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

2
00:00:01,000 --> 00:00:04,000
So we are going to continue our discussion with respect to login with Graphdb.

3
00:00:04,000 --> 00:00:11,000
Now I will be showing you like what generative AI project that we are specifically going to create with

4
00:00:11,000 --> 00:00:13,000
the help of Lang Chain along with Graphdb.

5
00:00:13,000 --> 00:00:16,000
Okay, so here the plan is very simple.

6
00:00:16,000 --> 00:00:26,000
Let's say if a user queries right, let's say if a user is querying anything right now with respect

7
00:00:26,000 --> 00:00:32,000
to this specific query, this will probably initially go to our LMS, right?

8
00:00:32,000 --> 00:00:34,000
My LM models.

9
00:00:34,000 --> 00:00:37,000
Let's consider this as my LM model.

10
00:00:37,000 --> 00:00:43,000
Now this LM model, what it should be doing is that it should be creating my Cypher query.

11
00:00:45,000 --> 00:00:47,000
Cypher query.

12
00:00:48,000 --> 00:00:53,000
Let's say if I go ahead and say, hey, who was this particular person who was acting in this particular

13
00:00:53,000 --> 00:00:54,000
movie?

14
00:00:54,000 --> 00:01:00,000
If I asked that question to my LLM, my LLM should be able to create my Cypher query, and once I get

15
00:01:00,000 --> 00:01:06,000
my Cypher query, it should be able to probably query from our graph DB database.

16
00:01:06,000 --> 00:01:07,000
Right.

17
00:01:07,000 --> 00:01:09,000
Let's say this is my graph db database.

18
00:01:14,000 --> 00:01:15,000
Okay.

19
00:01:15,000 --> 00:01:21,000
And once it is able to query right again, it should probably get the response from this.

20
00:01:21,000 --> 00:01:22,000
Give it to my LM model.

21
00:01:23,000 --> 00:01:30,000
And based on our prompt it should be able to give our output okay output response.

22
00:01:32,000 --> 00:01:37,000
So uh this is the entire thing that we are specifically going to create.

23
00:01:37,000 --> 00:01:40,000
And if I probably consider this entire thing this block.

24
00:01:40,000 --> 00:01:41,000
Right.

25
00:01:42,000 --> 00:01:48,000
This block where we are specifically using LM, uh, Cypher query graph DB.

26
00:01:48,000 --> 00:01:49,000
So this is my.

27
00:01:52,000 --> 00:01:54,000
Graph DB right.

28
00:01:54,000 --> 00:01:58,000
This is specifically called as graph agent.

29
00:01:59,000 --> 00:02:06,000
But here instead of, you know, only generating a Cypher query, we are also going to use a graph DB,

30
00:02:06,000 --> 00:02:11,000
and we are going to query with respect to the specific query that the user is putting.

31
00:02:11,000 --> 00:02:17,000
And once we get the output, we should basically be able to combine with a prompt along with the my

32
00:02:17,000 --> 00:02:19,000
LM model and get my output response.

33
00:02:19,000 --> 00:02:28,000
Okay, so this is the entire project that we are going to develop with respect to our, uh, that we

34
00:02:28,000 --> 00:02:30,000
are specifically planning in this particular project.

35
00:02:30,000 --> 00:02:30,000
Okay.

36
00:02:31,000 --> 00:02:35,000
So let's go ahead and, uh, let's generate this particular project.

37
00:02:35,000 --> 00:02:38,000
So I'll just go ahead and write one.

38
00:02:38,000 --> 00:02:44,000
And uh, I will keep this like Q&A, right.

39
00:02:44,000 --> 00:02:48,000
Q&A with graph I will write graph DB.

40
00:02:50,000 --> 00:02:51,000
Okay.

41
00:02:51,000 --> 00:02:52,000
So this is done I guess.

42
00:02:52,000 --> 00:02:59,000
Now the first thing first what I will do is that inside this folder I will go ahead and create my experiments

43
00:02:59,000 --> 00:03:00,000
dot p Ipynb file.

44
00:03:00,000 --> 00:03:04,000
So that will get an idea how to probably go ahead and start this.

45
00:03:04,000 --> 00:03:04,000
Okay.

46
00:03:05,000 --> 00:03:08,000
So first of all we will go ahead and select our kernel.

47
00:03:08,000 --> 00:03:14,000
Once we go ahead and select our kernel I am just going to go ahead and create a markdown.

