Book Image

Exploring GPT-3

By : Steve Tingiris
Book Image

Exploring GPT-3

By: Steve Tingiris

Overview of this book

Generative Pre-trained Transformer 3 (GPT-3) is a highly advanced language model from OpenAI that can generate written text that is virtually indistinguishable from text written by humans. Whether you have a technical or non-technical background, this book will help you understand and start working with GPT-3 and the OpenAI API. If you want to get hands-on with leveraging artificial intelligence for natural language processing (NLP) tasks, this easy-to-follow book will help you get started. Beginning with a high-level introduction to NLP and GPT-3, the book takes you through practical examples that show how to leverage the OpenAI API and GPT-3 for text generation, classification, and semantic search. You'll explore the capabilities of the OpenAI API and GPT-3 and find out which NLP use cases GPT-3 is best suited for. You’ll also learn how to use the API and optimize requests for the best possible results. With examples focusing on the OpenAI Playground and easy-to-follow JavaScript and Python code samples, the book illustrates the possible applications of GPT-3 in production. By the end of this book, you'll understand the best use cases for GPT-3 and how to integrate the OpenAI API in your applications for a wide array of NLP tasks.
Table of Contents (15 chapters)
1
Section 1: Understanding GPT-3 and the OpenAI API
4
Section 2: Getting Started with GPT-3
8
Section 3: Using the OpenAI API

Using the Semantic Search endpoint

In Chapter 2, GPT-3 Applications and Use Cases, we discussed semantic search. By way of a review, semantic search lets you perform a Google-like search over a list of provided documents. A query (a word, phrase, question, or statement) is compared to the contents of documents to determine whether semantic similarities exist. The result is a ranking, or score, for each document. The score is usually between 0 and 300 but can sometimes go higher. A higher score, above 200, typically means the document is semantically similar to the query.

To perform a semantic search using the API, you'll make a POST request to the Semantic Search endpoint. Like the Create Completions endpoint, you'll also include a JSON object in the request body. The JSON body object has two elements – the documents element and the query element. The documents element is an array of documents to be searched, and each item in the array is a string that represents...