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

2
00:00:01,000 --> 00:00:06,000
So in this video we are going to discuss about Knowledge Graph.

3
00:00:06,000 --> 00:00:15,000
Now what exactly is a knowledge graph okay you can consider Knowledge Graph as a semantic network.

4
00:00:16,000 --> 00:00:20,000
Please focus on this keywords which I am actually specifying.

5
00:00:20,000 --> 00:00:25,000
It is also known as semantic networks.

6
00:00:25,000 --> 00:00:30,000
And this network represents a network of real world entities.

7
00:00:30,000 --> 00:00:32,000
So let me just go ahead and write this.

8
00:00:32,000 --> 00:00:41,000
This is nothing, but it is a network of real world entities.

9
00:00:41,000 --> 00:00:43,000
Very important thing.

10
00:00:43,000 --> 00:00:43,000
Okay.

11
00:00:44,000 --> 00:00:50,000
Now in this real world, uh, entities, you know, uh, if I just consider some example of the real

12
00:00:50,000 --> 00:00:57,000
world entities, I may probably say, hey, um, there may be some kind of events, right?

13
00:00:57,000 --> 00:01:01,000
There may be some kind of situations.

14
00:01:01,000 --> 00:01:04,000
There may be some kind of concepts.

15
00:01:05,000 --> 00:01:05,000
Right.

16
00:01:05,000 --> 00:01:17,000
And this concepts or this situation may illustrate may illustrate the relationship between them, The

17
00:01:17,000 --> 00:01:22,000
relationship between them.

18
00:01:22,000 --> 00:01:23,000
Okay.

19
00:01:23,000 --> 00:01:27,000
See, whenever we talk with respect to NLP, use cases.

20
00:01:29,000 --> 00:01:29,000
Right.

21
00:01:29,000 --> 00:01:32,000
Let's say I have a sentence.

22
00:01:32,000 --> 00:01:34,000
I have sentence like this.

23
00:01:34,000 --> 00:01:34,000
Okay.

24
00:01:34,000 --> 00:01:46,000
Let's say Rohit Sharma is the captain of Indian cricket team.

25
00:01:47,000 --> 00:01:48,000
Okay.

26
00:01:49,000 --> 00:01:53,000
Now here you can see when we consider this entire sentence.

27
00:01:54,000 --> 00:01:54,000
Okay.

28
00:01:54,000 --> 00:01:59,000
Here you will be able to see there are some important entities also.

29
00:01:59,000 --> 00:01:59,000
Right?

30
00:01:59,000 --> 00:02:03,000
I can probably say, hey here we are talking about Rohit Sharma who is a person.

31
00:02:03,000 --> 00:02:07,000
This is another one important keyword which is called as captain.

32
00:02:07,000 --> 00:02:11,000
And this is their Indian cricket team right.

33
00:02:11,000 --> 00:02:14,000
So we are here, we are able to specify from this particular sentence.

34
00:02:14,000 --> 00:02:19,000
And as a human being, I will definitely be or you will be definitely able to understand if you have

35
00:02:19,000 --> 00:02:26,000
the knowledge of cricket right here we say that, hey, Rohit Sharma is the captain of Indian cricket

36
00:02:26,000 --> 00:02:26,000
team.

37
00:02:26,000 --> 00:02:31,000
So Indian cricket team I can consider as a separate entity.

38
00:02:31,000 --> 00:02:36,000
Rohit Sharma is a separate entity and there is kind of situation.

39
00:02:36,000 --> 00:02:41,000
There is a kind of relationship between Rohit Sharma and Indian cricket team.

40
00:02:41,000 --> 00:02:41,000
That is nothing.

41
00:02:41,000 --> 00:02:44,000
But it is with respect to the captain, right?

42
00:02:44,000 --> 00:02:51,000
So obviously when we take this entire sentence for us human beings, we can definitely understand what

43
00:02:51,000 --> 00:02:52,000
exactly the sentence is.

44
00:02:53,000 --> 00:02:57,000
But to make a machine learn much more efficiently, right?

45
00:02:57,000 --> 00:03:02,000
It is a better way that we can actually represent this data in some different way.

46
00:03:02,000 --> 00:03:03,000
Right?

47
00:03:03,000 --> 00:03:05,000
And that specific way is what we are going to talk about.

