Giter Club home page Giter Club logo

bases's Introduction

Click here to get started on this lab.

Explore the OpenAI GPT-3.5 Models

This session is a 60-minute live demonstration of interaction with OpenAI models GPT-3.5 Instruct (gpt-35-turbo-instruct) and GPT-3.5 Turbo (gpt-3.5-turbo). You can follow along with the demonstration live using Use Azure AI Studio or OpenAI Playground, or work through the examples in this repository later at your own pace and schedule.

The goal of this 60-minute session is to:

  • Understand the implementation and capabilities of the GPT-3.5 family of models
  • Learn how to use and customize natural language generative AI models using prompt engineering techniques
  • Understand the basics of integrating OpenAI models into applications with the API

Pre-requisites

You will need an Azure Account or an OpenAI account to complete this lab. If you do not have an Azure Account, you can create one for free here, and request access to Azure OpenAI Service here.

Get Started

Visit the lab website to get started.

Watch a video recording of this lab on YouTube: Make Azure AI Real: Exploring Azure OpenAI Service.

Overview

This workshop will cover the following topics:

  1. Setup: Create and deploy the Azure OpenAI resource in the Azure Portal
  2. Explore Models: Understand the natural language models availabe in OpenAI and Azure OpenAI Service.
  3. Completions: Understand and experiment with prompts and completions.
  4. Tokens: Learn about tokens in OpenAI models.
  5. Applications: Learn about applications of natural language generative AI models.
  6. Conversations: Using the Chat playground.
  7. Prompt Engineering: Learn how to use prompt engineering to customize the behavior of the model.
  8. Using the API: Learn how to generate integration code for use with the Azure OpenAI API.
  9. Learnings and Resources: Recap and links for further learning.
  10. Extra Credit: Explore the capabilities of Bing Chat.

Citations and Credits

"Explore the OpenAI GPT-3.5 Models", David Smith (Microsoft), 2023. When referening this repository, please use the shortlink: https://aka.ms/exploring-gpt35

Presented at Make AI Real in a Day, October 26 2023.

This repository was created by David Smith (Microsoft). Some content contributed by Henk Boelman (Microsoft) and Amy Boyd (Microsoft). Docusaurus integration by Dave Glover (Microsoft).

This lab is open source

This website is built using Docusaurus 2, a modern open-source static website generator.

You are free to copy, adapt and use this content according to the terms of the MIT License. For information on how to configure a fork of this site for deployment, see Building.md.

Feedback

We would love to hear your feedback on this lab. Please use the Discussions tab for comments, or the Issues tab for bugs or suggestions.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.