LLMs: What They Are and How to Leverage Them?

certificate
Recording and certification are available to Multipass and Full ticket holders only
Please login if you have one.
Rate this content
Bookmark

Join Nathan and Alexa in this hands-on session where you will first learn at a high level what large language models (LLMs) are and how they work. Then dive into an interactive coding exercise where you will implement LLM functionality into a basic example application. During this exercise you will get a feel for key skills for working with LLMs in your own applications such as prompt engineering and exposure to OpenAI's API.

After this session you will have insights around what LLMs are and how they can practically be used to improve your own applications.

This workshop has been presented at React Summit US 2024, check out the latest edition of this React Conference.

FAQ

The workshop aims to introduce participants to large language models and explore how they can be leveraged in the observability space at Grafana Labs.

The presenters of the workshop are Alexa, a software engineer, and Nathan, an engineering manager, both from Grafana Labs.

A large language model is a type of artificial intelligence model that is trained on a large dataset to predict the next word in a sequence, enabling it to generate human-like text. It consists of weights and parameters stored as matrices.

Pre-training involves training the model on a large quantity of diverse internet text to gather knowledge, while fine-tuning adjusts the model on high-quality Q&A data to align it with specific tasks or purposes.

Grafana Labs uses large language models for tasks like generating incident summaries, adding titles and descriptions to dashboards, and explaining flame graph profiling data.

Temperature controls the randomness of the model's responses. A low temperature results in more deterministic responses, while a high temperature allows for more creative and varied outputs.

Grafana Labs leverages large language models to enhance data visualization and monitoring by generating explanatory content and reducing the manual toil of creating descriptions and summaries.

The workshop utilized tools like CodeSandbox for hands-on exercises and OpenAI's GPT-4 model for generating text-based recommendations.

To ensure safety, the AI-generated cocktail recommendations are cross-referenced with curated cocktail lists from an open source CocktailDB API to avoid unsafe combinations.

Nathan Marrs
Nathan Marrs
Alexandra Vargas
Alexandra Vargas
112 min
03 Dec, 2024

Comments

Sign in or register to post your comment.
Video Summary and Transcription
Welcome to this intro to large language models workshop. We're exploring how to leverage large language models within the observability space. Today's workshop covers the introduction to large language models, obtaining parameters for the model, training and base model, working of parameters and neural network inference, Oppenheimer and neural network architecture, obtaining and training an assistant model, labeling and collaborating with models, obtaining and fine-tuning the chat model, Grafana's approach to using large language models, integrating models into day-to-day work, a hands-on exercise on integrating models, an AI-powered cocktail recommendation, getting familiar with APIs and API key, using API keys and communicating with models, configuring API and user input, generating cocktail recommendations, enabling full functionality and generating recipes, GPT models and context window, creating prompts and handling responses, handling OpenAI's response and error handling, troubleshooting and generating multiple choices, enhancing existing products with AI, and enhancing assistance and structured outputs.
Video transcription and chapters available for users with access.

