Agentic AI Bootcamp: Build RAG AI Agents with Generative AI

What you’ll learn

Build real-world RAG (Retrieval-Augmented Generation) AI applications from scratch
Use Local LLMs (LLaMA via Ollama) — no API cost required
Work with LangChain, FAISS, and embeddings for building scalable AI systems
Design and implement vector databases for efficient information retrieval
Develop ChatGPT-like web apps using Streamlit
Implement prompt engineering techniques for better AI responses
Build industry use cases like Resume Analyzer, Chatbot, Research Assistant
Deploy and run AI applications locally for real-world usage
Build a strong portfolio with real-world AI projects
Understand how Agentic AI systems work and how to design them
Create intelligent AI assistants that can read, understand, and answer from documents
Load and process PDF, TXT, and custom data sources for AI applications
Build a complete RAG pipeline (Retriever + Generator) step-by-step
Create multi-tool Agentic AI systems with reasoning capabilities
Learn how to structure production-ready AI projects
Debug and optimize AI systems for better performance and accuracy
Gain practical skills to start a career in Generative AI & AI Engineering

Course Content

Getting Started

Introduction ▶ Preview

Getting Started on Windows, MacOS, and Linux ▶ Preview

How to ask great questions ▶ Preview

FAQ’s ▶ Preview

Introduction to Agentic AI Fundamentals

Agentic AI – Introduction 🔒

Difference AI Models vs AI Agents 🔒

Real-world examples of AI Agents (ChatGPT, AutoGPT, copilots) ▶ Preview

Agentic AI is transforming industries Real-World Use Cases 🔒

Course Roadmap and Projects overview ▶ Preview

Generative AI Basic concepts for Everyone

Generative AI - Introduction 🔒

Artificial Intelligence (AI) ▶ Preview

Machine Learning (ML) 🔒

Deep Learning (DL) 🔒

Setting up and Exploring the Power of ChatGPT

Generative AI (Gen AI) for professionals 🔒

Set up an account with ChatGPT 🔒

How to use ChatGPT Open AI as Gen AI 🔒

Environment Setup for Local Development (Hands-on)

Get and Installing Python software ▶ Preview

Installing PyCharm - the python IDE 🔒

Getting start Pycharm IDE and futures ▶ Preview

First Python Hello World program 🔒

Getting and installing Ollama (Local LLM) 🔒

Integrating the LLaMA Model into Your Project 🔒

Python Basics for AI (Quick Start)

Python Essentials for AI Projects (quick refresher) 🔒

Installing libraries (OpenAI, LangChain, etc.) 🔒

Installing libraries numpy pandas matplotlib 🔒

Creating API keys (OpenAI or alternatives) 🔒

Generative AI for Prompt Engineering – Automation

Lesson plan writer 🔒

Create a meeting planer 🔒

Learn Language Grammar corrections 🔒

Create a healthy diet chart for weight loss 🔒

Translation for languages 🔒

Create a product sale plan PPT slides 🔒

Agentic AI - Understanding LLMs (Core Engine)

What are LLMs (GPT, Claude, Gemini) 🔒

Token, prompts, and completions 🔒

Prompt Engineering basics 🔒

Zero-shot vs Few-shot prompting 🔒

Limitations of LLMs 🔒

Fundamentals of AI Agents

What makes an AI Agent “agentic 🔒

Components - Memory, Tools, Planning 🔒

Types of agents (Relative, Autonomous, Multi-agent) 🔒

Agent lifecycle 🔒

AI Agents - Use case design thinking 🔒

Understanding RAG - Retrieval Augmented Generation (Architecture)

What is RAG How RAG Works 🔒

Vector Databases FAISS 🔒

Embeddings Explained 🔒

Chunking and Text Splitting 🔒

Retriever Generator Pipelines 🔒

LangChain for Agent Development (Framework)

Introduction to LangChain 🔒

Chain vs Agents 🔒

Prompt templates 🔒

Basic First RAG AI Assistant (Local, No API) (PROJECT 1 – part1)

Create a New Project (Python) 🔒

Create new venv and Activate 🔒

Run to pull llama3 (Local LLM) 🔒

Creating Project structure 🔒

Loading Custom Data (TXT Data) 🔒

Configuring Models and DB_PATH 🔒

Install langchain, faiss and other libraries 🔒

Adding Ingestion code with import libs 🔒

Writing loader and splitter functionality 🔒

Creating Embeddings (HuggingFace) 🔒

Adding FAISS Vector Database method 🔒

Building RAG Pipeline (PROJECT 1 – part2)