48
00:03:18,000 --> 00:03:21,000
Let's say over here I'm going to use this three quotes.

49
00:03:21,000 --> 00:03:21,000
Okay.

50
00:03:21,000 --> 00:03:27,000
So here we are basically going to build a question answer application over a graph database okay.

51
00:03:27,000 --> 00:03:34,000
So to start with uh the first thing that you actually require is all this information right.

52
00:03:34,000 --> 00:03:38,000
So here at least you have this URI username password right.

53
00:03:38,000 --> 00:03:41,000
Instance ID and instance name is not required.

54
00:03:41,000 --> 00:03:45,000
So I will just go ahead and initialize this right over here.

55
00:03:46,000 --> 00:03:49,000
So let's convert this into strings.

56
00:03:49,000 --> 00:03:52,000
So I will just go ahead and initialize all these things.

57
00:03:52,000 --> 00:03:56,000
Or you can also directly put it in your environment variable if you want.

58
00:03:56,000 --> 00:03:57,000
Okay.

59
00:03:57,000 --> 00:04:00,000
And you can probably read from those environment variable okay.

60
00:04:00,000 --> 00:04:01,000
It is up to you.

61
00:04:02,000 --> 00:04:06,000
So okay it is saying me to install the ipy and b uh, sorry.

62
00:04:07,000 --> 00:04:08,000
Uh ipykernel.

63
00:04:08,000 --> 00:04:11,000
So I will quickly go ahead and open my terminal.

64
00:04:11,000 --> 00:04:19,000
I will say, hey Pip, install Ipykernel because that is required when you are probably using Jupyter

65
00:04:19,000 --> 00:04:20,000
Notebook for the first time.

66
00:04:20,000 --> 00:04:21,000
Right.

67
00:04:21,000 --> 00:04:25,000
And the environment that is specifically used over here is 3.12.

68
00:04:27,000 --> 00:04:29,000
So let's this installation take place.

69
00:04:29,000 --> 00:04:30,000
Till then we will just wait.

70
00:04:30,000 --> 00:04:34,000
And then once the installation will be completed, we will continue.

71
00:04:34,000 --> 00:04:38,000
So here you can see guys, the ipykernel installation is done.

72
00:04:38,000 --> 00:04:39,000
So I will close this.

73
00:04:39,000 --> 00:04:41,000
Now let's go ahead and execute it once again.

74
00:04:41,000 --> 00:04:43,000
Now you can see it is connecting to the kernel.

75
00:04:43,000 --> 00:04:46,000
And now it absolutely works fine okay.

76
00:04:47,000 --> 00:04:52,000
Now the next thing is that I will just go ahead and import OS and we will go ahead and set up all these

77
00:04:52,000 --> 00:04:53,000
environment variables.

78
00:04:53,000 --> 00:04:54,000
Right.

79
00:04:54,000 --> 00:04:59,000
So specifically, whenever we set up this environment variable, we are going to set it for Neo4j's

80
00:04:59,000 --> 00:05:02,000
URI username and password.

81
00:05:02,000 --> 00:05:02,000
Okay.

82
00:05:03,000 --> 00:05:07,000
So uh this URL we will try to replace it with Neo4j's URI.

83
00:05:08,000 --> 00:05:10,000
So let me quickly go ahead and do this.

84
00:05:10,000 --> 00:05:14,000
And similarly we will go ahead and replace this with our username.

85
00:05:14,000 --> 00:05:17,000
At least we require this three important information.

86
00:05:17,000 --> 00:05:20,000
And this will basically be my new 4G password.

87
00:05:20,000 --> 00:05:21,000
Perfect.

88
00:05:21,000 --> 00:05:23,000
So till here everything looks good.

89
00:05:23,000 --> 00:05:29,000
Now in order to start working, first of all, I'll execute all since I've set up all the environment

90
00:05:29,000 --> 00:05:29,000
variables over here.

91
00:05:30,000 --> 00:05:35,000
Now, the next thing that we are going to do again I will go ahead and write from long chain underscore

92
00:05:35,000 --> 00:05:36,000
community okay.

93
00:05:36,000 --> 00:05:37,000
Dot graphs.

94
00:05:37,000 --> 00:05:42,000
So long chain community actually provides this library in graphs which is nothing.

95
00:05:42,000 --> 00:05:45,000
But it is a class which is called as Neo4j's graph.

