From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
49 lines
1.4 KiB
49 lines
1.4 KiB
WEBVTT |
|
|
|
00:00.920 --> 00:04.550 |
|
Well, welcome to the final part on rag. |
|
|
|
00:04.550 --> 00:10.310 |
|
And this is the session where you go from being a rag expert to being a rag master. |
|
|
|
00:10.520 --> 00:13.010 |
|
Uh, we are going to look today at a few things. |
|
|
|
00:13.010 --> 00:20.780 |
|
We're going to look at the Lang chain, LCL, the Lang chain expression language, which is where we |
|
|
|
00:20.780 --> 00:24.440 |
|
look at the declarative language for setting up these chains. |
|
|
|
00:24.560 --> 00:28.640 |
|
Uh, and it's not something we're going to use in earnest, but we'll take a look at it. |
|
|
|
00:28.790 --> 00:34.520 |
|
I'm going to talk a bit about how Lang Chain works behind the scenes, and we're going to fix and diagnose |
|
|
|
00:34.520 --> 00:37.700 |
|
some common problems that come up with rag. |
|
|
|
00:37.730 --> 00:41.600 |
|
And there's something else, something else that I just slipped in because I couldn't resist it. |
|
|
|
00:41.600 --> 00:44.120 |
|
Something that I said we could do that was really easy. |
|
|
|
00:44.150 --> 00:47.240 |
|
Uh, and I want to show you that we certainly can. |
|
|
|
00:47.240 --> 00:48.950 |
|
And in fact, we're going to do that right away. |
|
|
|
00:48.980 --> 00:54.470 |
|
So before we get on with the rest of today's activities, I'm going to take you to JupyterLab and show |
|
|
|
00:54.470 --> 01:01.070 |
|
you something that I just knocked up to prove a little point, but to also illustrate another vector |
|
|
|
01:01.070 --> 01:01.790 |
|
database. |
|
|
|
01:01.790 --> 01:02.690 |
|
See you there.
|
|
|