From the course: Oracle Cloud Infrastructure Generative AI Professional

Unlock this course with a free trial

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

Embed and store documents

Embed and store documents - Oracle Cloud Infrastructure Tutorial

From the course: Oracle Cloud Infrastructure Generative AI Professional

Start my 1-month free trial Buy for my team

Embed and store documents

“

- [Instructor] In the previous lesson, we discussed how documents are loaded and split into chunks. Now let us see how chunks are embedded and stored for retrieval. But before that, let us understand what are embeddings. If we take an example of three group of words, say animals, fruits and places, and are given a word, tiger, we as human beings will place it in the animals group because we know that semantically, tiger is similar to the words in the animal group. But for the machines to understand the similarity of words or sentences or even documents, concept of embeddings was born. The embeddings of similar words or sentences or documents are close by in the multi-dimensional space. This is achieved through a process of training the embedding models. One string embeddings reflect semantic similarity of words or sentences or documents. What we see in the picture is a two dimensional representation of the embeddings of a few words. If you measure the similarity of a new word, say…

Contents