96
00:05:45,000 --> 00:05:51,000
Now this Neo4j's graph actually helps you to connect to your DB with the help of this information.

97
00:05:51,000 --> 00:05:54,000
That is Neo4j's URI username and password.

98
00:05:54,000 --> 00:05:57,000
So here I'm going to go ahead and create my graph.

99
00:05:57,000 --> 00:06:02,000
And here you have this Neo4j's graph with URL is equal to.

100
00:06:03,000 --> 00:06:10,000
So first information that I want is even though I have actually set up my environment, you can also

101
00:06:10,000 --> 00:06:12,000
directly pass all these values over here.

102
00:06:12,000 --> 00:06:14,000
So let's go ahead and pass it.

103
00:06:14,000 --> 00:06:15,000
So Neo4j's URI.

104
00:06:16,000 --> 00:06:20,000
Then along with this my second is second parameter is nothing but username.

105
00:06:20,000 --> 00:06:25,000
So I can go ahead and write Neo4j's username.

106
00:06:25,000 --> 00:06:29,000
And the third one is something called as password whatever password we have.

107
00:06:29,000 --> 00:06:32,000
And here also I will just go ahead and write Neo4j's password.

108
00:06:32,000 --> 00:06:37,000
So this way also you will be able to initialize your graph which is basically connecting to your entire

109
00:06:37,000 --> 00:06:38,000
database.

110
00:06:38,000 --> 00:06:38,000
Right.

111
00:06:38,000 --> 00:06:46,000
So once you execute this here it shows that hey Lincoln underscore community dot graph Neo4j's underscore

112
00:06:46,000 --> 00:06:46,000
graph.

113
00:06:46,000 --> 00:06:49,000
At this specific memory location the object is basically created.

114
00:06:50,000 --> 00:06:57,000
Now let's see in for which data set we are going to specifically work okay.

115
00:06:57,000 --> 00:06:59,000
So data set that we are going to work is nothing.

116
00:06:59,000 --> 00:07:03,000
But it is with respect to movies uh data set.

117
00:07:03,000 --> 00:07:08,000
It has some of the information like which actor has probably worked and all and.

118
00:07:08,000 --> 00:07:08,000
All right.

119
00:07:09,000 --> 00:07:13,000
So here, uh, let's see this particular data set that we are going to use.

120
00:07:13,000 --> 00:07:16,000
So I'm just going to close this okay.

121
00:07:16,000 --> 00:07:17,000
So here is the data set.

122
00:07:17,000 --> 00:07:22,000
So here you can see I've opened this movie's underscore small dot CSV file.

123
00:07:22,000 --> 00:07:25,000
It is available in this GitHub location.

124
00:07:25,000 --> 00:07:30,000
It has informations like movie ID release title actors directors see directors can be many.

125
00:07:30,000 --> 00:07:36,000
So you can see over here you have like Jim Jim Varney, Tim Allen, Tom Hanks, Don Nickles.

126
00:07:36,000 --> 00:07:37,000
Right.

127
00:07:37,000 --> 00:07:43,000
So Don Rickles, then you have General Jim Generals, then you have ID and B ratings.

128
00:07:43,000 --> 00:07:43,000
Right.

129
00:07:43,000 --> 00:07:43,000
right.

130
00:07:43,000 --> 00:07:50,000
And with respect to a journalist right here also, you'll be able to see that it has adventure animation.

131
00:07:50,000 --> 00:07:52,000
So it has that pipe symbol.

132
00:07:52,000 --> 00:07:57,000
Now what we are going to do is that we're going to go ahead and read this entire URL right now.

133
00:07:57,000 --> 00:08:01,000
Already I've already shown you how to probably go ahead and read this particular URL.

134
00:08:01,000 --> 00:08:04,000
So first of all we'll go ahead and create our query okay.

135
00:08:05,000 --> 00:08:07,000
So let's go ahead and create our query.

136
00:08:07,000 --> 00:08:09,000
So I'll say hey this is my movie query.

137
00:08:09,000 --> 00:08:15,000
And this time I'm just going to use a triple quotes okay.

138
00:08:15,000 --> 00:08:22,000
So this will be my triple quotes here I'll say hey let's go ahead and load CSV okay CSV.

139
00:08:22,000 --> 00:08:30,000
And here uh, and I have to also make sure that I provide with headers from because this is the query

140
00:08:30,000 --> 00:08:31,000
initially we need to have some data.

