From the course: Hands-On AI: Introduction to Retrieval-Augmented Generation (RAG)
Unlock this course with a free trial
Join today to access over 24,700 courses taught by industry experts.
Solution: Comparing results - Python Tutorial
From the course: Hands-On AI: Introduction to Retrieval-Augmented Generation (RAG)
Solution: Comparing results
(upbeat music) - [Narrator] This is my solution to the compare and contrast of different setups. So here in the first couple blocks, we're just doing the same thing. We're getting our API key. We're getting the URL, we're setting up our LLM. We're setting up our embedding model. We're launching Phoenix. We're adding it to our LlamaIndex. Then we're going to load an index and we're going to ask some questions. And now, here's where we can do the compare and contrast. Let's load a different index and ask the same questions. As you can see, we got the same answers. Big Star Collectibles was started by Saura Chen. The story for Big Star Collectibles began at the International Arts Conference in 2013. Big Star Collectibles was started by Saura Chen. The story for Big Star Collectibles began in 2013 at the International Arts Conference. The answers are semantically the same, but they're structured a little bit differently. There may be other differences that you might get as you play around…
Contents
-
-
-
-
Understanding your RAG app with observability2m 31s
-
(Locked)
Begin optimizing your data ingestion1m 6s
-
(Locked)
Different embedding models1m 50s
-
(Locked)
Different ways to compare vectors1m 43s
-
(Locked)
Demo: Adding observability to RAG2m 37s
-
(Locked)
Challenge: Altered data ingestion46s
-
(Locked)
Solution: Altered data ingestion1m 17s
-
(Locked)
Challenge: Different embedding models40s
-
(Locked)
Solution: Different embedding models54s
-
(Locked)
Challenge: Comparing results57s
-
(Locked)
Solution: Comparing results1m 24s
-
-