CF

Build an LLM-powered Q&A App using LangChain, OpenAI and Python

2h 38m 22s
English
Paid

Project Overview

LLMs like GPT are exceptional at answering questions based on the data they’ve been trained on. But what if you need to inquire about information not included in their training set? For instance, asking about data from after their training cut-off date or querying non-public documents? This project will guide you on how to input extensive information, like books and documents, into the model to answer those questions. We will teach you this process from scratch!

In this project, you’ll learn to build cutting-edge LLM-powered apps using LangChain, Pinecone, OpenAI, and Python. Join us as we build together, step-by-step, line-by-line, in this learning-by-doing experience.

Why This Project Stands Out

This is a portfolio project designed to enrich your skill set. You will learn LangChain and build a Q&A application in about 3 hours.

LangChain is an open-source framework that simplifies working with AI by combining large language models (LLMs) like GPT-4 with external computation and data sources. It facilitates the creation and deployment of AI applications that are both scalable and performant. Whether you have a technical or non-technical background, LangChain provides an excellent entry point into the AI domain and supports deploying AI as a service. The practical applications are virtually limitless.

About the Author: Zero To Mastery

Zero To Mastery thumbnail

Zero To Mastery (ZTM) is a Toronto-based online coding academy founded by Andrei Neagoie, originally a senior developer at large Canadian tech firms before turning to teaching full-time. The academy's signature is the cohort-based bootcamp track combined with a deep self-paced course library, all aimed at career-changers and self-taught developers preparing to land software-engineering roles at top companies.

The instructor roster has grown well beyond Andrei to include other senior practitioners: Daniel Bourke (machine learning), Aleksa Tešić (DevOps), Jacinto Wong, and others. Courses cover the full software-engineering career path: web development with React and Next.js, Python, machine learning and deep learning, DevOps and cloud, system design, mobile, and the algorithm / data-structure interview prep that gates engineering jobs.

The CourseFlix listing under this source carries over 120 ZTM courses spanning that full range. Material is paid; ZTM itself runs on a monthly / annual membership model. The teaching style favours long-form, project-based courses where students build complete portfolio-quality applications rather than disconnected feature tutorials.

Watch Online 23 lessons

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 23 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Project Demo
All Course Lessons (23)
#Lesson TitleDurationAccess
1
Project Demo Demo
05:25
2
Introduction to LangChain
07:16
3
Setting Up The Environment: LangChain, Pinecone, and Python-dotenv
11:02
4
LLM Models (Wrappers): GPT-3
06:14
5
ChatModels: GPT-3.5-Turbo and GPT-4
04:42
6
Prompt Templates
05:11
7
Simple Chains
05:50
8
Sequential Chains
08:08
9
Introduction to LangChain Agents
04:01
10
LangChain Agents in Action
05:29
11
Short Recap of Embeddings
01:53
12
Introduction to Vector Databases
06:58
13
Splitting and Embedding Text Using LangChain
09:20
14
Inserting the Embeddings into a Pinecone Index
07:54
15
Asking Questions (Similarity Search)
07:54
16
Project Introduction
06:09
17
Loading Your Custom (Private) PDF Documents
07:28
18
Loading Different Document Formats
05:13
19
Public and Private Service Loaders
04:38
20
Chunking Strategies and Splitting the Documents
06:39
21
Embedding and Uploading to a Vector Database (Pinecone)
11:18
22
Asking and Getting Answers
10:34
23
Adding Memory (Chat History)
09:06
Unlock unlimited learning

Get instant access to all 22 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Related courses

Frequently asked questions

What prerequisites are needed before enrolling in this course?
The course is designed for both technical and non-technical audiences, so no specific prerequisites are required. However, familiarity with Python and basic programming concepts will be beneficial since the project involves setting up environments and writing code. Knowledge of AI concepts will also help, but the course provides an introduction to LangChain and related technologies.
What can I expect to build by the end of this course?
By the end of the course, you will have built a Q&A application powered by large language models (LLMs) using LangChain, Pinecone, OpenAI, and Python. The application will be capable of processing extensive information inputs, such as books and documents, to answer questions based on data not included in the LLM's original training set.
How does this course compare in depth and scope to other AI courses?
This course focuses specifically on building a Q&A application using LangChain and OpenAI, emphasizing practical application over theoretical depth. It covers setting up environments, using LLM models, and working with vector databases like Pinecone. Unlike broader AI courses, which may cover a wide range of topics, this course provides a focused, hands-on experience in creating scalable AI applications.
What specific tools and platforms will I learn to use in this course?
The course teaches you to use LangChain, an open-source framework that simplifies working with LLMs. You will also learn to work with Pinecone for vector databases, OpenAI's GPT models, and Python for programming. These tools are integrated to build an LLM-powered Q&A application, providing practical skills in AI application development.
What topics are not covered in this course?
This course does not cover the theoretical foundations of machine learning or deep learning beyond what is necessary to understand LangChain and LLMs. It also does not include topics such as model training from scratch, advanced NLP techniques outside the scope of LangChain, or deployment to specific production environments.
How much time should I expect to commit to this course?
The course is structured to be completed in approximately 3 hours. This includes 23 lessons, which guide you through building the Q&A application step-by-step. Additional time may be required for setting up environments and practicing the skills learned, especially for those less familiar with programming or the specific tools used.
How can the skills learned in this course be applied to a career in AI?
The skills acquired in this course can be valuable in various AI-related roles, such as AI developer, data scientist, or machine learning engineer. Understanding how to build applications using LLMs and frameworks like LangChain can open opportunities in developing AI services and solutions across industries, enhancing your ability to contribute to AI projects and innovation.