Full Stack Agentic AI and RAG & Generative AI with Python

Name: Full Stack Agentic AI and RAG & Generative AI with Python
Rating: 4.3 (53 reviews)

Master Agentic AI, Generative AI, Agents, RAG, Vector DBs, Hugging face, LLMs with LangGraph and LangChain

Created byDurga Prasad Chodavarapu

Last updated 8/2026

English

What you'll learn

Learn to build intelligent AI agents and full-stack applications using Python, modern AI frameworks, APIs, and web technologies.
Understand Retrieval-Augmented Generation (RAG), embeddings, vector databases, document processing, and semantic search to create knowledge-aware AI systems.
Work with LLMs, prompt engineering, AI APIs, and Python libraries to create practical generative AI applications and automation workflows.
Integrate Agentic AI, RAG, Generative AI, databases, and full-stack components to develop production-oriented intelligent applications from end to end.

Course content

80 sections • 404 lectures • 102h 1m total length

Introduction5:30
Begin your Terraform journey from scratch, progress through sequential sections, and learn AWS hardening guidelines historically implemented manually before codifying them in Terraform for exam readiness.

Getting Started With VS Code10:36
Explore infrastructure as code with Terraform, compare it to configuration management tools, and learn how Terraform orchestrates infrastructure across multi-clouds with Ansible integration, plugins, and free usage.
Python Basics-Syntax And Semantics20:17
Explore Terraform state management and use state subcommands—list, move, pull, push, remove, and show—to safely modify remote state without direct file edits.
Variables In Python18:55
Basics DataTypes In Python9:52
Operators In Python16:16

Conditional Statements in Python21:03
Explore Terraform provider configuration to deploy resources across multiple regions and accounts by using provider aliases, configuring per-resource provider blocks, and scaling elastic IP deployments.
Loops In Python28:02
Learn to enable team collaboration on Terraform code and tf state files by adopting centralized Git workflows, pushing and pulling from a shared repository, and using Bitbucket for demos.

Lists In Python37:07
launch your first ec2 instance with terraform by configuring the aws provider, authenticating with static credentials, selecting an ami and t2.micro size, then init, plan, and apply.
Tuples In Python22:34
Explore how the Terraform provider acts as the middleman between Terraform code and a service provider, handling authentication and API calls for AWS and DigitalOcean, and why version pinning matters.
Dictionaries In Python38:18
Real World Use cases Of List9:50

Getting Started With Functions24:21
Explore how to configure a DigitalOcean provider in Terraform and create a droplet with token authentication, specifying image, region, and size.
More Coding Examples With Functions28:03
Explore how to enable team collaboration in terraform by centralizing code and tf state in a git repository, using Bitbucket for central management and cross-platform git setup.
Lambda Function In Python9:44
Map Function In Python11:08
Filter Functions In Python9:00

Import Modules And Packages In Python17:06
Explore how Terraform providers manage API interactions and resources across cloud platforms, using versions, aliases, modules and the registry, with init, plan, apply, refresh, destroy, fmt, validate, and provisioners.
Standard Libraries Overview In Python17:44
Enable terraform debugging with tf_log and tf_log_path, and note that import updates state only, while root and child modules, workspaces, module sources, and data types shape configurations.

Classes And Objects In Python22:55
Single And Multiple Inheritance19:00
Polymorphism In OOPS19:08
Encapulation In OOPS22:12
Abstraction In OOPS9:08
Magic Methods In Python8:03
Operator Overloading In Python8:31
Custom Exception Handling7:05
Iterators In Python6:25
Generators In Python11:06
Fucntion Copy.Closures and Decorators21:15
Numpy In Python28:16
Pandas-DataFrame And Series29:09
Data Manipulation With Pandas And Numpy24:38
Reading Data From Various Data Source Using Pandas15:04
Logging Practical Implementation In Python14:37
Logging With Multiple Loggers4:40
Logging With A Real World Examples7:43
Introduction To Pydantic14:07
Pydantic Practical Implementation21:38

Getting Started With Langchain And Open AI11:08
Creating Virtual Environment7:12
Important Components Of LangChain13:09
Data Ingestion With Documents Loaders22:43
Recursive Character Text Splitter12:56
Character Text Splitter With Langchain3:53
HTML Header Text Splitter7:01
Recursive Json Text Splitter6:48
Introduction To OPENAI Embeddings22:20
Ollama Embeddings15:43
HuggingFace Embeddings10:20
Vector Stores-FAISS16:34
Vector Store And Retriever- Chroma DB9:32

Requirements

You must have a passion for learning Agentic AI, Generative AI and RAG

Description

Full Stack Agentic AI and RAG & Generative AI with Python is a comprehensive, hands-on online course designed for developers, AI enthusiasts, and professionals who want to build modern AI-powered applications from end to end. This course combines Python programming, Generative AI, Retrieval-Augmented Generation (RAG), Agentic AI, LLMs, APIs, databases, and full-stack development into one practical learning experience.

You will learn how to build intelligent AI applications that can understand user requests, retrieve relevant information, use external tools, maintain context, and perform multi-step tasks autonomously. The course covers the fundamentals of Large Language Models and Generative AI before progressing into advanced concepts such as prompt engineering, embeddings, vector databases, document processing, semantic search, RAG pipelines, AI agents, tool calling, memory, workflows, and multi-agent systems.

Using Python, you will develop real-world AI solutions and connect them with modern frontend and backend technologies to create complete full-stack applications. You will learn how to integrate LLM APIs, build RAG-based chatbots, create AI assistants, process documents, develop intelligent search applications, and design autonomous agent workflows.

The course also focuses on practical development, helping you understand how different components work together in production-ready AI systems. You will gain experience working with APIs, databases, vector stores, authentication, application deployment, and AI application architecture.

By the end of this course, you will have the knowledge and practical skills to design, develop, and deploy full-stack Agentic AI, RAG, and Generative AI applications using Python. Whether you are a Python developer, software engineer, AI/ML learner, or aspiring Generative AI developer, this course provides a structured path from fundamentals to advanced AI application development.

Who this course is for:

It is for those who want to master Agentic AI, Generative AI and RAG

Full Stack Agentic AI and RAG & Generative AI with Python

What you'll learn

Explore related topics

Course content

Introduction1 lecture • 6min

Basics of Python for Agentic AI and Generative AI5 lectures • 1hr 16min

Python Control Flow for Agentic AI and Generative AI2 lectures • 49min

Data Structures Using Python for Agentic AI and Generative AI4 lectures • 1hr 48min

Functions In Python for Agentic AI and Generative AI5 lectures • 1hr 22min

Importing, Creating Modules in Python for Agentic AI and Generative AI2 lectures • 35min

File Handling In Python for Agentic AI and Generative AI3 lectures • 51min

OOPS Classes And Objects for Agentic AI and Generative AI20 lectures • 5hr 15min

Langchain Hands On13 lectures • 2hr 39min

Getting Started With OpenAI And Ollama6 lectures • 1hr 21min

Requirements

Description

Who this course is for: