From the course: Advanced RAG Applications with Vector Databases
Unlock the full course today
Join today to access over 24,700 courses taught by industry experts.
Challenge: Find the dog most similar to a cat
From the course: Advanced RAG Applications with Vector Databases
Challenge: Find the dog most similar to a cat
(bright upbeat music) - [Instructor] Now that you know how to generate semantic embeddings of images, how to store them and how to retrieve them, it's time to put your skills to the test. The coding challenge for this chapter, it's to find the dog that looks most similar to the cats, at least according to our image embedding model. The basic idea behind this is to find the dog picture that returns the most cat pictures. You can also weight those return values by their total distances or inversely based on rank. Good luck and see you in the Solution Video.
Contents
-
-
-
-
(Locked)
Introduction to vector embeddings for images2m 8s
-
Vision models 1014m 58s
-
(Locked)
Demo: Getting semantic vectors57s
-
(Locked)
Demo: Storing image vectors1m 10s
-
(Locked)
Demo: Comparing images semantically46s
-
(Locked)
Challenge: Find the dog most similar to a cat42s
-
(Locked)
Solution: Find the dog most similar to a cat1m 46s
-
(Locked)
-
-