48
00:03:05,000 --> 00:03:07,000
That is nothing but knowledge graph.

49
00:03:08,000 --> 00:03:14,000
Now let's talk more about this and you will definitely get a really good idea about this.

50
00:03:14,000 --> 00:03:14,000
Okay.

51
00:03:14,000 --> 00:03:17,000
So here you'll be able to see a knowledge graph.

52
00:03:19,000 --> 00:03:23,000
if I just consider about our knowledge graph.

53
00:03:27,000 --> 00:03:28,000
Okay.

54
00:03:28,000 --> 00:03:36,000
It is made up of three main components.

55
00:03:37,000 --> 00:03:39,000
Let's talk about this particular components.

56
00:03:39,000 --> 00:03:43,000
One is something called as nodes okay.

57
00:03:44,000 --> 00:03:48,000
Second is something called as edges.

58
00:03:49,000 --> 00:03:54,000
And third is something called as labels.

59
00:03:55,000 --> 00:03:55,000
Okay.

60
00:03:56,000 --> 00:04:04,000
Now let's see what this exactly nodes specify I can say hey any object.

61
00:04:07,000 --> 00:04:12,000
Or any place or a person.

62
00:04:14,000 --> 00:04:14,000
Okay.

63
00:04:14,000 --> 00:04:15,000
I'm just giving some example.

64
00:04:16,000 --> 00:04:19,000
Can be a node.

65
00:04:20,000 --> 00:04:20,000
Right.

66
00:04:20,000 --> 00:04:22,000
So here what we are specifying a node.

67
00:04:22,000 --> 00:04:23,000
What exactly is a node.

68
00:04:24,000 --> 00:04:30,000
Node basically means it can be in any object, any person, any place or any noun.

69
00:04:30,000 --> 00:04:32,000
You can also consider it as a noun, right?

70
00:04:32,000 --> 00:04:33,000
Can be a node.

71
00:04:33,000 --> 00:04:39,000
Okay, if I talk about edges, right?

72
00:04:40,000 --> 00:04:42,000
An edge

73
00:04:44,000 --> 00:04:57,000
defines the relationship between the nodes.

74
00:04:58,000 --> 00:04:59,000
Okay.

75
00:04:59,000 --> 00:05:04,000
So edge is what it defines the relationship between the nodes.

76
00:05:04,000 --> 00:05:05,000
Right.

77
00:05:05,000 --> 00:05:11,000
So here if I just consider right some examples.

78
00:05:12,000 --> 00:05:12,000
Okay.

79
00:05:12,000 --> 00:05:18,000
And uh my example is something like Rohit Sharma is the captain of Indian cricket team.

80
00:05:18,000 --> 00:05:18,000
Okay.

81
00:05:18,000 --> 00:05:20,000
So let's talk about this okay.

82
00:05:20,000 --> 00:05:22,000
So here I will.

83
00:05:22,000 --> 00:05:26,000
You know that an object, place or person can be a node okay.

84
00:05:26,000 --> 00:05:29,000
And here you'll be able to see that I will go ahead and create this node.

85
00:05:30,000 --> 00:05:35,000
This is my first node here I'm just going to write Rohit Sharma okay.

86
00:05:35,000 --> 00:05:37,000
So let me write it in another color.

87
00:05:37,000 --> 00:05:44,000
So let's say here I'm going to basically write Rohit Sharma Okay.

88
00:05:44,000 --> 00:05:46,000
My second node.

89
00:05:47,000 --> 00:05:52,000
If I draw it over here is nothing but Indian cricket team.

90
00:05:55,000 --> 00:05:56,000
Indian.

91
00:05:58,000 --> 00:06:01,000
Cricket team.

92
00:06:01,000 --> 00:06:02,000
Okay.

93
00:06:02,000 --> 00:06:05,000
Now we know that according to the sentence, we are saying.

94
00:06:05,000 --> 00:06:08,000
Hey, Rohit Sharma is the captain of Indian cricket team.

95
00:06:08,000 --> 00:06:14,000
So when we say, hey, he's the captain of Indian cricket team, that basically means we are trying

96
00:06:14,000 --> 00:06:15,000
to show some relationship over here.

