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

2
00:00:01,000 --> 00:00:05,000
So we are going to continue the discussion with respect to Lang Chin.

3
00:00:05,000 --> 00:00:11,000
And already in our previous module, we have discussed about some of the very important components of

4
00:00:11,000 --> 00:00:16,000
Lang Chen that we usually use, uh, that are nothing but like document loaders.

5
00:00:16,000 --> 00:00:20,000
We also discussed about data transformation technique, where we are dividing our documents into chunks

6
00:00:20,000 --> 00:00:23,000
of text or chunks of documents.

7
00:00:23,000 --> 00:00:28,000
After that, we also saw how we can convert this text into vectors by using various vector embedding

8
00:00:28,000 --> 00:00:29,000
techniques.

9
00:00:29,000 --> 00:00:34,000
And after that, we also saw how to store this vector embeddings into a vector store database.

10
00:00:34,000 --> 00:00:40,000
And finally we could find out the response of our output with the help of both retriever and.

11
00:00:40,000 --> 00:00:43,000
Along with that we also use some kind of LM models.

12
00:00:43,000 --> 00:00:49,000
Okay, so now we are going to go ahead and build some amazing simple LM applications.

13
00:00:49,000 --> 00:00:52,000
So in this video we are just going to build a simple LM application.

14
00:00:53,000 --> 00:00:57,000
And in the upcoming videos lot many things we are going to add on top of it okay.

15
00:00:57,000 --> 00:01:03,000
So what we are going to discuss in this video we are building a simple LM application with LCL.

16
00:01:03,000 --> 00:01:03,000
Okay.

17
00:01:03,000 --> 00:01:05,000
So this is a very important word.

18
00:01:05,000 --> 00:01:10,000
If you don't know the full form of LCL, it is nothing but using Lang chain expression language.

19
00:01:10,000 --> 00:01:14,000
And this is basically used to chain components together.

20
00:01:14,000 --> 00:01:14,000
Okay.

21
00:01:14,000 --> 00:01:19,000
So what we are going to do in this tutorial here I have given a brief information.

22
00:01:19,000 --> 00:01:23,000
In this quick start, we'll show you how to build a simple LM application with long chain.

23
00:01:23,000 --> 00:01:28,000
This application will translate text from English into other languages.

24
00:01:28,000 --> 00:01:30,000
This is a relatively simple LM application.

25
00:01:30,000 --> 00:01:33,000
It is just a single LM clock plus prompting.

26
00:01:33,000 --> 00:01:36,000
So I will also be talking about prompting over here.

27
00:01:36,000 --> 00:01:39,000
Still, this is a great way to get started with launching.

28
00:01:39,000 --> 00:01:41,000
A lot of features can be built.

29
00:01:41,000 --> 00:01:44,000
Uh, and that is what we are going to see in the upcoming series of video.

30
00:01:44,000 --> 00:01:44,000
Right?

31
00:01:44,000 --> 00:01:50,000
So after seeing this video, you will be getting a high level overview of using language models, using

32
00:01:50,000 --> 00:01:57,000
prompt templates and output parser, using Lang chain expression uh language to chain components together,

33
00:01:57,000 --> 00:02:02,000
debugging and tracing your application using Lang Smith, and finally deploy your application with Lang

34
00:02:02,000 --> 00:02:02,000
serve.

35
00:02:02,000 --> 00:02:03,000
So everything.

36
00:02:03,000 --> 00:02:06,000
We will go ahead and discuss about it here.

37
00:02:06,000 --> 00:02:10,000
In this video we are also going to discuss about something called as Lang serve.

38
00:02:10,000 --> 00:02:10,000
Okay.

39
00:02:10,000 --> 00:02:13,000
So multiple set of videos are going to come with respect to this.

40
00:02:13,000 --> 00:02:16,000
So let's go ahead and discuss uh this entire thing.

41
00:02:16,000 --> 00:02:22,000
But at the end of the day, after completing at least this particular module, you will probably get

42
00:02:22,000 --> 00:02:25,000
the best hands on experience of building the LLM application.

43
00:02:25,000 --> 00:02:26,000
I am going to make that.

44
00:02:26,000 --> 00:02:27,000
Sure.