Watch more workshops on topic

React Performance Debugging Masterclass
React Summit 2023React Summit 2023
170 min
React Performance Debugging Masterclass
Top Content
Featured WorkshopFree
Ivan Akulov
Ivan Akulov
Ivan’s first attempts at performance debugging were chaotic. He would see a slow interaction, try a random optimization, see that it didn't help, and keep trying other optimizations until he found the right one (or gave up).
Back then, Ivan didn’t know how to use performance devtools well. He would do a recording in Chrome DevTools or React Profiler, poke around it, try clicking random things, and then close it in frustration a few minutes later. Now, Ivan knows exactly where and what to look for. And in this workshop, Ivan will teach you that too.
Here’s how this is going to work. We’ll take a slow app → debug it (using tools like Chrome DevTools, React Profiler, and why-did-you-render) → pinpoint the bottleneck → and then repeat, several times more. We won’t talk about the solutions (in 90% of the cases, it’s just the ol’ regular useMemo() or memo()). But we’ll talk about everything that comes before – and learn how to analyze any React performance problem, step by step.
(Note: This workshop is best suited for engineers who are already familiar with how useMemo() and memo() work – but want to get better at using the performance tools around React. Also, we’ll be covering interaction performance, not load speed, so you won’t hear a word about Lighthouse 🤐)
React Hooks Tips Only the Pros Know
React Summit Remote Edition 2021React Summit Remote Edition 2021
177 min
React Hooks Tips Only the Pros Know
Top Content
Featured Workshop
Maurice de Beijer
Maurice de Beijer
The addition of the hooks API to React was quite a major change. Before hooks most components had to be class based. Now, with hooks, these are often much simpler functional components. Hooks can be really simple to use. Almost deceptively simple. Because there are still plenty of ways you can mess up with hooks. And it often turns out there are many ways where you can improve your components a better understanding of how each React hook can be used.You will learn all about the pros and cons of the various hooks. You will learn when to use useState() versus useReducer(). We will look at using useContext() efficiently. You will see when to use useLayoutEffect() and when useEffect() is better.
React, TypeScript, and TDD
React Advanced 2021React Advanced 2021
174 min
React, TypeScript, and TDD
Top Content
Featured WorkshopFree
Paul Everitt
Paul Everitt
ReactJS is wildly popular and thus wildly supported. TypeScript is increasingly popular, and thus increasingly supported.

The two together? Not as much. Given that they both change quickly, it's hard to find accurate learning materials.

React+TypeScript, with JetBrains IDEs? That three-part combination is the topic of this series. We'll show a little about a lot. Meaning, the key steps to getting productive, in the IDE, for React projects using TypeScript. Along the way we'll show test-driven development and emphasize tips-and-tricks in the IDE.
Master JavaScript Patterns
JSNation 2024JSNation 2024
145 min
Master JavaScript Patterns
Top Content
Featured Workshop
Adrian Hajdin
Adrian Hajdin
During this workshop, participants will review the essential JavaScript patterns that every developer should know. Through hands-on exercises, real-world examples, and interactive discussions, attendees will deepen their understanding of best practices for organizing code, solving common challenges, and designing scalable architectures. By the end of the workshop, participants will gain newfound confidence in their ability to write high-quality JavaScript code that stands the test of time.
Points Covered:
1. Introduction to JavaScript Patterns2. Foundational Patterns3. Object Creation Patterns4. Behavioral Patterns5. Architectural Patterns6. Hands-On Exercises and Case Studies
How It Will Help Developers:
- Gain a deep understanding of JavaScript patterns and their applications in real-world scenarios- Learn best practices for organizing code, solving common challenges, and designing scalable architectures- Enhance problem-solving skills and code readability- Improve collaboration and communication within development teams- Accelerate career growth and opportunities for advancement in the software industry
Designing Effective Tests With React Testing Library
React Summit 2023React Summit 2023
151 min
Designing Effective Tests With React Testing Library
Top Content
Featured Workshop
Josh Justice
Josh Justice
React Testing Library is a great framework for React component tests because there are a lot of questions it answers for you, so you don’t need to worry about those questions. But that doesn’t mean testing is easy. There are still a lot of questions you have to figure out for yourself: How many component tests should you write vs end-to-end tests or lower-level unit tests? How can you test a certain line of code that is tricky to test? And what in the world are you supposed to do about that persistent act() warning?
In this three-hour workshop we’ll introduce React Testing Library along with a mental model for how to think about designing your component tests. This mental model will help you see how to test each bit of logic, whether or not to mock dependencies, and will help improve the design of your components. You’ll walk away with the tools, techniques, and principles you need to implement low-cost, high-value component tests.
Table of contents- The different kinds of React application tests, and where component tests fit in- A mental model for thinking about the inputs and outputs of the components you test- Options for selecting DOM elements to verify and interact with them- The value of mocks and why they shouldn’t be avoided- The challenges with asynchrony in RTL tests and how to handle them
Prerequisites- Familiarity with building applications with React- Basic experience writing automated tests with Jest or another unit testing framework- You do not need any experience with React Testing Library- Machine setup: Node LTS, Yarn
AI on Demand: Serverless AI
DevOps.js Conf 2024DevOps.js Conf 2024
163 min
AI on Demand: Serverless AI
Top Content
Featured WorkshopFree
Nathan Disidore
Nathan Disidore
In this workshop, we discuss the merits of serverless architecture and how it can be applied to the AI space. We'll explore options around building serverless RAG applications for a more lambda-esque approach to AI. Next, we'll get hands on and build a sample CRUD app that allows you to store information and query it using an LLM with Workers AI, Vectorize, D1, and Cloudflare Workers.

