RAG Basics

After this skill you can…

• Chunk documents with LangChain or LlamaIndex
• Generate embeddings and store in a vector DB
• Build a Q&A app over your own data

Prerequisites

Watch (10 videos)

High Performance (Realtime) RAG Chains: From Basic to Advanced

Rabbitmetrics · beginner hands-on

→ Build a RAG pipeline with LangChain→ Optimize RAG systems for real-time performance

Coding the Ultimate RAG Engine from Zero

ClearTheAI · intermediate hands-on

→ Build a RAG engine from scratch→ Implement vector databases for information retrieval

Building Agentic RAG From Scratch in Pure Python

Dave Ebbelaar · beginner hands-on

→ Build an Agentic RAG pipeline→ Implement semantic search in Python

RAG Demo for Beginners: Full Hands-On Tutorial in Tamil | Build Your Own RAG AI | Karthik's Show

Karthik's Show · beginner hands-on

→ Build a RAG pipeline from scratch→ Implement retrieval-augmented generation with FAISS and Sentence Transformers

RAG with LangChain on Google Cloud

Google Cloud Tech · intermediate hands-on

→ Implement RAG with LangChain on Google Cloud→ Build a web application with Retrieval-Augmented Generation

Build an End-to-End RAG API with AWS Bedrock & Azure OpenAI

AI Anytime · intermediate hands-on

→ Build a RAG tool→ Implement a vector database→ Integrate a language model

Chat With Your Documents Data Ingestion & RAG Pipeline(Beginner Friendly)

ChethanAIChronicles · beginner hands-on

→ Build a RAG pipeline for data ingestion→ Integrate chatbot with RAG pipeline

RAG from scratch: Part 6 (Query Translation -- RAG Fusion)

LangChain · advanced hands-on

→ Build a RAG pipeline from scratch→ Implement query translation and RAG fusion

NLP JumpStart | The Power of Multilingual Semantic Search

Cohere · intermediate hands-on

→ Build a multilingual semantic search solution→ Implement Cohere and Pinecone

Build a RAG Application from Scratch — No LangChain, No LlamaIndex

Muhammad Moin · intermediate hands-on

→ Build a RAG pipeline→ Store embeddings in ChromaDB

Read (10 articles)