141
00:08:31,000 --> 00:08:34,000
So that is the reason I'm writing the Cypher query language right.

142
00:08:34,000 --> 00:08:37,000
And then I will go ahead and put this entire URL okay.

143
00:08:38,000 --> 00:08:42,000
Now from this I will make this as row okay.

144
00:08:42,000 --> 00:08:46,000
So it will be when I say as row it is going to take with all the headers right.

145
00:08:46,000 --> 00:08:50,000
So as row we will be taking all the row right.

146
00:08:50,000 --> 00:08:54,000
And then we will also make sure that we will merge this okay.

147
00:08:54,000 --> 00:09:00,000
Now see merging is very much important because there are so many features that is available.

148
00:09:00,000 --> 00:09:07,000
So first of all, I will go ahead and create a node with movie M right M and this will basically be

149
00:09:07,000 --> 00:09:08,000
my label.

150
00:09:08,000 --> 00:09:13,000
So and please make sure that whatever things I'm writing, you follow that same steps.

151
00:09:13,000 --> 00:09:17,000
Right inside this movie you will be having two important features.

152
00:09:17,000 --> 00:09:19,000
So if I go ahead and show you.

153
00:09:19,000 --> 00:09:22,000
So this is nothing but movie ID, right?

154
00:09:22,000 --> 00:09:26,000
So in order to access this, I will just go ahead and create my property, which is called as ID.

155
00:09:26,000 --> 00:09:34,000
So here I'm going to basically write ID colon right row dot movie ID okay.

156
00:09:34,000 --> 00:09:43,000
So but inside this movie ID also you'll be able to see that um, along with this movie ID so if I go

157
00:09:43,000 --> 00:09:49,000
ahead and see over here, you'll also be seeing that same for that particular movie ID there are information

158
00:09:49,000 --> 00:09:55,000
like a release titles, actors, right Id.me ratings and all right.

159
00:09:55,000 --> 00:10:00,000
And obviously when I'm using this released, uh, let's say title is also there.

160
00:10:00,000 --> 00:10:00,000
Right.

161
00:10:00,000 --> 00:10:02,000
And I'd and B ratings are there remaining.

162
00:10:02,000 --> 00:10:05,000
All are like they are like actors.

163
00:10:05,000 --> 00:10:08,000
Also there will be many actors directors also there will be many directors.

164
00:10:08,000 --> 00:10:10,000
So first of all, let's do one thing.

165
00:10:10,000 --> 00:10:16,000
Let's take all the single fields and probably create that many number of features in short right or

166
00:10:16,000 --> 00:10:17,000
property keys.

167
00:10:17,000 --> 00:10:19,000
So I'll go over here.

168
00:10:19,000 --> 00:10:19,000
Now see this.

169
00:10:19,000 --> 00:10:25,000
What I will do I will say hey go ahead and set all this features.

170
00:10:25,000 --> 00:10:28,000
That is M dot released is equal to date.

171
00:10:28,000 --> 00:10:32,000
We are converting this particular value row dot release to date okay.

172
00:10:32,000 --> 00:10:39,000
And then I have this row dot title m dot idb m rating to float row.id rating.

173
00:10:39,000 --> 00:10:39,000
Okay.

174
00:10:39,000 --> 00:10:42,000
So all these things are done similarly for directors.

175
00:10:42,000 --> 00:10:45,000
For directors we will go ahead and use for each loop.

176
00:10:45,000 --> 00:10:49,000
So here you will be able to see in Cypher Query.

177
00:10:49,000 --> 00:10:53,000
You also have this for each directory in split Road or Director with this pipe symbol.

178
00:10:53,000 --> 00:10:59,000
Then you have this P person name is equal to name trim director then merge p director with respect to

179
00:10:59,000 --> 00:11:01,000
this particular m value okay.

180
00:11:02,000 --> 00:11:08,000
So this are all the directories we are going to put inside our person node itself.

181
00:11:08,000 --> 00:11:08,000
Right.

182
00:11:08,000 --> 00:11:11,000
Or person entity which we have actually created.

183
00:11:11,000 --> 00:11:15,000
And we are also going to create a relationship with respect to P with movies.

184
00:11:15,000 --> 00:11:15,000
Right.

185
00:11:15,000 --> 00:11:17,000
With all the movies information.

186
00:11:17,000 --> 00:11:18,000
Okay.