45
00:02:27,000 --> 00:02:27,000
Okay.

46
00:02:27,000 --> 00:02:28,000
So let's go ahead.

47
00:02:28,000 --> 00:02:32,000
So first of all here we will go ahead and install.

48
00:02:32,000 --> 00:02:35,000
That is nothing but Lang chan okay.

49
00:02:35,000 --> 00:02:42,000
So I will go ahead and right over here Pip install pip install Lang chan okay.

50
00:02:42,000 --> 00:02:43,000
So we definitely require this.

51
00:02:43,000 --> 00:02:47,000
And already in our previous module we have done this installation.

52
00:02:47,000 --> 00:02:51,000
But just for the people who have directly jumped into the session, I will just show you how to do the

53
00:02:51,000 --> 00:02:52,000
installation.

54
00:02:52,000 --> 00:02:56,000
So once we do the installation in this specific environment it will get installed.

55
00:02:56,000 --> 00:02:59,000
You can see already the requirement is already satisfied at my end.

56
00:02:59,000 --> 00:03:00,000
Okay.

57
00:03:00,000 --> 00:03:02,000
The reason is because I have already done the installation.

58
00:03:02,000 --> 00:03:07,000
So please make sure that you go ahead and right after the installation, this particular library name

59
00:03:07,000 --> 00:03:11,000
in the requirement dot txt right how I have actually shown you in the previous module.

60
00:03:11,000 --> 00:03:17,000
Now after this, uh, what we are going to do in this particular video, that is very much important

61
00:03:17,000 --> 00:03:18,000
here.

62
00:03:18,000 --> 00:03:22,000
See, in our previous module we have shown how to use the OpenAI API key.

63
00:03:22,000 --> 00:03:23,000
Right.

64
00:03:23,000 --> 00:03:27,000
And with the help of this we try to interact with some LLM models over there.

65
00:03:27,000 --> 00:03:33,000
Now the most important thing that you really need to understand from this is that whenever we try to

66
00:03:33,000 --> 00:03:37,000
create an OpenAI API key, you have to go to the account and create it.

67
00:03:37,000 --> 00:03:41,000
So one problem that I usually find that many people do not have credit card or debit card, and they

68
00:03:41,000 --> 00:03:46,000
don't even want to invest some money in just going ahead and seeing OpenAI API calls, right?

69
00:03:47,000 --> 00:03:52,000
Uh, and OpenAI API is basically paid if you specifically use both the embedding or any other models

70
00:03:52,000 --> 00:03:56,000
like GPT four or GPT four turbo or GPT 3.5.

71
00:03:56,000 --> 00:03:58,000
So there will be some charges involved.

72
00:03:58,000 --> 00:04:01,000
So in this video, I'll just not show you OpenAI.

73
00:04:01,000 --> 00:04:06,000
I will also go ahead and show you how you can use open source models.

74
00:04:06,000 --> 00:04:06,000
Okay.

75
00:04:06,000 --> 00:04:10,000
Open source models such as, uh, llama three okay.

76
00:04:10,000 --> 00:04:12,000
Llama three from meta you.

77
00:04:12,000 --> 00:04:16,000
I will also show you how to use this gamma two model, which is the recent model that has been come.

78
00:04:17,000 --> 00:04:20,000
Uh, it is an open source model that has been brought by Google before it was gamma one.

79
00:04:21,000 --> 00:04:24,000
Um, along with it, if you want, you can also go ahead and use Mistral.

80
00:04:24,000 --> 00:04:24,000
Okay.

81
00:04:24,000 --> 00:04:28,000
So all these kind of variants of model will have we are going to see uh, how we can actually use it.

82
00:04:29,000 --> 00:04:33,000
And to use this open source model I'm going to use a platform which is called as grok.

83
00:04:33,000 --> 00:04:34,000
Okay.

84
00:04:34,000 --> 00:04:38,000
So the first thing what I'm actually going to do is that I will go ahead and show you how you can go

85
00:04:38,000 --> 00:04:40,000
ahead and create your grok API key.

86
00:04:40,000 --> 00:04:46,000
Open API key is already there in the env file, which we basically created in our previous module.