97
00:06:15,000 --> 00:06:19,000
So Rohit Sharma is somewhere related to this Indian cricket team.

98
00:06:20,000 --> 00:06:25,000
And that is where your third component comes into label right.

99
00:06:25,000 --> 00:06:30,000
In order to specify what kind of relationship is there with respect to this particular node, that is

100
00:06:30,000 --> 00:06:32,000
where we are going to use this label.

101
00:06:32,000 --> 00:06:37,000
And here the label will be nothing, but it will be something called as captain.

102
00:06:38,000 --> 00:06:38,000
Right.

103
00:06:38,000 --> 00:06:45,000
So this is how in a knowledge graph this entire sentence is basically represented.

104
00:06:46,000 --> 00:06:46,000
Okay.

105
00:06:46,000 --> 00:06:50,000
Rohit Sharma is the captain of Indian cricket team right now.

106
00:06:50,000 --> 00:06:54,000
Why do you want to represent.

107
00:06:54,000 --> 00:06:55,000
Just think over this okay?

108
00:06:55,000 --> 00:07:04,000
Why do you specifically want to represent right the data specifically in this kind of nodes and edges

109
00:07:04,000 --> 00:07:05,000
and labels.

110
00:07:05,000 --> 00:07:07,000
This is really much important to understand.

111
00:07:08,000 --> 00:07:10,000
Understand this is just one of the text.

112
00:07:10,000 --> 00:07:15,000
I may have another text over here okay I may have some text like this.

113
00:07:15,000 --> 00:07:18,000
Virat Kohli I hope everybody knows about this.

114
00:07:18,000 --> 00:07:20,000
Two famous people, right?

115
00:07:20,000 --> 00:07:30,000
Is the player of Indian cricket team now I have used my second sentence.

116
00:07:31,000 --> 00:07:34,000
Okay, I have used a second sentence.

117
00:07:34,000 --> 00:07:37,000
Virat Kohli is the player of Indian cricket team.

118
00:07:37,000 --> 00:07:42,000
So in this scenario, what I will do, I will just go ahead and create my another node.

119
00:07:42,000 --> 00:07:45,000
And in this node we will go ahead and write Virat Kohli.

120
00:07:48,000 --> 00:07:50,000
Write Virat Kohli.

121
00:07:50,000 --> 00:08:00,000
Now when we write Virat Kohli over here, right, you'll be able to see that Virat Kohli is a player,

122
00:08:00,000 --> 00:08:01,000
right?

123
00:08:01,000 --> 00:08:07,000
So this is Virat Kohli is basically related to the Indian cricket team with the label that is nothing

124
00:08:07,000 --> 00:08:10,000
but player, right?

125
00:08:10,000 --> 00:08:14,000
So this becomes another relationship, right?

126
00:08:14,000 --> 00:08:19,000
Now finally, you can see that if Rohit Sharma is the captain of Indian cricket team and Virat Kohli

127
00:08:19,000 --> 00:08:26,000
is a player of Indian cricket team, let's say that if we go ahead and ask our or along with this,

128
00:08:26,000 --> 00:08:31,000
if we just go ahead and create a Genie application along with my login and some LLM modules, don't

129
00:08:31,000 --> 00:08:38,000
you think that with respect to this specific relationship, you know there can be some relationship

130
00:08:38,000 --> 00:08:40,000
between Rohit Sharma and Virat Kohli?

131
00:08:40,000 --> 00:08:41,000
We can derive that right?

132
00:08:41,000 --> 00:08:44,000
And that is what this entire knowledge graph does.

133
00:08:45,000 --> 00:08:51,000
Not only this, there may be more nodes, more nodes which may be related over here.

134
00:08:51,000 --> 00:08:53,000
This will be related to.

135
00:08:54,000 --> 00:08:55,000
Let me just go ahead and write this.

136
00:08:55,000 --> 00:08:57,000
This may be related to here.

137
00:08:57,000 --> 00:09:01,000
There may be again another relationship which you can specifically derive.

138
00:09:01,000 --> 00:09:04,000
This will be another relationship which can be connected to this.

139
00:09:05,000 --> 00:09:05,000
Right.

140
00:09:05,000 --> 00:09:07,000
So so many different different connection.