187
00:11:18,000 --> 00:11:24,000
Then, uh, similarly for the actor also we will be doing and we also need to create another relationship

188
00:11:24,000 --> 00:11:27,000
that is called as acting in acted in.

189
00:11:27,000 --> 00:11:27,000
Okay.

190
00:11:27,000 --> 00:11:30,000
So here directed here acted in okay.

191
00:11:30,000 --> 00:11:33,000
And again we are going to basically do trim dot actor.

192
00:11:33,000 --> 00:11:36,000
We are using this pipe symbol to separate all the actors from that movie okay.

193
00:11:37,000 --> 00:11:40,000
And similarly you will be able to also see that there will be a joiner field.

194
00:11:40,000 --> 00:11:41,000
Right.

195
00:11:41,000 --> 00:11:43,000
And joiner also we are using a pipe symbol.

196
00:11:43,000 --> 00:11:45,000
So again joiner in Split Road or joiners genres.

197
00:11:46,000 --> 00:11:48,000
We are using this pipe symbol again.

198
00:11:48,000 --> 00:11:51,000
We are saying merge on or name trimmed or genre.

199
00:11:51,000 --> 00:11:56,000
Then we are merging this by creating a relationship over here with this G right?

200
00:11:57,000 --> 00:11:58,000
And G is nothing but genre.

201
00:11:58,000 --> 00:12:05,000
So movie with genre is basically created as a relationship person with movie.

202
00:12:05,000 --> 00:12:10,000
We have created a relationship like actor P directed with M, we have created like this.

203
00:12:10,000 --> 00:12:14,000
Okay, so this is the query to probably load this entire data set.

204
00:12:14,000 --> 00:12:15,000
So I will go ahead and execute this.

205
00:12:15,000 --> 00:12:19,000
So if you go ahead and see my movie query okay.

206
00:12:19,000 --> 00:12:22,000
So here you'll be able to see this is my entire query.

207
00:12:22,000 --> 00:12:23,000
Right.

208
00:12:23,000 --> 00:12:23,000
Perfect.

209
00:12:24,000 --> 00:12:25,000
Great.

210
00:12:25,000 --> 00:12:30,000
Now what I'm actually going to do I'll just go ahead and write graph dot query okay.

211
00:12:30,000 --> 00:12:37,000
So if you go ahead and see this definition the Cypher query to execute whatever query that we are going

212
00:12:37,000 --> 00:12:38,000
to execute over here.

213
00:12:38,000 --> 00:12:43,000
So let's go ahead and write this movies query okay.

214
00:12:43,000 --> 00:12:49,000
So once I execute this here you'll be able to see I'm getting some blank okay.

215
00:12:49,000 --> 00:12:50,000
But no worries.

216
00:12:50,000 --> 00:12:51,000
Uh, let's do one thing.

217
00:12:51,000 --> 00:12:55,000
Let's take this entire graph and refresh its schema.

218
00:12:55,000 --> 00:12:55,000
Okay.

219
00:12:55,000 --> 00:13:06,000
So I will go ahead and write refresh schema and we will go ahead and print our graph dot schema.

220
00:13:06,000 --> 00:13:06,000
Okay.

221
00:13:09,000 --> 00:13:13,000
So here you can see all the information right.

222
00:13:13,000 --> 00:13:14,000
Node properties.

223
00:13:14,000 --> 00:13:17,000
This all all the previous information that I had uploaded.

224
00:13:17,000 --> 00:13:21,000
Right now you have movie user post this right relationship.

225
00:13:21,000 --> 00:13:25,000
Also you can see a person acted in movie directed in movie.

226
00:13:25,000 --> 00:13:28,000
These all are my previous information that I had right now.

227
00:13:28,000 --> 00:13:29,000
Let me do one thing.

228
00:13:29,000 --> 00:13:32,000
Let me just go back to my Neo4j's DB.

229
00:13:32,000 --> 00:13:34,000
So let's reload this.

230
00:13:34,000 --> 00:13:37,000
I don't know whether we will be able to reload this or not, but it shows.

231
00:13:37,000 --> 00:13:38,000
Disconnected.

232
00:13:38,000 --> 00:13:42,000
No worries, I will go to my home page of Neo4j's.

233
00:13:43,000 --> 00:13:54,000
Okay, so let me just go ahead and write new, Neo for J or RDB and I will go ahead and click this start

234
00:13:54,000 --> 00:13:55,000
free.

