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: Putting it all together - Python Tutorial
From the course: Hands-On AI: Introduction to Retrieval-Augmented Generation (RAG)
Solution: Putting it all together
(upbeat music) - [Narrator] Welcome back to our "Putting It All Together Solution". Here in the first block of code, we're doing the exact same thing as we did before. And the next block of code, we're doing the exact same thing as we did before. Nothing changes. Then, here, what we're doing is we're doing the exact same thing as we're doing before, we're loading the index. Now, what I'm going to do is I'm going to get the query engine and I'm going to set the LM equal to the LM we created earlier. You can also do this with the global settings .llm that we showed in the last video. Or, if you'd like to change the LLM, you can change the LLM here. And I'll ask, let's ask, "When did the Big Star Collectibles Story Start?" "The Big Star Collectibles story began in 2013." Now let's ask, "Who started Big Star Collectibles?" "Big Star Collectibles was started by Saura Chen." And there you go. That's how you build a basic RAG application.
Contents
-
-
-
Architecture of a RAG app2m 33s
-
(Locked)
Introduction to LLM usage2m 30s
-
(Locked)
Introduction to embedding models55s
-
(Locked)
Introduction to vector databases1m 40s
-
(Locked)
Demo: Calling an LLM2m
-
(Locked)
Demo: Generating an embedding56s
-
(Locked)
Demo: Using a vector database2m 6s
-
(Locked)
Challenge: Putting it all together1m 13s
-
(Locked)
Solution: Putting it all together1m 22s
-
-
-