141
00:09:07,000 --> 00:09:14,000
And just imagine when you have this huge amount of data, when this kind of graph is basically created

142
00:09:14,000 --> 00:09:16,000
and this is nothing, but this is my knowledge graph.

143
00:09:17,000 --> 00:09:21,000
And based on this knowledge graph we can derive many, many things.

144
00:09:22,000 --> 00:09:25,000
Even our recent like in Google, the search engine.

145
00:09:27,000 --> 00:09:28,000
Google search engine, right?

146
00:09:29,000 --> 00:09:38,000
Let's say if I am searching for Virat Kohli or Virat Kohli, then after getting the result of Virat

147
00:09:38,000 --> 00:09:42,000
Kohli, I may get some suggestion with respect to other players.

148
00:09:43,000 --> 00:09:44,000
Let's say like Rohit Sharma.

149
00:09:46,000 --> 00:09:51,000
How this is possible because Virat Kohli, you know that it is playing under Indian cricket team.

150
00:09:51,000 --> 00:09:54,000
We get to know more about Indian cricket team along with Virat Kohli.

151
00:09:54,000 --> 00:09:58,000
All the information that you will be seeing and more suggestions will be able to get about Rohit Sharma.

152
00:09:59,000 --> 00:10:04,000
And that is how this entire Google search engine will be able to derive information that are related

153
00:10:04,000 --> 00:10:05,000
to Virat Kohli.

154
00:10:05,000 --> 00:10:12,000
Because this entire graph, this entire knowledge of graph is connected to each other right between

155
00:10:12,000 --> 00:10:14,000
nodes with respect to relationships.

156
00:10:14,000 --> 00:10:17,000
And that is how each and every suggestions that you will be able to see.

157
00:10:19,000 --> 00:10:22,000
And this gives you a clear idea about knowledge graph.

158
00:10:23,000 --> 00:10:24,000
Now let me do one thing.

159
00:10:24,000 --> 00:10:30,000
Let me just go ahead and show you some of the amazing examples directly in Google Chrome, because Google

160
00:10:30,000 --> 00:10:35,000
search engine is the best example of specifically using this kind of knowledge graph.

161
00:10:36,000 --> 00:10:36,000
Okay.

162
00:10:36,000 --> 00:10:38,000
So let's go ahead and see that.

163
00:10:38,000 --> 00:10:41,000
So guys now let's go ahead and see some examples from the Google search engine.

164
00:10:41,000 --> 00:10:48,000
Because I feel that Google search engine is one of the best example to probably showcase the working

165
00:10:48,000 --> 00:10:49,000
of the Knowledge graph.

166
00:10:49,000 --> 00:10:54,000
So here right now, uh, I have not even signed in in my Google account.

167
00:10:54,000 --> 00:10:59,000
The reason is very simple because I do not want my search history to impact the kind of queries that

168
00:10:59,000 --> 00:11:00,000
I'm actually searching.

169
00:11:00,000 --> 00:11:05,000
Okay, so here, uh, if I just go ahead and click it, these are all the trending stories, uh, trending

170
00:11:05,000 --> 00:11:08,000
searches that are probably showing up over here.

171
00:11:08,000 --> 00:11:10,000
So let me do one thing to start with.

172
00:11:10,000 --> 00:11:12,000
I'm just going to take a basic example.

173
00:11:12,000 --> 00:11:12,000
Okay.

174
00:11:12,000 --> 00:11:15,000
So I'll go and search for my name Krishna.

175
00:11:15,000 --> 00:11:17,000
So let me just go ahead and search okay.

176
00:11:18,000 --> 00:11:21,000
So here you'll be able to see that I'm able to find out some of the information.

177
00:11:21,000 --> 00:11:23,000
It says, hey, I'm a YouTuber.

178
00:11:23,000 --> 00:11:26,000
Along with that, I also upload videos on Udemy, as you all know.

179
00:11:26,000 --> 00:11:33,000
Um, along with that here, you'll be able to see that I have my profiles LinkedIn, Instagram, YouTube.

180
00:11:33,000 --> 00:11:33,000
Right?

181
00:11:34,000 --> 00:11:39,000
And here it is also specifying what all books you have actually written about me.

182
00:11:39,000 --> 00:11:42,000
This entire Google is providing it, right?

