What you'll learn

Learn directly from LangChain creator, Harrison Chase
Access over 80 unique loaders to handle accessing various data sources using LangChain
Build your own chatbot to chat directly with information from your own documents and data

Course recap

PRO

This course provides a deep dive into building RAG applications with LangChain, covering the complete pipeline from document loading through splitting, embedding, retrieval, and conversational question answering. It demonstrates over 80 document loaders, advanced text splitting strategies, multiple retrieval techniques, and how to build a chatbot that maintains conversation context while answering questions grounded in your documents.

Concept map

Key concepts

RagComplete retrieval-augmented generation pipeline from document ingestion to conversational QA
ChunkingText splitting strategies using recursive character splitting, with careful attention to chunk size, overlap, and metadata preservation
EmbeddingsOpenAI embeddings for semantic similarity search across document chunks
Vector storesChroma vector database for persistent storage and retrieval of embedded document chunks

Lesson highlights

1.**Document Loading** — 80+ document loaders for PDFs, YouTube (via Whisper), web pages, and Notion databases
2.**Document Splitting** — Recursive character splitting, token-based splitting, markdown/code-aware splitting, and metadata handling
3.**Vectorstores and Embeddings** — Creating Chroma vector stores, OpenAI embeddings, and similarity/MMR search
4.**Retrieval** — Advanced retrieval techniques: MMR, self-query, compression, and contextual compression
5.**Question Answering** — RetrievalQA chain types (stuff, map_reduce, refine) and prompt customization
6.**Chat** — ConversationalRetrievalChain with chat history, follow-up questions, and memory management
7.**Conclusion** — Summary of the full RAG pipeline
8.**Introduction** — Course overview and motivation for chatting with your data

About this course

Join our new short course, LangChain: Chat With Your Data! The course delves into two main topics: (1) Retrieval Augmented Generation (RAG), a common LLM application that retrieves contextual documents from an external dataset, and (2) a guide to building a chatbot that responds to queries based on the content of your documents, rather than the information it has learned in training.

You’ll learn about:

Document Loading: Learn the fundamentals of data loading and discover over 80 unique loaders LangChain provides to access diverse data sources, including audio and video.
Document Splitting: Discover the best practices and considerations for splitting data.
Vector stores and embeddings: Dive into the concept of embeddings and explore vector store integrations within LangChain.
Retrieval: Grasp advanced techniques for accessing and indexing data in the vector store, enabling you to retrieve the most relevant information beyond semantic queries.
Question Answering: Build a one-pass question-answering solution.
Chat: Learn how to track and select pertinent information from conversations and data sources, as you build your own chatbot using LangChain.

Start building practical applications that allow you to interact with data using LangChain and LLMs.

Who should join?

Developers familiar with Python who are interested in developing applications using Large Language Models like ChatGPT

LangChain Chat with your data

What you'll learn

Course recap

Concept map

Key concepts

Lesson highlights

About this course

Who should join?

Course Outline

Elevate your learning experience with Pro

Instructor

Harrison Chase

LangChain Chat with your data

Want to learn more about Generative AI?