LangChain for JavaScript developers
LangChain for JavaScript developers
How to integrate LLMs into Javascript web apps
About the Book
LangChain for JavaScript developers is a practical beginner’s workshop for integrating LLMs into JS applications.
Learn by building 5 real LLM-powered apps with LangChain, Next.js, and React.
📘 Preview first 25 pages for free
The AI Engineer, responsible for integrating AI features into traditional software applications, will be one of the most in-demand roles in the coming years. In fact, there is a high chance that AI Engineers will outnumber ML Engineers in the near future.
LangChain is a perfect gateway to starting your AI Engineering journey. LangChain serves as the orchestrator that connects nearly everything in the AI-Webapp integration system. Starting from this point, you can gain a good understanding of how all the components work together.
Not yet ready to buy? Let's keep in touch 🤜🤛.
I’ve been doing JavaScript for almost 20 years, and this book emerged from my struggle to reconcile the undeniable wave of AI Technologies with classic web development. You can read the full story here.
In this short course, we take a fun, hands-on, and pragmatic approach to learning how to build LLM-powered apps using LangChain. We will build the following five examples using LangChain, Next.js, and React:
- 🦄 The Story Maker
- 🍵 Tea Wikipedia app
- 🧭 Geography Trivia game
- 🗄 Documents Researcher app
- 🕵️♂️ AI Agent chatbot
The goal of this course is to teach you LangChain development in a manageable way without overwhelming you. Some of the topics we will cover include:
- models and prompt templates
- output parsers,
- streaming data
- conversation memory
- agents & tools
- RAG - Retrieval Augmented Generation
- debugging responses and more.
📘 See the full table of contents
Recent Changes
- 01 aug 2024: both code samples and the content are updated to use LCEL (LangChain Expression Language) & removed all the code references to ChatGPT 3.5
- 19 may 2024: I've updated all the code to use the .invoke() method for chains instead of .call(). The .call() method will be deprecated in the future versions of LangChain.
Not yet ready to buy? Let's keep in touch 🤜🤛.
What prerequisites do I need to have before taking this course?
The examples are using Next.js and React. You don't need to be an expert but you will need a very basic understanding of how React works.
Is the learning material up-to-date?
LangChain is currently undergoing rapid development. Technical books often become outdated soon after release, but since this book is self-published, I can update it as needed. I aim to provide monthly updates.
What if I don't like it? Can I get a refund?
I'm sorry to hear that you're not happy with the book! Yes, you can do a refund request within 60 days of purchase and I will fully refund you the price. While not mandatory, I would appreciate it if you could provide the reason for the refund so I can improve the book.
Do you support Purchasing Power Parity or student discounts?
If you live in a country with low purchasing power, or you are a student mail me with your details and some proof (student ID, etc.) and I'll organize a special discount for you.
About the Author
Table of Contents
-
-
Introduction
- About the author
- How this book came to be
- What is LangChain
- Overview of this book
- Requirements and how to use this book
-
Models, Prompts and Chains
- Introduction
- Getting Started
- The API key for the OpenAI ChatGPT model
- Using the ChatOpenAI LangChain model
- Prompt templates
- Chains
-
Introduction
- Introduction and project setup
- Project refactor
- Streaming the response
-
Output parsers
- Introduction
- Example setup
- StringOutputParser
- CommaSeparatedListOutputParser
- The getFormatInstructions() method and custom parsers
- StructuredOutputParser
-
Chat memory
- Introduction and project setup
- Injecting messages into the conversation memory
- Full conversation history
-
RAG / Chating with documents
- Introduction
- Example setup
- Using local documents
- Components of the RAG process
- Vectors, Embeddings and Vector databases
- Using CheerioWebBaseLoader and MemoryVectorStore
-
AI Agents
- Introduction and project setup
- Making an agent
- Monitoring agents and performance considerations
- Recap
- Final Words
-
Introduction
The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
Now, this is technically risky for us, since you'll have the book or course files either way. But we're so confident in our products and services, and in our authors and readers, that we're happy to offer a full money back guarantee for everything we sell.
You can only find out how good something is by trying it, and because of our 100% money back guarantee there's literally no risk to do so!
So, there's no reason not to click the Add to Cart button, is there?
See full terms...
Earn $8 on a $10 Purchase, and $16 on a $20 Purchase
We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
In fact, authors have earnedover $14 millionwriting, publishing and selling on Leanpub.
Learn more about writing on Leanpub
Free Updates. DRM Free.
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
