4.61 out of 5
4.61
1158 reviews on Udemy

Learn LangChain, Pinecone & OpenAI: Build Next-Gen LLM Apps

Hands-On Applications with LangChain, Pinecone, and OpenAI. Build Web Apps with Streamlit. Join the AI Revolution Today!
Instructor:
Andrei Dumitrescu
9,226 students enrolled
English [Auto] More
How to Use LangChain, Pinecone, and OpenAI to Build LLM-Powered Applications.
Learn about LangChain components, including LLM wrappers, prompt templates, chains, and agents.
Learn about the different types of chains available in LangChain, such as stuff, map_reduce, refine, and LangChain agents.
Acquire a solid understanding of embeddings and vector data stores.
Learn how to use embeddings and vector data stores to improve the performance of your LangChain applications.
Deep Dive into Pinecone.
Learn about Pinecone Indexes and Similarity Search.
Project: Build an LLM-powered question-answering app with a modern web-based front-end for custom or private documents.
Project: Build a summarization system for large documents using various methods and chains: stuff, map_reduce, refine, or LangChain Agents.
This will be a Learning-by-Doing Experience. We'll Build Together, Step-by-Step, Line-by-Line, Real-World Applications (including front-ends using Streamlit).
You'll learn how to create web interfaces (front-ends) for your LLM and generative AI apps using Streamlit.
Streamlit: main concepts, widgets, session state, callbacks.
Learn how to use Jupyter AI efficiently.

Master LangChain, Pinecone, and OpenAI. Build hands-on generative LLM-powered applications with LangChain.

Create powerful web-based front-ends for your generative apps using Streamlit.

The AI revolution is here and it will change the world! In a few years, the entire society will be reshaped by artificial intelligence.

By the end of this course, you will have a solid understanding of the fundamentals of LangChain, Pinecone, and OpenAI. You’ll also be able to create modern front-ends using Streamlit in pure Python.

This LangChain course is the 2nd part of “OpenAI API with Python Bootcamp”. It is not recommended for complete beginners as it requires some essential Python programming experience.

Currently, the effort, knowledge, and money of major technology corporations worldwide are being invested in AI.

In this course, you’ll learn how to build state-of-the-art LLM-powered applications with LangChain.

What is LangChain?

LangChain is an open-source framework that allows developers working with AI to combine large language models (LLMs) like GPT-4 with external sources of computation and data. It makes it easy to build and deploy AI applications that are both scalable and performant.

It also facilitates entry into the AI field for individuals from diverse backgrounds and enables the deployment of AI as a service.

In this course, we’ll go over LangChain components, LLM wrappers, Chains, and Agents. We’ll dive deep into embeddings and vector databases such as Pinecone.

This will be a learning-by-doing experience. We’ll build together, step-by-step, line-by-line, real-world LLM applications with Python, LangChain, and OpenAI. The applications will be complete and we’ll also contain a modern web app front-end using Streamlit.

We will develop an LLM-powered question-answering application using LangChain, Pinecone, and OpenAI for custom or private documents. This opens up an infinite number of practical use cases.

We will also build a summarization system, which is a valuable tool for anyone who needs to summarize large amounts of text. This includes students, researchers, and business professionals.

I will continue to add new projects that solve different problems. This course, and the technologies it covers, will always be under development and continuously updated.

The topics covered in this “LangChain, Pinecone and OpenAI” course are:

  • LangChain Fundamentals

  • Setting Up the Environment with Dotenv: LangChain, Pinecone, OpenAI

  • LLM Models (Wrappers): GPT-3

  • ChatModels: GPT-3.5-Turbo and GPT-4

  • LangChain Prompt Templates

  • Simple Chains

  • Sequential Chains

  • Introduction to LangChain Agents

  • LangChain Agents in Action

  • Vector Embeddings

  • Introduction to Vector Databases

  • Diving into Pinecone

  • Diving into Chroma

  • Splitting and Embedding Text Using LangChain

  • Inserting the Embeddings into a Pinecone Index

  • Asking Questions (Similarity Search) and Gettings Answers (GPT-4)

  • Proficient in using AI Coding Assistants (Jupyter AI)   

  • Creating front-ends for LLM and generative AI apps using Streamlit

  • Streamlit: main concepts, widgets, session state, callbacks

The skills you’ll acquire will allow you to build and deploy real-world AI applications. I can’t tell you how excited I am to teach you all these cutting-edge technologies.

