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.
Challenge: Comparing results - Python Tutorial
From the course: Hands-On AI: Introduction to Retrieval-Augmented Generation (RAG)
Challenge: Comparing results
(upbeat music) - [Instructor] For your last project, let's go ahead and compare and contrast how different setups for your RAG application look. Here, in our starting notebook, we have the same few blocks of code at the beginning. Here, all we're doing is importing these tokens. The URL, the LLM, the embedding, Phoenix, starting Phoenix to LlamaIndex. And then here we're reading in new data and perhaps storing it in a different vector store index. And then we're asking questions. So this block is where you need to be changing your code so that you can compare and contrast different ways that the code might be set up.
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
-
-