Advanced LangChain Techniques: Mastering RAG Applications

Name: Advanced LangChain Techniques: Mastering RAG Applications
Rating: 4.4 (322 reviews)

Elevate Your RAG Applications to the Next Level

Created byMarkus Lang

Last updated 1/2026

English

What you'll learn

Learn LangChain Expression Language (LCEL)
Master advanced RAG techniques using the LangChain framework
Evaluate RAG pipelines using the RAGAS framework
Apply NeMo Guardrails for safe and reliable AI interactions

Course content

15 sections • 39 lectures • 3h 40m total length

How to get started1:21
Why should you take THIS course?1:13
Requirements for this course1:18
Prepare by meeting prerequisites in intermediate Python, Docker, SQL, and OpenAI access, and gain basics of terminals, vector databases, and translating natural language to SQL.
IMPORTANT! - Quick note about the installation of the packages1:03
Clone the repository and set up the virtual environment4:28
Clone the GitHub repository, create a virtual environment, install dependencies from requirements.txt, and configure env with your OpenAI key to run notebooks in VS Code.
Repository Walkthrough3:21
Walk through the repository structure from the app folder to back ends and Postgres, learn to configure the OpenAI key, and review data, notebooks, and Rag pipelines.
Full Stack App Walkthrough7:55
Why NOT to take this course1:09
2026 Course Revision – Core Content (LangChain 1.0.x)2:18

LCEL - The Runnable Interface3:56
Explore how LangChain implements a runnable interface to pipe a prompt, a model, and an output parser, building a chain with a topic and invoke method that yields a joke.
Building Our Own Small Version of LCEL4:16
Build a small lang chain style expression language by overloading the pipe operator to chain runnables, using an abstract base class with invoke and process methods.
The most important Runnables of LangChain9:15
LCEL - Real World Examples9:21
Explore real world examples of retrieval augmented generation using a chat prompt template, a vector store, embeddings, and a RAC workflow.
LCEL - Pipelines with Chat History8:17

Creating an AI Augmented Testset (RAGAS 0.1.x)5:21
Introduce ragas, a framework for evaluating retrieval augmented generation with metrics like faithfulness and answer relevancy, then build a test set using LangChain with embeddings and a chat model.
Evaluating RAG Performance with an LLM (RAGAS 0.1.x)8:13
Migration from v0.1 to v0.2 (most important changes)5:47
Migrate from v1 to v2 by wrapping the Chadami and embeddings models with the length change wrapper and length chain embeddings wrapper, using the default query distribution.

Requirements

LangChain Basics
Intermediate Python Skills (OOP, Datatypes, Functions, modules etc.)
Basic Terminal and Docker knowledge

Description

What to Expect from This Course

Welcome to our course on Advanced Retrieval-Augmented Generation (RAG) with the LangChain Framework!

In this course, we dive into advanced techniques for Retrieval-Augmented Generation, leveraging the powerful LangChain framework to enhance your AI-powered language tasks. LangChain is an open-source tool that connects large language models (LLMs) with other components, making it an essential resource for developers and data scientists working with AI.

Course Highlights

Focus on RAG Techniques: This course provides a deep understanding of Retrieval-Augmented Generation, guiding you through the intricacies of the LangChain framework. We cover a range of topics from basic concepts to advanced implementations, ensuring you gain comprehensive knowledge.

Comprehensive Content: The course is designed for developers, software engineers, and data scientists with some experience in the world of LLMs and LangChain. Throughout the course, you'll explore:

LCEL Deepdive and Runnables
Chat with History
Indexing API
RAG Evaluation Tools
Advanced Chunking Techniques
Other Embedding Models
Query Formulation and Retrieval
Cross-Encoder Reranking
Routing
Agents
Tool Calling
NeMo Guardrails
Langfuse Integration

Additional Resources

Helper Scripts: Scripts for data ingestion, inspection, and cleanup to streamline your workflow.
Full-Stack App and Docker: A comprehensive chatbot application with a React frontend and FastAPI backend, complete with Docker support for easy setup and deployment.
Additional resources are available to support your learning.

Happy Learning! :-)

Who this course is for:

Software Engineers and Data Scientists with Experience in Langchain who want to bring RAG applications to the next level

Advanced LangChain Techniques: Mastering RAG Applications

What you'll learn

Explore related topics

Course content

Before we start...9 lectures • 24min

LangChain Expression Language (LCEL): A Deep Dive5 lectures • 35min

Indexing API1 lecture • 12min

RAGAS - Framework for Evaluating RAG Performance3 lectures • 19min

Chunking Techniques1 lecture • 9min

Embedding models1 lecture • 6min

Improving queries for better retrieval2 lectures • 8min

Parent Document Retriever - Two-Stage-Retrieval2 lectures • 17min

Agentic RAG1 lecture • 4min

Retrieval - Postprocessing Documents2 lectures • 14min

Requirements

Description

Who this course is for: