Responsive LLM Applications with Server-Sent Events

1h 18m 18s
English
Paid

Course description

Large Language Models (LLM) are transforming entire industries, but integrating them into user interfaces with real-time data streaming comes with unique challenges. In this course, you will learn to seamlessly embed LLM APIs into applications and create AI interfaces for streaming text and chats using TypeScript, React, and Python. We will develop a fully functional AI application step by step with high-quality code and flexible implementation.
Read more about the course

As part of the course, you will create an LLM application that includes:

  • autocompletion scenario (translation from English to emoji),
  • chat,
  • retrieval augmented generation scenario,
  • AI agent usage scenarios (code execution, data analysis agent).

This application can become a starting point for most projects, saving a lot of time, and its flexibility allows for the addition of new tools as needed.

By the end of the course, you will have mastered the end-to-end implementation of a flexible and high-quality LLM application. You will also gain the knowledge and skills necessary to create complex solutions based on LLM.

Watch Online

Join premium to watch
Go to premium
# Title Duration
1 Introduction to AI Product Development 03:48
2 Picking the stack - Navigating JavaScript and Python 06:10
3 Designing a Hybrid Web Application Architecture with JavaScript and Python 05:08
4 Streaming events with Server-Sent Events and WebSockets 06:31
5 Discovering the OpenAI Completion API 06:30
6 Handling Server-Sent Events with JavaScript 06:14
7 Building the useCompletion hook 07:01
8 Rendering Completion Output 01:26
9 Mocking Streams 03:29
10 Testing the useCompletion hook 03:11
11 Creating a FastAPI server 01:55
12 Exploring asynchronous programming in Python 03:42
13 Integrating Langchain with FastAPI for Asynchronous Streaming 04:34
14 Testing with PyTest and LangChain 01:02
15 Building the useChat hook 05:12
16 Building the User Interface 01:53
17 Discovering Retrieval Augmented Generation 03:19
18 Building a Semantic Search Engine with Chroma 03:37
19 Adding Retrieval-Augmented Generation to the chat 02:14
20 Final words 01:22