Beginner1h48m

LangChain for LLM Application Development

Instructors: Harrison Chase, Andrew Ng

LangChain 🦜🔗

Earn an accomplishment with PRO · Updated Oct 14, 2025

Enroll for Free

Beginner
1h48m
8 Video Lessons
6 Code Examples
1 Graded Assignment PRO
Earn an accomplishment with PRO
Updated Oct 14, 2025
Instructors: Harrison Chase, Andrew Ng
LangChain 🦜🔗
Learn more aboutMembership PRO Plan

Enroll for Free

What you'll learn

Learn LangChain directly from the creator of the framework, Harrison Chase
Apply LLMs to your proprietary data to build personal assistants and specialized chatbots
Use agents, chained calls, and memories to expand your use of LLMs

Course recap

PRO

This foundational course teaches LangChain, the open-source framework for building LLM applications, covering its core abstractions: models, prompts, parsers, memory, chains, question answering over documents, evaluation, and agents. Taught by Harrison Chase (LangChain creator) alongside Andrew Ng, it demonstrates how LangChain's composable components enable rapid development of applications that would otherwise require extensive glue code.

Concept map

Key concepts

Prompt EngineeringReusable prompt templates with variables, output format specifications, and built-in templates for common tasks
EmbeddingsNumerical vector representations of text that capture semantic meaning, used to find relevant document chunks
Retrieval-Augmented GenerationRetrieval-augmented generation: combining vector similarity search with LLM generation for document QA
AI AgentsLLMs used as reasoning engines that decide which tools to call, using strategies like ReAct prompting
MemoryMechanisms for maintaining conversation context: buffer, window, token-limited, and summary memory types

Lesson highlights

1.Introduction — Overview of LangChain's composition and modularity philosophy
2.Models, Prompts and Parsers — Chat models, prompt templates, and structured output parsing into Python dictionaries
3.Memory — ConversationBufferMemory, BufferWindowMemory, TokenBufferMemory, and ConversationSummaryBufferMemory
4.Chains — LLMChain, SimpleSequentialChain, SequentialChain, and RouterChain for routing between specialized prompts
5.Question and Answer — Document QA with embeddings, vector stores, and retrieval QA chains (stuff, map_reduce, refine, map_rerank)
6.Evaluation — QA generation chains, langchain.debug, LLM-based grading, and the LangChain evaluation platform
7.Agents — DuckDuckGo search and Wikipedia tools, CHAT_ZERO_SHOT_REACT_DESCRIPTION agent type, and custom tool creation
8.Conclusion — Summary and encouragement to build applications with LangChain

About this course

In LangChain for LLM Application Development, you will gain essential skills in expanding the use cases and capabilities of language models in application development using the LangChain framework.

In this course you will learn and get experience with the following topics:

Models, Prompts and Parsers: calling LLMs, providing prompts and parsing the response
Memories for LLMs: memories to store conversations and manage limited context space
Chains: creating sequences of operations
Question Answering over Documents: apply LLMs to your proprietary data and use case requirements
Agents: explore the powerful emerging development of LLM as reasoning agents.

This one-hour course, instructed by the creator of LangChain Harrison Chase as well as Andrew Ng will vastly expand the possibilities for leveraging powerful language models, where you can now create incredibly robust applications in a matter of hours.