FourthBrain Workshop

LangChain: ChatGPT for Your Data

A one-day LIVE workshop for engineers, developers, and data scientists on building a question-answering service using your own data. You’ll learn prompt engineering with LangChain, and how to use vector databases in an LLM application.

Date: Tuesday March 5th
Time: 9am-3pm PT
Cost: $500 | $1500 for teams

Register Now

With the popularity of LLM-powered applications like ChatGPT, many are eager to build similar private tools for their own data. In this workshop, we will show you how to do that using the LangChain framework.

In this workshop you will learn to use LangChain for prompt engineering, how to leverage vector databases, and how to build an index. You’ll also learn to integrate multiple documents and how to chain requests, culminating in a complete end-to-end project.

Key Outcomes

Build a prompt chain using LangChain

Use vector databases and create an index

Build a final project with multiple documents

Workshop Schedule

This workshop is hands-on and interactive. Participants are expected to come ready to build!

Overview of the LLM stack including OpenAI, ChromaDB, and LangChain
LangChain infrastructure overview
Building prompts chains
Setting up vector databases to search PDFs
Building an index with LangChain

Download the Syllabus

This workshop is for you if:

1

You want to use tools like ChatGPT for your own proprietary data

2

You are eager to build applications with LLMs and have some experience with ML modeling

3

You are a strong Python coder and have experience building basic ML models like classifiers. Experience with APIs and deployment is strongly encouraged but not required.

How to Prepare

Many employers offer reimbursement for programs like ours. Check out our tips for getting reimbursed.

Register Here

FAQs

No, each participant is responsible for their own compute resources. We will be conducting the workshop with open-source tools including Google Colab and Hugging Face. We recommend that each student purchases 100 compute units from Google Colab (approximately $10). As of April 2023, it will take about 15 compute units to do fine-tuning on roughly 100 data points with 100 training steps. You should also budget about $1 / hour of hosting your application on Hugging Face for as long as you would like it to be public.

About FourthBrain

FourthBrain's mission is to bring more people into the growing fields of Machine Learning and Artificial Intelligence through flexible education programs. We equip leaders with the skills to lead organizations towards AI maturity, and support engineers, developers, and data scientists to make an impact in this field.