Generative AI Full Course (Part 2) | Document Loaders, Text Splitters, Vector DB, RAG & LangChain

Mar 17, 2026 ยท 3h 41m 38s
Generative AI Full Course (Part 2) | Document Loaders, Text Splitters, Vector DB, RAG & LangChain
Description

In this project-based Generative AI tutorial, you will build a complete Retrieval-Augmented Generation (RAG) system from scratch using real-world concepts and tools. This is Part 2 of our Generative AI...

show more
In this project-based Generative AI tutorial, you will build a complete Retrieval-Augmented Generation (RAG) system from scratch using real-world concepts and tools.

This is Part 2 of our Generative AI series, where we move beyond fundamentals and implement a production-style AI system that can read documents and answer questions intelligently. Instead of just theory, you’ll build a working AI application step by step.

Whether you are a beginner or a developer, this video will help you understand how modern AI systems like ChatGPT work with private data using RAG architecture.

👨‍🏫 Instructor – Akarsh Vyas guiding you step-by-step through building a real-world RAG system in a simple and practical way.

📚 What You Will Learn in This Video
• What Document Loaders are and how they load PDFs into LangChain
• How Text Splitters break large documents into manageable chunks
• Understanding Embeddings and semantic meaning of text
• How Vector Databases store and retrieve information
• What Retrievers are and how they fetch relevant context
• How all components connect to form a complete RAG pipeline
• How AI systems answer questions using external knowledge

📝 Notes -
https://drive.google.com/file/d/1pRtg6YWuLPFamb6GcW4Y3s7hOdOI9FR8/view?usp=sharing

💻 Code -
https://github.com/AkarshVyas/GenAI-part2-Rag-implementation

⚡ Project You Will Build
A complete AI system that:

• Loads a PDF book
• Splits it into smaller chunks
• Converts text into embeddings
• Stores them inside a vector database
• Uses a retriever to fetch relevant data
• Sends context to an LLM for answering queries

⏱️ Timestamps -
00:00:00 - 00:01:48 - Introduction
00:01:48 - 00:17:54 - Learning & Development Plan
00:17:54 - 00:30:10 - Basic Setup
00:30:10 - 00:58:45 - Document Loaders
00:58:45 - 01:42:29 - Text Splitter
01:42:29 - 02:31:37 - Vector Stores
02:31:37 - 03:11:24 - Retrievers
03:11:24 - 03:41:24 - Completing the Project

🛠 Tech Stack Used
• Python
• LangChain
• Chroma (Vector Database)
• OpenAI Embeddings
• Mistral LLM

🌐 Connect With Sheryians -

🌐 Website - https://sheryians.com/
🔗 View Our Courses – https://www.sheryians.com/courses/68d
📷 Instagram – https://instagram.com/sheryians.ai
🎮 Discord – https://discord.gg/sheryians


Don’t forget to LIKE 👍, SUBSCRIBE 🔔 for more Generative AI projects, and COMMENT 💬 if you want more real-world AI tutorials.

generative ai rag tutorial , rag langchain project , retrieval augmented generation tutorial , langchain rag , ai project tutorial , build rag system , vector database tutorial , embeddings explained , ai with pdf chatbot , llm rag project , gen ai projects , python ai project , rag explained , langchain full course , ai development tutorial
show less
Information
Author fert
Organization fert
Website -
Tags
-

Looks like you don't have any active episode

Browse Spreaker Catalogue to discover great new content

Current

Podcast Cover

Looks like you don't have any episodes in your queue

Browse Spreaker Catalogue to discover great new content

Next Up

Episode Cover Episode Cover

It's so quiet here...

Time to discover new episodes!

Discover
Your Library
Search