183
00:11:42,000 --> 00:11:49,000
So once I search for Kreshnik, you can see that since I, I have been using Google products for a long

184
00:11:49,000 --> 00:11:52,000
period of time, like I've been using Gmail, I've been using Google.

185
00:11:52,000 --> 00:11:54,000
I have my own Google account, right?

186
00:11:54,000 --> 00:12:00,000
You'll be able to see that it actually has taken my entire data, and it has created that kind of knowledge

187
00:12:00,000 --> 00:12:05,000
graph, because when I search for my name, it is showing my YouTube channel.

188
00:12:05,000 --> 00:12:09,000
If I go ahead and see in the videos, so many different, different videos are there with respect to

189
00:12:09,000 --> 00:12:10,000
my YouTube channel.

190
00:12:10,000 --> 00:12:15,000
Not only that, people also search for what kind of important suggestions are there that also you are

191
00:12:15,000 --> 00:12:18,000
able to see, right how this is entirely possible.

192
00:12:18,000 --> 00:12:24,000
It is very simple that it is uh, it is possible because that entire knowledge graph is actually present

193
00:12:24,000 --> 00:12:29,000
with Google, and based on that knowledge graph, it is being able to retrieve lot of information.

194
00:12:29,000 --> 00:12:33,000
Now, when I'm searching the specific information, let's take a different example.

195
00:12:33,000 --> 00:12:35,000
I will go ahead and write Einstein.

196
00:12:35,000 --> 00:12:35,000
Okay.

197
00:12:35,000 --> 00:12:39,000
So let me just go and search for Albert Einstein.

198
00:12:39,000 --> 00:12:44,000
Now in the case of Albert Einstein here you can see theoretical physicist is basically their overview

199
00:12:44,000 --> 00:12:45,000
education.

200
00:12:46,000 --> 00:12:50,000
And now this person like Einstein was born on 14th March 1879.

201
00:12:50,000 --> 00:12:53,000
And he died and he died on 18th April 1955.

202
00:12:53,000 --> 00:12:54,000
Right.

203
00:12:54,000 --> 00:12:56,000
So here you'll be able to see about Einstein.

204
00:12:56,000 --> 00:13:00,000
We are able to see all the information and whatever research he has specifically done.

205
00:13:00,000 --> 00:13:05,000
All those research will also be visible as we go ahead over here right now.

206
00:13:05,000 --> 00:13:09,000
This is what is there in the in the in the knowledge graph.

207
00:13:09,000 --> 00:13:09,000
Right.

208
00:13:09,000 --> 00:13:11,000
How Albert Einstein is basically connected.

209
00:13:11,000 --> 00:13:12,000
Now this is really important.

210
00:13:12,000 --> 00:13:14,000
So this is all information will be able to see about Einstein.

211
00:13:14,000 --> 00:13:15,000
Right.

212
00:13:15,000 --> 00:13:18,000
All the information influence spouse grandchildren children.

213
00:13:18,000 --> 00:13:20,000
All this information is there okay.

214
00:13:20,000 --> 00:13:20,000
Perfect.

215
00:13:21,000 --> 00:13:26,000
Now if you go ahead and see here, you can see people also search for these all famous people.

216
00:13:26,000 --> 00:13:32,000
Now here you have Edward Einstein, you have Isaac Newton, you have Stephen Hawking.

217
00:13:32,000 --> 00:13:33,000
Wright Hawking.

218
00:13:33,000 --> 00:13:39,000
Why all these researchers are like given as a suggestion for you.

219
00:13:39,000 --> 00:13:44,000
The idea is very simple because Albert Einstein was a researcher, right?

220
00:13:44,000 --> 00:13:45,000
And theoretical physicist.

221
00:13:45,000 --> 00:13:49,000
He was theoretical physicist who created this amazing research.

222
00:13:49,000 --> 00:13:54,000
He did amazing research on different, different concepts, different different things, and that all

223
00:13:54,000 --> 00:13:56,000
are available in the internet, right?

224
00:13:56,000 --> 00:14:00,000
And based on that, you're able to see that they are also trying to find out the link with respect to

225
00:14:00,000 --> 00:14:02,000
other researchers like Isaac Newton.

226
00:14:02,000 --> 00:14:03,000
Right.

