From the course: Oracle Cloud Infrastructure Generative AI Professional Cert Prep

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Embedding models

Embedding models - Oracle Cloud Infrastructure Tutorial

From the course: Oracle Cloud Infrastructure Generative AI Professional Cert Prep

Start my 1-month free trial Buy for my team

Embedding models

“

(ambient music) - [Rohit] Welcome, everyone. In this lesson, let us look at embedding models available in the OCI generative AI service. First, let us understand what embeddings are. Embeddings are numerical representations of a piece of text converted to number sequences. A piece of text could be a word, it could be a phrase, could be a sentence, could be a paragraph, or it could be an entire documents, one or more paragraphs. Embeddings make it easy for computers to understand the relationship between pieces of text. Now let us look at a practical example where embeddings are used. So for example, if I have a sentence which is something like, "They sent me a," or rather a phrase, "They sent me a," and I send this to an encoder. It's kind of an LLM architecture. Now, encoders are really designed to take that text, so this is an encoder, and convert it into a vector. So you see these five vectors, there is a vector for each of the words, and there is also a vector, a representation…

Contents