Discover how embeddings models power many of the most exciting AI applications. Learn to use the OpenAI API to create embeddings and compute the semantic similarity between text.

The wonderful world of embeddings!

What are embeddings?

Embeddings applications

Creating embeddings

Digging into the embeddings response

Investigating the vector space

Embedding product descriptions

Visualizing the embedded descriptions

Text similarity

Computing cosine distances

More repeatable embeddings

Finding the most similar product

What are Embeddings?

Embeddings enable powerful AI applications, including semantic search engines, recommendation engines, and classification tasks like sentiment analysis. Learn how to use OpenAI's embeddings model to enable these exciting applications!

Semantic search and enriched embeddings

Enriching embeddings

Sorting by similarity

Semantic search for products

Recommendation systems

Product recommendation system

Adding user history to the recommendation engine

Embeddings for classification tasks

Embedding restaurant reviews

Classifying review sentiment

Embedding more detailed descriptions

Embeddings for AI Applications

To enable embedding applications in production, you'll need an efficient vector storage and querying solution: enter vector databases! You'll learn how vector databases can help scale embedding applications and begin creating and adding to your very own vector databases using Chroma.

Vector databases for embedding systems

Options

Metadata

Not metadata

To metadata or not to metadata?

Choosing a vector database solution

Creating vector databases with ChromaDB

Getting started with ChromaDB

Estimating embedding costs with tiktoken

Adding data to the collection

Querying and updating the database

Querying the Netflix collection

Updating and deleting items from a collection

Multiple queries and filtering

Querying with multiple texts

Filtering using metadata

Congratulations!

Vector Databases

Online Retail Products

Netflix Titles (Full)

Netflix Titles (First 1000)

Text embedding models create numerical representations from text inputs. This ability to encode text and capture its semantic meaning means that embedding models underpin many types of AI applications, like semantic search engines and recommendation engines. In this course, you'll learn how to harness OpenAI's Embeddings model via the OpenAI API to create embeddings from text datasets and begin developing real-world applications. You'll also take a big step towards creating production-ready applications by learning about vector databases to efficiently store and query embedded texts.

<h2>Enable Powerful AI Applications</h2>
Embeddings allow us to represent text numerically, capturing the context and intent behind the text. You'll learn about how these abilities can enable semantic search engines, that can search based on meaning, more relevant recommendation engines, and perform classification tasks like sentiment analysis.<br><br>
<h2>Create Embeddings Using the OpenAI API</h2>The OpenAI API not only has endpoints for accessing its GPT and Whisper models, but also for models for creating embeddings from text inputs. You'll create embeddings using OpenAI's state-of-the-art embeddings models to capture the semantic meaning of text.<br><br>
<h2>Build Semantic Search and Recommendation Engines</h2>
Traditional search engines relied on keyword matching to return the most relevant results to users, but more modern techniques use embeddings, as they can capture the semantic meaning of the text. You'll learn to create a semantic search engine for a online retail platform using OpenAI's embeddings model, so users can more easily find the most relevant products. You'll also learn how to create a product recommendation system, which are built on the same principles as semantic search.<br><br>
<h2>Utilize Vector Databases</h2>
AI applications in production that rely on embeddings often use a vector database to store and query the embedded text in a more efficient and reproducible way. In this course, you’ll learn to use ChromaDB, an open-source, self-managed vector database solution, to create and store embeddings on your local system.

Working with the OpenAI API

Python Toolbox

Unlock more advanced AI applications, like semantic search and recommendation engines, using OpenAI's embedding model!

Introduction to Embeddings with the OpenAI API

Ingegnere AI associato per sviluppatori

Sviluppare applicazioni AI

Fondamenti di OpenAI

Choosing a vector database solution

Introduction to Embeddings with the OpenAI API

Esercizio pratico interattivo