From the course: AWS Certified Machine Learning Engineer Associate (MLA-C01) Cert Prep

Unlock this course with a free trial

Join today to access over 24,700 courses taught by industry experts.

Embeddings and vector databases

Embeddings and vector databases

From the course: AWS Certified Machine Learning Engineer Associate (MLA-C01) Cert Prep

Start my 1-month free trial Buy for my team

Embeddings and vector databases

“

(calm music) - [Instructor] Hello guys, and welcome again. So in today's lesson we're going to talk about the embeddings and the vector databases. We're going to mention what are they, how they're being used, and what are the associated AWS services with them. Embeddings are numerical representations of data such as text, images, or even audio that are being mapped into a multidimensional vector space. These embeddings help machine learning models understand the context and the relationships within complex data, allowing them to make more sense of the abstract concepts. For example, word embeddings, which is a one type of an embedding, allow the models to grasp the word similarity. So the embedding for king would be closer to queen than to apple in this vector space. This means that the model understands how the words relate to each other beyond just the literal spelling or definition. Now, let's talk about the vector databases. A vector database stores these embeddings as high…

Contents