227
00:14:03,000 --> 00:14:10,000
Because Isaac Newton were also there at this particular time frame when gravity was probably, uh,

228
00:14:10,000 --> 00:14:15,000
you know, that Apple fell on his head and he was able to completely invent gravity completely through

229
00:14:15,000 --> 00:14:16,000
his research.

230
00:14:16,000 --> 00:14:16,000
Right.

231
00:14:16,000 --> 00:14:18,000
So here you could see that.

232
00:14:18,000 --> 00:14:23,000
Then you have Stephen Hawking's, you know, so all this information, how they are actually related

233
00:14:23,000 --> 00:14:25,000
to Einstein, that is basically shown over here.

234
00:14:25,000 --> 00:14:28,000
And that is all possible because of this knowledge graph.

235
00:14:29,000 --> 00:14:29,000
Right?

236
00:14:29,000 --> 00:14:34,000
Obviously when I'm searching for Albert Einstein, Albert Einstein, uh, when I search for Albert Einstein,

237
00:14:34,000 --> 00:14:37,000
uh, they're not going to give the suggestion of my name over there.

238
00:14:37,000 --> 00:14:43,000
The idea is very simple over there, because I am nowhere related right, to Albert Einstein in terms

239
00:14:43,000 --> 00:14:45,000
of research or anything else.

240
00:14:45,000 --> 00:14:47,000
So it is completely different, right?

241
00:14:47,000 --> 00:14:53,000
So that is how in this world, since there are huge amount of data that is available in Google, right?

242
00:14:53,000 --> 00:14:58,000
And there you'll be able to see that this kind of knowledge graph is created with respect to nodes,

243
00:14:58,000 --> 00:14:59,000
edges and labels.

244
00:14:59,000 --> 00:14:59,000
Right?

245
00:14:59,000 --> 00:15:04,000
And that is how this entire Google search engine is working behind that, right?

246
00:15:04,000 --> 00:15:10,000
Even YouTube search, completely YouTube search, the kinds of ad that is visible on you are like what

247
00:15:10,000 --> 00:15:11,000
kind of ads you will be have.

248
00:15:11,000 --> 00:15:12,000
You'll be able to see it.

249
00:15:12,000 --> 00:15:16,000
That entire thing is controlled by this graph knowledge knowledge graph itself.

250
00:15:16,000 --> 00:15:16,000
Right?

251
00:15:17,000 --> 00:15:20,000
So I hope you are able to get an idea about knowledge Graph.

252
00:15:20,000 --> 00:15:25,000
And I hope I was able to explain you this in a pretty easy way.

253
00:15:25,000 --> 00:15:31,000
Okay, so in the upcoming videos we are going to discuss about Neo4j's graph database.

254
00:15:31,000 --> 00:15:34,000
Uh, and yeah, I just want to show you one more example over here.

255
00:15:34,000 --> 00:15:35,000
Uh, let me hide this.

256
00:15:35,000 --> 00:15:39,000
So this is what a neo4j's database looks like okay.

257
00:15:39,000 --> 00:15:43,000
And I have inserted huge amount of data over here just to try out multiple things.

258
00:15:43,000 --> 00:15:43,000
Okay.

259
00:15:44,000 --> 00:15:46,000
So let's say there is a relationship over here.

260
00:15:46,000 --> 00:15:50,000
I'll just, uh, and one of the relationship is something like chief Executive Officer.

261
00:15:50,000 --> 00:15:54,000
So once I click this here, you'll be able to see this is the this is the query that you are able to

262
00:15:54,000 --> 00:15:55,000
see over here.

263
00:15:55,000 --> 00:15:58,000
And this query is basically called as a Cypher query okay.

264
00:15:58,000 --> 00:16:05,000
So usually whenever you work with the graph database, uh in the graph database you specifically get

265
00:16:05,000 --> 00:16:06,000
this kind of Cypher query.

266
00:16:06,000 --> 00:16:06,000
Okay.

267
00:16:07,000 --> 00:16:12,000
Uh, so this based on this Cypher query, you can see that as soon as I selected a relationship, like

268
00:16:12,000 --> 00:16:14,000
chief executive officer, it shows.

269
00:16:14,000 --> 00:16:18,000
Hey, Elon Musk is a chief executive officer of Tesla, right?

