Introduction to Embeddings

Overview

Want to generate embeddings with no setup required? Gradient provides a simple API to utilize embeddings models.

🔢 What are embeddings?

Embeddings are numerical representations of natural language concepts. A word, phrase or even document is converted into a vector of real numbers. Generating embeddings makes it easier to perform ML tasks such as semantic search and classification.

Embeddings are also a key component in Retrieval Augmented Generation (RAG), a technique that can greatly enhance your LLM’s knowledge in a specific domain and reduce hallucinations in AI applications.

🔓 Why use Gradient to generate embeddings?

We make it easy to generate embeddings with a single API call, so you don't have to set it up yourself.

With Gradient, you also have full control and ownership of your data and the embeddings you generate. No one outside of your private workspace can access them.

🛠️ What embeddings models can be used?

This list of open-source embeddings models is currently available. We will be expanding to more models soon!