87
00:04:46,000 --> 00:04:48,000
So let me do one thing quickly.

88
00:04:48,000 --> 00:04:49,000
Let me just go over here.

89
00:04:49,000 --> 00:04:55,000
I will open my Google over here okay I'll just go ahead and write grok LPU okay.

90
00:04:56,000 --> 00:04:59,000
Now what exactly is this grok LPU will discuss about it.

91
00:04:59,000 --> 00:05:04,000
So first of all, uh, instead of just searching, I will just go ahead and do grok.com.

92
00:05:04,000 --> 00:05:05,000
Okay.

93
00:05:05,000 --> 00:05:09,000
So once I write grok.com this is what a platform you will be getting.

94
00:05:09,000 --> 00:05:11,000
I have right now signed in.

95
00:05:11,000 --> 00:05:12,000
Uh if you have not signed in.

96
00:05:12,000 --> 00:05:16,000
So please make sure that you go ahead and create a, uh, your account over here.

97
00:05:16,000 --> 00:05:17,000
Sign up.

98
00:05:17,000 --> 00:05:22,000
Because, uh, grok actually helps you to access all these open source models like gamma two, nine,

99
00:05:22,000 --> 00:05:29,000
nine, be it other than that gamma seven, be it uh, llama 370 billion parameters llama three 8 billion

100
00:05:29,000 --> 00:05:31,000
parameters Mistral eight into seven be.

101
00:05:31,000 --> 00:05:33,000
All these models are completely open source.

102
00:05:33,000 --> 00:05:35,000
And these are like powerful models.

103
00:05:35,000 --> 00:05:37,000
These are from tech giants.

104
00:05:37,000 --> 00:05:43,000
Now to access these models you definitely require API key because grok has deployed this particular

105
00:05:43,000 --> 00:05:44,000
model in its own cloud.

106
00:05:44,000 --> 00:05:51,000
And over there they have used this amazing inferencing, which is called as LPU AI Inferencing Engine

107
00:05:51,000 --> 00:05:52,000
right now.

108
00:05:52,000 --> 00:05:54,000
What exactly is this LPU inferencing engine?

109
00:05:54,000 --> 00:05:55,000
Let's talk about it.

110
00:05:55,000 --> 00:05:59,000
So first of all we will go ahead and click on Why Grok okay.

111
00:05:59,000 --> 00:06:01,000
You need to understand why grok.

112
00:06:01,000 --> 00:06:05,000
So grok is a fast AI inference okay.

113
00:06:05,000 --> 00:06:07,000
What is exactly grok.

114
00:06:07,000 --> 00:06:11,000
It is an AI infrastructure company that delivers fast AI inferencing.

115
00:06:11,000 --> 00:06:13,000
Let me tell you one thing guys.

116
00:06:13,000 --> 00:06:20,000
Right now, in this generative AI era, every bigger companies are in that competition to probably create

117
00:06:20,000 --> 00:06:22,000
the best LLM models.

118
00:06:22,000 --> 00:06:22,000
Okay.

119
00:06:23,000 --> 00:06:29,000
Every company like let's say llama three open source, they come coming up with the slam from meta.

120
00:06:29,000 --> 00:06:32,000
Specifically llama three model has come from Google.

121
00:06:32,000 --> 00:06:33,000
Gamma two model has come.

122
00:06:33,000 --> 00:06:38,000
You know if I probably talk about OpenAI again there is a GPT four model, right?

123
00:06:38,000 --> 00:06:41,000
It is a multi model which works with both text and images.

124
00:06:41,000 --> 00:06:43,000
So all these specific models are there.

125
00:06:43,000 --> 00:06:43,000
Right.

126
00:06:43,000 --> 00:06:46,000
And all these tech giants are in fierce competition.

127
00:06:46,000 --> 00:06:48,000
Who actually brings the best accuracy out there.

128
00:06:49,000 --> 00:06:57,000
But I still believe that the company instead uh, you know uh, the company who will win is that who

129
00:06:57,000 --> 00:07:00,000
will be able to help us in the inferencing.

130
00:07:00,000 --> 00:07:00,000
Right.

131
00:07:00,000 --> 00:07:05,000
Because all these models are huge models and we really need to deploy this particular model somewhere.

