This article will show you different approaches you can take to create embeddings for your data

Creating quality embeddings from your data is crucial for your AI system’s efficacy. This article will show you different approaches you can use to convert your data from formats like images, texts, and audio, into powerful embeddings that can be used for your machine learning tasks. Your ability to create high-performance embeddings will have a large impact on the performance of your AI system, hence it is essential to learn and understand how to craft quality embeddings.

Making embeddings from a photo. Image by ChatGPT. “make an image of an AI making embeddings from a photo” prompt. ChatGPT, 4, OpenAI, 18 Feb. 2024.

The motivation for this article is that creating good embeddings from your data is essential to most AI systems and it is therefore something you often have to do, making better embeddings a good way of improving all your future AI systems. The use cases for creating embeddings are tasks like clustering, similarity search, and anomaly detection, all of which can massively benefit from better embeddings. This article will explore two main ways of calculating embeddings; using an online model or training your very own model, which will both be discussed in subsequent sections of this article.

The pipeline for creating embeddings. First retrieve your data, which can for example be image, text, or audio data. Enter the data into the embedding model, which outputs a generated embedding. Image by the author made with

· Introduction
· Table of contents
· Motivation and use case
· Create embeddings using PyTorch models
· Create embeddings using HuggingFace models
Approach 1
Approach 2
· Create embeddings using GitHub
· Creating embeddings using paid models
· Create your own embeddings
Training your own model on a downstream task
· Typical errors when creating embeddings
Forget to use a pre-trained model
· Conclusion