWS Python SDK

Cost Optimization for Generative AI Apps

  • Understanding Caching in Generative AI
  • Understanding Direct Hit Cache Limitations
  • Lab: Deploying Redis with Generative AI For Direct Hit Cache
  • Lab: Deploying Redis and Vector Databases with Generative AI for Score Based Sematic Caching

Frequently asked questions

Is this training live or pre-recorded?
The training is live instructor led training which is available in classroom as well as online format. We also record every training session which is then uploaded to our student portal.
How will I join the live online training?
The live online training is conducted via the zoom software, we will be providing you with the zoom meeting link to join the training.
How many students are there in a single batch?
On an average one batch will have a maximum of 18 students. We keep smaller batch sizes to promote interaction between the students and the instructor.
How can I practice the labs?
We will provide you with online labs. If needed, we can also provide you with the software required to create your own labs.
Do you offer payment flexibility?
Yes, we provide zero interest EMI options.
Can I attend the training in classroom?
Yes, our classroom training location is in New Delhi near Lajpat Nagar metro staton.