Come on board now, so that you are not left behind.

I will see you in the course!

Getting Started

1
How to Get the Most Out of This Course
2
Join My Private Community!
3
Course Resources

Deep Dive into LangChain and Pinecone

1
LangChain Demo
2
Introduction to LangChain
3
OpenAI API and LangChain Libraries V1 (Important Update)
4
Setting Up the Environment: LangChain, Pinecone, and Python-dotenv
5
ChatModels: GPT-3.5-Turbo and GPT-4
6
Prompt Templates
7
Simple Chains
8
Sequential Chains
9
Introduction to LangChain Agents
10
LangChain Agents in Action
11
Short Recap of Embeddings
12
Introduction to Vector Databases
13
Diving into Pinecone, Part 1
14
Diving into Pinecone, Part 2
15
Splitting and Embedding Text Using LangChain
16
Inserting the Embeddings into a Pinecone Index
17
Asking Questions (Similarity Search)

Jupyter AI

1
Jupyter AI
2
Introduction to Jupyter AI and Other Coding Companions
3
Installing Jupyter AI
4
Using Jupyter AI in JupyterLab
5
Setting Up Jupyter AI in Jupyter Notebook
6
Using Jupyter AI in Jupyter Notebook
7
Using Interpolation for More Advanced Use Cases
8
Using Jupyter AI with Other Providers and Models

Project #1: Building a Custom ChatGPT App with LangChain From Scratch

1
Project Introduction
2
Implementing a ChatGPT App with ChatPromptTemplates and Chains
3
Adding Chat Memory Using ConversationBufferMemory
4
Saving Chat Sessions

Project #2: Question-Answering Application on Your Custom (or Private) Documents

1
Project Introduction
2
Loading Your Custom (Private) PDF Documents
3
Loading Different Document Formats
4
Public and Private Service Loaders
5
Chunking Strategies and Splitting the Documents
6
Embedding and Uploading to a Vector Database (Pinecone)
7
Asking and Getting Answers
8
Adding Memory (Chat History)

Project #3: Building a Front-End for the Question-Answering App Using Streamlit

1
Project Introduction and Library Installation
2
Defining Functions
3
Creating the Sidebar
4
Reading, Chunking, and Embedding Data
5
Asking Questions and Getting Answers
6
Saving the Chat History
7
Clearing Session State History Using Callback Functions

Project #4: Summarizing With LangChain and OpenAI

1
Project Introduction
2
Summarizing Using a Basic Prompt
3
Summarizing using Prompt Templates
4
Summarizing Using StuffDocumentsChain
5
Summarizing Large Documents Using map_reduce
6
map_reduce With Custom Prompts
7
Summarizing Using the refine CombineDocumentChain
8
refine With Custom Prompts
9
Summarizing Using LangChain Agents

Project #5: Building a Custom ChatGTP App with LangChain and Streamlit

1
Project Introduction
2
Building the App
3
Displaying the Chat History
4
Testing the App

[Appendix]: Creating Web Interfaces for LLM Applications Using Streamlit

1
Section Resources
2
Introduction to Streamlit
3
Streamlit Main Concepts
4
Displaying Data on the Screen: st.write() and Magic
5
Widgets, Part 1: text_input, number_input, button
6
Widgets, Part 2: checkbox, radio, select
7
Widgets, Part 3: slider, file_uploader, camera_input, image
8
Layout: Sidebar
9
Layout: Columns
10
Layout: Expander
11
Displaying a Progress Bar
12
Session State
13
Callbacks

[Appendix]: Python Programming

1
README
2
While and continue Statements
3
While and break Statements
4
List Slicing and Iteration
5
List Comprehension - Part 1
6
List Comprehension - Part 2
7
Working with Dictionaries
8
JSON Data Serialization
9
JSON Data Deserialization
10
Assignment: JSON and Requests/REST API
11
Assignment Answer: JSON and Requests/REST API

[Appendinx]: Installing Jupyter Notebook and Google Colab

1
Installing Jupyter Notebook and Google Colab

BONUS SECTION

1
Congratulations
2
BONUS: THANK YOU GIFT!
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.6
4.6 out of 5
1158 Ratings

Detailed Rating

Stars 5
698
Stars 4
345
Stars 3
83
Stars 2
11
Stars 1
2