132
00:07:05,000 --> 00:07:10,000
Let's say that if we are using our own inferencing or if we are using our own premise, right, to deploy

133
00:07:10,000 --> 00:07:15,000
that particular model and use it for inferencing, then there will be a lot of charges for that, right?

134
00:07:15,000 --> 00:07:16,000
It is not that simple.

135
00:07:16,000 --> 00:07:21,000
They will definitely be a lot of charges and grok what it has actually done.

136
00:07:21,000 --> 00:07:24,000
It has brought this amazing LPU inferencing engine.

137
00:07:24,000 --> 00:07:24,000
Right.

138
00:07:24,000 --> 00:07:26,000
So what is an LPU inferencing engine?

139
00:07:26,000 --> 00:07:29,000
LPU stands for Language Processing Unit.

140
00:07:29,000 --> 00:07:35,000
It is a hardware and software platform that delivers exceptional compute speed, quality and energy

141
00:07:35,000 --> 00:07:36,000
efficiency.

142
00:07:36,000 --> 00:07:38,000
And because of this, this is really, really fast.

143
00:07:38,000 --> 00:07:40,000
You will be able to get the response in no time.

144
00:07:40,000 --> 00:07:42,000
You'll be seeing it once.

145
00:07:42,000 --> 00:07:44,000
I will probably go ahead and execute things right in front of you.

146
00:07:44,000 --> 00:07:50,000
You will be able to understand how powerful it is now, why it is so powerful, and why it is faster

147
00:07:50,000 --> 00:07:52,000
than GPUs that also you really need to understand.

148
00:07:52,000 --> 00:07:56,000
The GPU is designed to overcome the two LM bottlenecks.

149
00:07:56,000 --> 00:08:02,000
One is compute density and memory bandwidth, and LPO has greater compute capacity than a GPU and CPU.

150
00:08:02,000 --> 00:08:07,000
In regards to LM, this reduces the amount of time per words calculated, allowing sequence of text

151
00:08:07,000 --> 00:08:09,000
to be generated much faster.

152
00:08:09,000 --> 00:08:15,000
Okay, so this is what it is basically doing is that it is the two bottlenecks is basically there in

153
00:08:15,000 --> 00:08:19,000
the GPU, which is called as compute density and memory bandwidth, and it is fixing that.

154
00:08:19,000 --> 00:08:22,000
You can go ahead and read about more about this particular research paper.

155
00:08:22,000 --> 00:08:25,000
You know and probably understand about the architecture and all.

156
00:08:25,000 --> 00:08:31,000
But again, thanks to grok, uh, this AI infrastructure is giving us some APIs to probably call, uh,

157
00:08:31,000 --> 00:08:35,000
all this kind of LLM models and use it for our, uh, application purpose.

158
00:08:35,000 --> 00:08:35,000
Okay.

159
00:08:36,000 --> 00:08:38,000
Now let's go ahead and let's do this.

160
00:08:38,000 --> 00:08:42,000
So first of all, I will go to my grok, uh.com okay.

161
00:08:42,000 --> 00:08:44,000
Now let's go ahead and log out.

162
00:08:44,000 --> 00:08:46,000
I will first of all show you how the home page looks like.

163
00:08:46,000 --> 00:08:48,000
So this is what you will be able to see.

164
00:08:48,000 --> 00:08:51,000
So first of all go ahead and sign in for signing it.

165
00:08:51,000 --> 00:08:55,000
Uh, I will just go ahead and use my Google account.

166
00:08:55,000 --> 00:08:55,000
Okay.

167
00:08:55,000 --> 00:08:58,000
So I'll just go ahead and click on Google right now.

168
00:08:58,000 --> 00:09:02,000
As I said, here are so many different, different LLM models.

169
00:09:02,000 --> 00:09:07,000
Now if you want to use this LLM models with the help of uh in the grok AI platform specifically from

170
00:09:07,000 --> 00:09:13,000
here, we have to go ahead and create our, uh, you know, we have to create our API key.

171
00:09:13,000 --> 00:09:17,000
Now in order to create a API key, I will go ahead and click on Grok Cloud.

172
00:09:17,000 --> 00:09:19,000
Let's open this in a new link.