270
00:16:18,000 --> 00:16:22,000
Not only that, uh, let's, uh, select some more thing, right?

271
00:16:22,000 --> 00:16:25,000
Like trillion dollar, uh, trillion dollar company.

272
00:16:25,000 --> 00:16:27,000
So here you can see Tesla is $1 trillion company.

273
00:16:27,000 --> 00:16:28,000
Right.

274
00:16:28,000 --> 00:16:30,000
And this is the query, uh, that is there.

275
00:16:30,000 --> 00:16:32,000
I'll try to show you.

276
00:16:32,000 --> 00:16:36,000
I'll give a tutorial with respect to the Cypher query as we go ahead in the series of video.

277
00:16:36,000 --> 00:16:38,000
Okay then, uh, let's select some more.

278
00:16:38,000 --> 00:16:38,000
Okay.

279
00:16:38,000 --> 00:16:41,000
So here you can see there are nodes okay.

280
00:16:41,000 --> 00:16:45,000
Nodes are over here there are relationship and there are property keys.

281
00:16:45,000 --> 00:16:46,000
Property keys are nothing.

282
00:16:46,000 --> 00:16:51,000
But it's just like a uh you can you can just see that, uh, relationship are nothing but this specific

283
00:16:51,000 --> 00:16:53,000
relationship along with the label.

284
00:16:53,000 --> 00:16:57,000
If I go ahead and click on property keys, let's select one of them.

285
00:16:57,000 --> 00:16:57,000
Okay.

286
00:16:57,000 --> 00:17:03,000
There you'll be able to see some values that are really related to this kind of searches that we specifically

287
00:17:03,000 --> 00:17:04,000
do.

288
00:17:04,000 --> 00:17:06,000
But anyhow I will try to show it to you.

289
00:17:06,000 --> 00:17:09,000
Uh, some more examples if I try to go ahead and show you over here.

290
00:17:09,000 --> 00:17:11,000
Okay, let's see some more things.

291
00:17:11,000 --> 00:17:12,000
Right.

292
00:17:12,000 --> 00:17:13,000
Let's say best selling is there.

293
00:17:13,000 --> 00:17:14,000
Okay.

294
00:17:14,000 --> 00:17:15,000
Now here you can see Tesla.

295
00:17:15,000 --> 00:17:19,000
Uh, there is two best selling models that is model Y and model three.

296
00:17:19,000 --> 00:17:19,000
Right.

297
00:17:19,000 --> 00:17:23,000
And this is the query that you have with respect to that.

298
00:17:23,000 --> 00:17:28,000
Right Then um, let's say I will go ahead and do select one more thing.

299
00:17:28,000 --> 00:17:29,000
Inspiration okay.

300
00:17:29,000 --> 00:17:35,000
So here you can see, uh, a piece of writing inspiration, all this information, how it is there a

301
00:17:35,000 --> 00:17:40,000
piece of writing that expresses emotions or ideas in a rhythmic and imaginative way?

302
00:17:40,000 --> 00:17:41,000
This is a poem, right?

303
00:17:41,000 --> 00:17:46,000
I've taken a poem I've inserted into the entire graph database automatically from that particular graph

304
00:17:46,000 --> 00:17:51,000
database, Since I've used this neo4j's along with lang chain, you'll be able to see that automatically.

305
00:17:51,000 --> 00:17:52,000
This nodes are.

306
00:17:52,000 --> 00:17:57,000
We are able to create it, and not only nodes, we are also able to create this kind of relationships

307
00:17:57,000 --> 00:17:57,000
itself.

308
00:17:57,000 --> 00:17:57,000
Right.

309
00:17:58,000 --> 00:18:01,000
So all these things we will proceed and we'll see.

310
00:18:01,000 --> 00:18:06,000
It'll be quite amazing and interesting when we will be starting this from this completely scratch and

311
00:18:06,000 --> 00:18:07,000
will be understanding more about it.

312
00:18:07,000 --> 00:18:09,000
So I hope you like this particular video.

313
00:18:09,000 --> 00:18:11,000
Uh, this was it for my side.

314
00:18:11,000 --> 00:18:12,000
I'll see you all in the next video.

315
00:18:12,000 --> 00:18:12,000
Thank you.