235
00:13:56,000 --> 00:13:57,000
It will tell me to log in okay.

236
00:13:57,000 --> 00:13:59,000
So I have logged in over here.

237
00:13:59,000 --> 00:14:06,000
I will go ahead and open it and it will tell me to connect let's say whether it connects or not.

238
00:14:06,000 --> 00:14:08,000
These are all my queries that I have actually created.

239
00:14:08,000 --> 00:14:11,000
And it has also been attached.

240
00:14:11,000 --> 00:14:14,000
Right now let's go to the database.

241
00:14:14,000 --> 00:14:16,000
Here you can see in genre.

242
00:14:16,000 --> 00:14:20,000
So if I go ahead and click this see amazing graph is basically getting created.

243
00:14:20,000 --> 00:14:25,000
That basically means my entire data has got just inserted right.

244
00:14:25,000 --> 00:14:26,000
Romance.

245
00:14:26,000 --> 00:14:27,000
Drama.

246
00:14:27,000 --> 00:14:30,000
Father of the bride part two.

247
00:14:30,000 --> 00:14:32,000
It is a comedy genre comedy.

248
00:14:32,000 --> 00:14:34,000
Toy story two comedy.

249
00:14:34,000 --> 00:14:35,000
It is fantasy.

250
00:14:35,000 --> 00:14:37,000
It is having this animations and.

251
00:14:37,000 --> 00:14:37,000
All right.

252
00:14:37,000 --> 00:14:38,000
Amazing.

253
00:14:39,000 --> 00:14:39,000
Right.

254
00:14:39,000 --> 00:14:42,000
And, uh, if you go and and see acted in.

255
00:14:42,000 --> 00:14:45,000
Right, this is a huge database again.

256
00:14:45,000 --> 00:14:49,000
So with respect to acted you'll be able to see over here.

257
00:14:49,000 --> 00:14:52,000
Let's see with uh acted in I will just go ahead and click it.

258
00:14:54,000 --> 00:14:57,000
See forest white text acted in species.

259
00:14:58,000 --> 00:15:01,000
Uh burnt by Nikita mike.

260
00:15:01,000 --> 00:15:04,000
I guess they have acted in different movies.

261
00:15:04,000 --> 00:15:09,000
Clint Eastwood this jawlensky French twist.

262
00:15:09,000 --> 00:15:09,000
Right?

263
00:15:09,000 --> 00:15:13,000
So this is the kind of data that we have already there.

264
00:15:13,000 --> 00:15:13,000
Okay.

265
00:15:13,000 --> 00:15:17,000
Along with this, you know that we have also created directed, right?

266
00:15:17,000 --> 00:15:22,000
So if I go ahead and click on directed, there's so many directors see Oliver Stone and all.

267
00:15:22,000 --> 00:15:25,000
So with respect to person, how many persons are there?

268
00:15:25,000 --> 00:15:28,000
If I want to double click this, it will show a relation.

269
00:15:28,000 --> 00:15:32,000
It has directed heat Jon Lester, it has directed Toy Story.

270
00:15:32,000 --> 00:15:32,000
Right.

271
00:15:32,000 --> 00:15:40,000
So this is a simple way of just showing you that how with the help of using this graph dot query function.

272
00:15:40,000 --> 00:15:41,000
Right.

273
00:15:41,000 --> 00:15:45,000
We use just just this graph dot query to probably insert this entire data.

274
00:15:45,000 --> 00:15:46,000
Right.

275
00:15:46,000 --> 00:15:50,000
And let us executed the entire query itself inside the graph database.

276
00:15:51,000 --> 00:15:55,000
Now, uh, this was the basic fundamental of inserting.

277
00:15:55,000 --> 00:15:58,000
Now in my next video we will go.

278
00:15:58,000 --> 00:15:59,000
We'll proceed further.

279
00:15:59,000 --> 00:16:04,000
And then I will try to ask any kind of questions with the graph DB with the help of LLM.

280
00:16:04,000 --> 00:16:06,000
And I think I should be able to get the answer.

281
00:16:06,000 --> 00:16:10,000
And that is what we are going to see in the next video.

282
00:16:10,000 --> 00:16:11,000
This was it.

283
00:16:11,000 --> 00:16:12,000
I will see you all in the next video.

284
00:16:12,000 --> 00:16:13,000
Thank you.