Check out more articles and videos

We constantly think of articles and videos that might spark Git people interest / skill us up or help building a stellar career

Don't Solve Problems, Eliminate Them
React Advanced 2021React Advanced 2021
39 min
Don't Solve Problems, Eliminate Them
Top Content
Kent C. Dodds discusses the concept of problem elimination rather than just problem-solving. He introduces the idea of a problem tree and the importance of avoiding creating solutions prematurely. Kent uses examples like Tesla's electric engine and Remix framework to illustrate the benefits of problem elimination. He emphasizes the value of trade-offs and taking the easier path, as well as the need to constantly re-evaluate and change approaches to eliminate problems.
Using useEffect Effectively
React Advanced 2022React Advanced 2022
30 min
Using useEffect Effectively
Top Content
Today's Talk explores the use of the useEffect hook in React development, covering topics such as fetching data, handling race conditions and cleanup, and optimizing performance. It also discusses the correct use of useEffect in React 18, the distinction between Activity Effects and Action Effects, and the potential misuse of useEffect. The Talk highlights the benefits of using useQuery or SWR for data fetching, the problems with using useEffect for initializing global singletons, and the use of state machines for handling effects. The speaker also recommends exploring the beta React docs and using tools like the stately.ai editor for visualizing state machines.
Design Systems: Walking the Line Between Flexibility and Consistency
React Advanced 2021React Advanced 2021
47 min
Design Systems: Walking the Line Between Flexibility and Consistency
Top Content
The Talk discusses the balance between flexibility and consistency in design systems. It explores the API design of the ActionList component and the customization options it offers. The use of component-based APIs and composability is emphasized for flexibility and customization. The Talk also touches on the ActionMenu component and the concept of building for people. The Q&A session covers topics such as component inclusion in design systems, API complexity, and the decision between creating a custom design system or using a component library.
React Concurrency, Explained
React Summit 2023React Summit 2023
23 min
React Concurrency, Explained
Top Content
Watch video: React Concurrency, Explained
React 18's concurrent rendering, specifically the useTransition hook, optimizes app performance by allowing non-urgent updates to be processed without freezing the UI. However, there are drawbacks such as longer processing time for non-urgent updates and increased CPU usage. The useTransition hook works similarly to throttling or bouncing, making it useful for addressing performance issues caused by multiple small components. Libraries like React Query may require the use of alternative APIs to handle urgent and non-urgent updates effectively.
Managing React State: 10 Years of Lessons Learned
React Day Berlin 2023React Day Berlin 2023
16 min
Managing React State: 10 Years of Lessons Learned
Top Content
Watch video: Managing React State: 10 Years of Lessons Learned
This Talk focuses on effective React state management and lessons learned over the past 10 years. Key points include separating related state, utilizing UseReducer for protecting state and updating multiple pieces of state simultaneously, avoiding unnecessary state syncing with useEffect, using abstractions like React Query or SWR for fetching data, simplifying state management with custom hooks, and leveraging refs and third-party libraries for managing state. Additional resources and services are also provided for further learning and support.
TypeScript and React: Secrets of a Happy Marriage
React Advanced 2022React Advanced 2022
21 min
TypeScript and React: Secrets of a Happy Marriage
Top Content
React and TypeScript have a strong relationship, with TypeScript offering benefits like better type checking and contract enforcement. Failing early and failing hard is important in software development to catch errors and debug effectively. TypeScript provides early detection of errors and ensures data accuracy in components and hooks. It offers superior type safety but can become complex as the codebase grows. Using union types in props can resolve errors and address dependencies. Dynamic communication and type contracts can be achieved through generics. Understanding React's built-in types and hooks like useState and useRef is crucial for leveraging their functionality.