Discover how to integrate external data sources into chat models with LangChain. Learn how to load, split, embed, store, and retrieve data for use in LLM applications.

Loading Documents for RAG with LangChain

Loading PDF files for RAG

Loading HTML files for RAG

Text splitting, embeddings, and vector storage

Getting started with text splitting

Recursively splitting documents

Embedding and storing documents

Building an LCEL retrieval chain

Creating the retrieval prompt

Building the retrieval chain

Building RAG Applications with LangChain

Discover state-of-the-art techniques for loading, splitting, and retrieving documents, including loading Python files, splitting semantically, and using MRR and self-query retrieval methods. Learn to evaluate your RAG architecture using robust metrics and frameworks.

Loading and splitting code files

Loading code files

Splitting Python files

Advanced splitting methods

Splitting by tokens

Splitting semantically

Optimizing document retrieval

Options

Sparse

Dense

Sparse vs. dense retrieval

Understanding BM25

Sparse retrieval with BM25

Introduction to RAG evaluation

Ragas context precision evaluation

Ragas faithfulness evaluation

String evaluation

Improving the RAG Architecture

Discover how graph databases and retrieval can overcome some of the limitations of traditional vector-based storage and retrieval.

From vectors to graphs

Creating graph documents

Getting to know graphs

Storing and querying documents

Building-up your graph database

Querying your graph database

Creating the Graph RAG chain

A journey through the Graph RAG system

Chaining, Graph RAG style!

Improving graph retrieval

Graph RAG with filtering

Validating Cypher queries

Creating a Cypher few-shot prompt

Congratulations!

Introduction to Graph RAG

RAG Academic Paper PDF

DataCamp Blog HTML

LangChain README Markdown

Chatbot Python File

RAG Workflow Python File

Large Language Models (LLMs) are being integrated into computers, phones, and software applications, but they do have one drawback: their knowledge is limited by their training data, which is slow and costly. Enter Retrieval Augmented Generation (RAG)! RAG enables you to integrate external data with LLMs. In this course, you'll learn state-of-the-art techniques for loading, processing, and retrieving external data for LLMs! You'll utilize vector databases, the latest LLMs, including GPT-4o-Mini, and the LangChain framework to create RAG applications. This course concludes with a chapter on Graph RAG, a twist on traditional RAG that uses graph databases for more reliable data retrieval.

<h2>Build RAG Systems with LangChain</h2>Retrieval Augmented Generation (RAG) is a technique used to overcome one of the main limitations of large language models (LLMs): their limited knowledge. RAG systems integrate external data from a variety of sources into LLMs. This process of connecting multiple different systems is usually tedious, but LangChain makes this a breeze!<br><br><h2>Learn State-of-the-Art Splitting and Retrieval Methods</h2>Level-up your RAG architecture! You'll learn how to load and split code files, including Python and Markdown files to ensure that splits are "aware" of code syntax. You'll split your documents using tokens instead of characters to ensure that your retrieved documents stay within your model's context window. Discover how semantic splitting can help retain context by detecting when the subject in the text shifts and splitting at these points. Finally, learn to evaluate your RAG architecture robustly with LangSmith and Ragas.<br><br><h2>Discover the Graph RAG Architecture</h2>Flip your RAG architecture on its head and discover how graph-based, rather than vector-based RAG systems can improve your system's understanding of the entities and relationships in your documents. You'll learn how to convert unstructured text data into graphs using LLMs to do the translation! Then, you'll store these graph documents in a Neo4j graph database and integrate it into a wider RAG system to complete the application.

Developing LLM Applications with LangChain

Learn cutting-edge methods for integrating external data with LLMs using Retrieval Augmented Generation (RAG) with LangChain.

Build RAG Systems with LangChain

Retrieval Augmented Generation (RAG) with LangChain

Développement d’applications avec LangChain

Splitting Python files

Retrieval Augmented Generation (RAG) with LangChain

Instructions

Exercice interactif pratique