Creating RAG Main System with import libs 🔒

Building RAG Pipeline 🔒

Connecting Local LLM (Ollama) 🔒

Create Prompt Templates for Better AI Outputs 🔒

Preparing RAG AI Assistant chain of execution 🔒

Run ingest to Create Vector DB 🔒

Run Your RAG AI Assistant to Test Responses 🔒

Using a RAG AI Assistant with Custom Data updates

Adding Custom Data – Payment Gateway FAQs 🔒

Updating Vector Database Using an Ingest Script 🔒

Run Your AI Assistant to Test Updated Custom Data 🔒

AI Document Assistant - Working Multiple Data Sources (PROJECT 2)

Writing ingest methods for Handling Multiple Files (TXT PDF) 🔒

Adding PDF TXT Multiple Documents on data 🔒

Updating Vector Database and pypdf package 🔒

Improving Retrieval Accuracy (update prompt template) 🔒

Run RAG AI Agent to Querying PDF or TXT Data 🔒

Advanced: Creating RAG - Agentic AI Agents adding ChatGPT-style (PROJECT 3)

Convert into Agentic AI with RAG 🔒

Creating tool and agent for Agentic AI Model 🔒

Running the Agentic AI Agent Project 🔒

Streamlit UI Installation – ChatGPT style 🔒

Create app.py file for Web interface code 🔒

Running RAG-Based Agentic AI on a Web interface 🔒

Practical AI Prompts for Real-World Projects

AI Research Assistant 🔒

AI Resume Analyzer for Human Resources (HR) 🔒

Customer Support Agent 🔒

Requirements

Basic knowledge of computers and using software
A laptop/PC with internet access (Windows/Mac)
Willingness to learn and build hands-on AI projects

Description

Are you ready to build real-world AI applications without relying on expensive APIs?

Welcome to the Agentic AI Bootcamp, where you’ll learn how to design and develop powerful AI assistants using RAG (Retrieval-Augmented Generation), Local LLMs, LangChain, and FAISS — all from scratch.

This course is designed for beginners, developers, and professionals who want to move beyond theory and start building practical, industry-ready AI solutions. Instead of just learning concepts, you’ll work on hands-on projects that simulate real business use cases in this Agentic AI Bootcamp: Build RAG AI Agents with Generative AI

You’ll discover how to create intelligent AI systems that can read documents, understand context, retrieve knowledge, and respond like ChatGPT — but running locally with zero API cost.

By the end of this course, you will confidently build:

* AI-powered document assistants (PDF & TXT)

* ChatGPT-style web apps using Streamlit

* Agentic AI systems with multiple tools

* Real-world RAG-based AI applications

No prior AI experience is required — we guide you step-by-step using simple explanations and practical coding sessions.

This course is perfect if you want to:

* Start a career in Generative AI & AI Engineering

* Build your own AI tools or startup ideas

* Add high-value AI projects to your portfolio

* Work on real-world applications instead of just theory

The future belongs to those who can build AI, not just use it.

Enroll now and start your journey into Agentic AI and real-world AI development

Who this course is for

Beginners who want to start learning Generative AI and Agentic AI from scratch
Students looking to build real-world AI projects and improve their portfolio
Python learners who want to apply their skills in AI development
Developers interested in RAG, LLMs, and AI automation systems
Professionals who want to upgrade their skills in AI and emerging technologies
Freelancers aiming to build and offer AI-based solutions to clients
Entrepreneurs who want to create AI-powered tools or startups
Anyone curious about how to build ChatGPT-like AI assistants locally

Recommended Courses

Excel with AI From Zero to Hero in Data Skills
₹499

Build REST APIs with Python, Django REST Framework: Web API
₹519

SQL Mastery with Generative AI: From Beginner to Expert
₹519

Microsoft SQL Server Bootcamp: Zero to Hero
₹496

₹596

₹10,000 94% off

This course includes:

🎥 5+ hours on-demand video
📱 Access on mobile and desktop
♾ Full lifetime access
🧠 Practical sessions
📜 Certificate of completion