1
00:00:00,000 --> 00:00:01,000
Hello guys.

2
00:00:01,000 --> 00:00:06,000
Welcome to this new amazing module on building generative AI application using Landgraff.

3
00:00:06,000 --> 00:00:10,000
Now Landgraff is an amazing library that is available in long chain and with the help of Landgraff,

4
00:00:10,000 --> 00:00:17,000
you will be able to build stateful multi actor application with Llms used to create agents and multi-agent

5
00:00:17,000 --> 00:00:17,000
workflows.

6
00:00:17,000 --> 00:00:18,000
Right?

7
00:00:18,000 --> 00:00:23,000
And one amazing thing about this agents will be that they will also be able to communicate with each

8
00:00:23,000 --> 00:00:24,000
other, right?

9
00:00:24,000 --> 00:00:29,000
Specifically, if you're working in some data science projects, you know, you'll be having data analysts,

10
00:00:29,000 --> 00:00:33,000
you'll be having data scientists, you will be having product managers, you'll be having program managers.

11
00:00:33,000 --> 00:00:38,000
And, you know, while developing the entire project, there will be a lot of communication with all

12
00:00:38,000 --> 00:00:39,000
these specific roles, right?

13
00:00:39,000 --> 00:00:43,000
With respect to requirements, with respect to development and many more things.

14
00:00:43,000 --> 00:00:48,000
Now we can actually create those kind of projects with the help of completely different, different

15
00:00:48,000 --> 00:00:49,000
multi agents.

16
00:00:49,000 --> 00:00:54,000
You know, each and every agent can specifically perform different different tasks.

17
00:00:54,000 --> 00:01:01,000
Let's say for my project, I want to probably create a multi-agent, uh generative AI application where

18
00:01:01,000 --> 00:01:05,000
I may have a data analyst, I may have a data scientist, I may have a program manager.

19
00:01:05,000 --> 00:01:10,000
And I can probably implement all the functionalities with the help of this AI agents itself.

20
00:01:11,000 --> 00:01:11,000
Right?

21
00:01:11,000 --> 00:01:17,000
And that is what in order to efficiently manage this entire workflow and the stateful management, we

22
00:01:17,000 --> 00:01:18,000
specifically use line graph.

23
00:01:18,000 --> 00:01:19,000
Okay.

24
00:01:19,000 --> 00:01:23,000
Now in the upcoming videos, you'll be seeing some amazing projects where I will be showing you the

25
00:01:23,000 --> 00:01:24,000
importance of line graph.

26
00:01:24,000 --> 00:01:30,000
Now, compared to other LLM frameworks, it offers this core benefits, that is cycle controllability

27
00:01:30,000 --> 00:01:31,000
and persistence.

28
00:01:31,000 --> 00:01:37,000
Line graphs allows you to define the flows that involves cycles essential for most Agentic uh, architectures,

29
00:01:37,000 --> 00:01:40,000
differentiating it from uh Dag based solutions.

30
00:01:40,000 --> 00:01:45,000
Okay, so there will be a lot of things that we will be discussing as we go ahead.

31
00:01:45,000 --> 00:01:49,000
Um, why this module or why this library is super important?

32
00:01:49,000 --> 00:01:57,000
Because, see, uh, if you have already seen this particular post lang graph or what Lang has actually

33
00:01:57,000 --> 00:02:01,000
done is that they are also coming up with this Lang Graph Studio.

34
00:02:01,000 --> 00:02:06,000
Okay, now, with the help of this studio, what you will be able to do is that you will be able to

35
00:02:06,000 --> 00:02:09,000
create all these workflows just by drag and drop.

36
00:02:09,000 --> 00:02:12,000
Right now, this particular studio is just available in Mac.

37
00:02:12,000 --> 00:02:18,000
Okay, but don't worry, as soon as it gets uploaded from both Windows and Mac, I will start making

38
00:02:18,000 --> 00:02:19,000
the videos on that.

39
00:02:19,000 --> 00:02:24,000
Also just by doing drag and drop here you can see just by doing drag and drop you will be able to implement

40
00:02:24,000 --> 00:02:26,000
the entire workflows.

