From the course: Introduction to AI-Native Vector Databases
Join today to access over 24,400 courses taught by industry experts.
Frame the query as a question or search
From the course: Introduction to AI-Native Vector Databases
Frame the query as a question or search
Now that we understand, vectors can be used to capture the meaning behind data, and can also be understood by machines, let's imagine all of our data in vector form. We can take all the data files that we have on our computer, or information that our company wants to store and represent them as vectors. This is known as embedding your data into vector space. We visualized each of these vectors as a green point in this visual. You can embed text files, images, audio, video, and more into vector space. In this vector space, similar file vectors are closer together, while vectors for dissimilar files are further apart. Now, let's think about how we can search through this data. Searching involves asking a question or querying. For example, you might want to retrieve the images of your family vacation from your computer. We now want to take the question and see which information on our computer is relevant. How can we search through the tens of thousands of data points and retrieve the…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
Contents
-
-
-
-
(Locked)
Frame the query as a question or search1m 56s
-
(Locked)
Generate the question in machine-understandable language1m 22s
-
Adding data to a vector database9m 48s
-
Performing semantic searches using Weaviate13m 36s
-
(Locked)
Challenge: Vector search with Weaviate49s
-
Solution: Vector Search with Weaviate11m 5s
-
(Locked)
-
-
-
-