Video course · 15 chapters · 153 min · certificate
Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer
Lance Martin (LangChain) teaches RAG from scratch: indexing, retrieval and generation, query translation (multi-query, RAG Fusion, decomposition, step-back, HyDE), routing, query construction, advanced indexing (multi-representation, RAPTOR, ColBERT), corrective and adaptive RAG with LangGraph, and the future of RAG with long context.
What you'll learn
- Build a basic RAG pipeline: index, retrieve, generate
- Improve retrieval with query translation techniques
- Route questions and construct structured queries
- Use advanced indexing like multi-representation, RAPTOR and ColBERT
- Build corrective and adaptive RAG flows with LangGraph
- Judge how RAG changes with long-context models
Chapters
15 chapters · 153:11-
5:53
01Intro Members
Overview
The RAG map.
-
9:59
02Index Members
Indexing and retrieval
Embed and search.
-
6:22
03Generate Members
Generation
Answer with context.
-
6:06
04Query translation Members
Multi-query
Many perspectives.
-
5:37
05Fusion Members
RAG Fusion
Rank the results.
-
6:34
06Decompose Members
Decomposition
Break it down.
-
11:36
07Abstraction Members
Step-back and HyDE
Higher-level and hypothetical.
-
7:01
08Routing Members
Routing
Right source.
-
5:57
09Structured Members
Query construction
Natural language to filters.
-
6:34
10Indexing Members
Multi-representation indexing
Summaries point to docs.
-
7:40
11RAPTOR Members
RAPTOR
Hierarchical summaries.
-
7:13
12ColBERT Members
ColBERT
Token-level matching.
-
17:37
13CRAG Members
Corrective RAG (CRAG)
Grade and fix.
-
27:53
14Adaptive Members
Adaptive RAG
Route and self-check.
-
21:09
15Future Members
The future of RAG
Is RAG dead?
Jobs this course suits
Our AI checked this course against 500 jobs; these get the most out of it. Each job links to its learning path.