41
00:02:26,000 --> 00:02:32,000
And right now in our course till this entire studio does not come as an open source availability.

42
00:02:32,000 --> 00:02:36,000
What we will do, we will try to write the code for all these things, okay.

43
00:02:36,000 --> 00:02:40,000
And that will be the best thing to probably learn, because once you learn all those things, working

44
00:02:40,000 --> 00:02:42,000
with the studio will be super easy, right?

45
00:02:42,000 --> 00:02:45,000
So here you can just see an example, right?

46
00:02:45,000 --> 00:02:49,000
When we are specifically running this entire workflow.

47
00:02:49,000 --> 00:02:49,000
Right?

48
00:02:49,000 --> 00:02:51,000
How step by step it is able to run.

49
00:02:51,000 --> 00:02:51,000
Right.

50
00:02:51,000 --> 00:02:54,000
So here you can also see here you can also see an example.

51
00:02:54,000 --> 00:02:59,000
This is my workflow that is probably running up I'll ask a specific question who created you.

52
00:02:59,000 --> 00:03:02,000
So step by step it will probably go to the agent.

53
00:03:02,000 --> 00:03:03,000
It will take an action.

54
00:03:03,000 --> 00:03:05,000
It will go and execute each and every code.

55
00:03:05,000 --> 00:03:08,000
And it will go ahead and execute and show us the output response.

56
00:03:08,000 --> 00:03:10,000
That is the most amazing thing, right?

57
00:03:10,000 --> 00:03:15,000
So, uh, right now in this upcoming series, what we are going to do, first of all, we are going

58
00:03:15,000 --> 00:03:18,000
to develop this with the help of Python programming language.

59
00:03:18,000 --> 00:03:21,000
And along with that we will also be using a library called as line graph.

60
00:03:21,000 --> 00:03:26,000
But once this studio is available, I will also show you all the examples with respect to that.

61
00:03:26,000 --> 00:03:27,000
And probably it should be available in some time.

62
00:03:28,000 --> 00:03:31,000
Okay, that I will keep a note on that and I'll keep on updating my course itself.

63
00:03:31,000 --> 00:03:35,000
So this was just about line graph to give you an introduction.

64
00:03:35,000 --> 00:03:38,000
But here please make sure that you remember this.

65
00:03:38,000 --> 00:03:43,000
It is a library for building stateful multi actor application with LMS used to create agents and multi-agent

66
00:03:43,000 --> 00:03:43,000
workflow.

67
00:03:43,000 --> 00:03:48,000
And this agents will be able to communicate with itself and it will be able to perform various tasks.

68
00:03:48,000 --> 00:03:53,000
And that is what I'm actually going to show you in the next video where we will deep dive more into

69
00:03:53,000 --> 00:03:56,000
line graph and we will be developing some good projects.

70
00:03:56,000 --> 00:03:58,000
So yes, this was it from my side.

71
00:03:58,000 --> 00:04:03,000
One very important thing that I really also want to note that we will first of all start with Google

72
00:04:03,000 --> 00:04:03,000
Colab, right?

73
00:04:03,000 --> 00:04:09,000
We will work with Google Colab wherein we will go ahead and write our code, will execute and show you

74
00:04:09,000 --> 00:04:09,000
each and everything.

75
00:04:09,000 --> 00:04:11,000
Let's say I will give you one example.

76
00:04:11,000 --> 00:04:18,000
This is one of the first project that we will specifically work on, where we will create a simple chatbot

77
00:04:18,000 --> 00:04:19,000
application with the help of line graph.

78
00:04:19,000 --> 00:04:23,000
And here you will be able to see that this kind of graphs will also be visible.

79
00:04:23,000 --> 00:04:27,000
These are nothing but these are nodes right These are relationship that also we have learned in the

80
00:04:27,000 --> 00:04:28,000
graph database.

81
00:04:28,000 --> 00:04:31,000
And we'll see step by step how we will be executing all these things.

82
00:04:31,000 --> 00:04:32,000
Right.

83
00:04:32,000 --> 00:04:34,000
So yes this was it from my side.

84
00:04:34,000 --> 00:04:35,000
I will see you all in the next video.

85
00:04:35,000 --> 00:04:36,000
Thank you.