173
00:09:19,000 --> 00:09:22,000
Uh, over here you'll be able to see playground documentation.

174
00:09:22,000 --> 00:09:22,000
Right.

175
00:09:22,000 --> 00:09:24,000
How to use this grok API key.

176
00:09:24,000 --> 00:09:26,000
Everything is over here right.

177
00:09:26,000 --> 00:09:27,000
How to use it.

178
00:09:27,000 --> 00:09:30,000
Uh, along with the library, everything, uh, is basically available, right?

179
00:09:30,000 --> 00:09:34,000
We will talk more about this, but, uh, let's go ahead and create our API key.

180
00:09:34,000 --> 00:09:37,000
So here you can go and see that I have created so many API keys.

181
00:09:37,000 --> 00:09:40,000
You can use any of the API key that you want in order to create it.

182
00:09:40,000 --> 00:09:41,000
Just click on create API key.

183
00:09:41,000 --> 00:09:46,000
Give the name of the API key like something like grok test and just click on submit.

184
00:09:46,000 --> 00:09:50,000
Once you click on submit, you will be able to get this secret key, something like this.

185
00:09:50,000 --> 00:09:50,000
Right?

186
00:09:50,000 --> 00:09:54,000
It is not visible right now, but once you create it, you will be able to create that secret key.

187
00:09:55,000 --> 00:09:57,000
Once you get the secret key, please copy it.

188
00:09:57,000 --> 00:10:00,000
And then you go to your environment variable.

189
00:10:00,000 --> 00:10:04,000
And here you can see I've also created this grok underscore API key with this particular secret key

190
00:10:04,000 --> 00:10:06,000
because I have already created it.

191
00:10:06,000 --> 00:10:06,000
Okay.

192
00:10:07,000 --> 00:10:11,000
Now with the help of this grok API key, I will try to call the open source models.

193
00:10:11,000 --> 00:10:12,000
Okay.

194
00:10:12,000 --> 00:10:16,000
So let's go ahead and let me show you how you can basically go ahead and do it.

195
00:10:16,000 --> 00:10:21,000
So first of all I will go ahead and write import os okay.

196
00:10:21,000 --> 00:10:32,000
Import os uh, along with the OS, I'm also going to say from dot env I'm going to import load underscore

197
00:10:32,000 --> 00:10:33,000
dot env okay.

198
00:10:33,000 --> 00:10:37,000
Now let me just go ahead and initialize load underscore dot env okay.

199
00:10:37,000 --> 00:10:40,000
So now this load underscore dot env right.

200
00:10:40,000 --> 00:10:46,000
It actually loads all the environment variable I have both my environment variables of OpenAI key and

201
00:10:46,000 --> 00:10:47,000
grok API key.

202
00:10:47,000 --> 00:10:49,000
In order to load the OpenAI key.

203
00:10:49,000 --> 00:10:51,000
What I can do, I can just go ahead and right import OpenAI.

204
00:10:51,000 --> 00:10:57,000
And here I will just go and say OpenAI dot API key is nothing.

205
00:10:57,000 --> 00:11:03,000
But here I will say OS dot get env uh os dot get env.

206
00:11:03,000 --> 00:11:09,000
And here I'm just going to give my key name, which is nothing but open AI underscore API underscore

207
00:11:09,000 --> 00:11:10,000
key okay.

208
00:11:11,000 --> 00:11:13,000
This is done right.

209
00:11:13,000 --> 00:11:15,000
Uh, that is how I actually call.

210
00:11:15,000 --> 00:11:22,000
Now I can go in and just, uh, use any, uh, open AI models and I can basically go ahead and do my

211
00:11:22,000 --> 00:11:25,000
further task, whatever task I really want to do.

212
00:11:25,000 --> 00:11:25,000
Right?

213
00:11:25,000 --> 00:11:31,000
Similarly, in order to create the grok API key, what I will basically do is that I'll say, hey,

214
00:11:31,000 --> 00:11:32,000
this is my grok API key.

215
00:11:32,000 --> 00:11:38,000
I will go ahead and create this and I'll say, hey, this is my OS dot environ, and let me just go

216
00:11:38,000 --> 00:11:41,000
ahead and call sorry OS dot get env.

217
00:11:41,000 --> 00:11:42,000
I'll say.

218
00:11:43,000 --> 00:11:49,000
And here I'm just going to go and call my grok underscore API underscore key.

219
00:11:49,000 --> 00:11:49,000
Okay.

220
00:11:50,000 --> 00:11:53,000
Now this basically is my grok underscore API key.

221
00:11:53,000 --> 00:11:54,000
Okay.

222
00:11:54,000 --> 00:11:57,000
Now understand one more thing I have got my key.

223
00:11:57,000 --> 00:12:01,000
This is my key that I'm actually going to use to interact with the models right now.

224
00:12:01,000 --> 00:12:07,000
The next library that I'm actually going to use is something called as pip install lang chain grok.

225
00:12:08,000 --> 00:12:13,000
Now understand why I'm installing this library, because this library will be responsible in taking

226
00:12:13,000 --> 00:12:20,000
that particular API, along with interact with any LLM models that are deployed in the grok platform.

227
00:12:20,000 --> 00:12:20,000
Okay.

228
00:12:20,000 --> 00:12:22,000
So first of all we'll go ahead and install this.

229
00:12:22,000 --> 00:12:27,000
So here I think I've already done this installation because I don't want to take much time.

230
00:12:27,000 --> 00:12:29,000
So here you can see it is already satisfied okay.

231
00:12:29,000 --> 00:12:30,000
Now do one thing.

232
00:12:30,000 --> 00:12:36,000
As soon as I do this installation you also need to go ahead and update in the requirements.txt.

233
00:12:36,000 --> 00:12:37,000
So I have already done that.

234
00:12:37,000 --> 00:12:39,000
I have updated in the requirements.txt.

235
00:12:39,000 --> 00:12:44,000
Uh, and please do not miss that because later on whenever you want to do the, uh installation, I

236
00:12:44,000 --> 00:12:49,000
can, you can directly go ahead and write pip install minus requirement dot txt in the same environment

237
00:12:49,000 --> 00:12:50,000
that is called as v and v.

238
00:12:50,000 --> 00:12:51,000
Okay.

239
00:12:51,000 --> 00:12:52,000
Perfect.

240
00:12:52,000 --> 00:12:53,000
Till here everything is done.

241
00:12:53,000 --> 00:12:55,000
Now let's see how to call our model okay.

242
00:12:55,000 --> 00:13:01,000
So I will go ahead and write from lang chain lang chain underscore grok.

243
00:13:01,000 --> 00:13:04,000
And we will be using this will not be using OpenAI.

244
00:13:04,000 --> 00:13:04,000
Yeah.

245
00:13:04,000 --> 00:13:10,000
In some of the use cases we'll be using OpenAI API keys because uh it actually performs well over there.

246
00:13:10,000 --> 00:13:15,000
But, uh, in most of the use cases, I'll go ahead and use this open source, uh, API keys itself.

247
00:13:15,000 --> 00:13:15,000
Right.

248
00:13:15,000 --> 00:13:18,000
So here I'm going to import something called as chat grok.

249
00:13:18,000 --> 00:13:18,000
Right.

250
00:13:18,000 --> 00:13:21,000
So whenever I go ahead and import OpenAI.

251
00:13:21,000 --> 00:13:31,000
So for that I use from lang chain underscore OpenAI I'll import chat import chat OpenAI.

252
00:13:31,000 --> 00:13:32,000
Right.

253
00:13:32,000 --> 00:13:35,000
But in the case of grok I will be importing chat grok.

254
00:13:35,000 --> 00:13:37,000
Now see this is what LinkedIn is basically doing.

255
00:13:37,000 --> 00:13:41,000
LinkedIn wants to probably create integration with every LLM platform out there, right?

256
00:13:41,000 --> 00:13:47,000
LLM models out there, they'll say, hey, you all bigger companies, you keep on competing, you bring

257
00:13:47,000 --> 00:13:51,000
up new new models, but we will create a wrapper which will help us to integrate with any kind of model

258
00:13:51,000 --> 00:13:54,000
that comes in the in the picture right there.

259
00:13:54,000 --> 00:13:54,000
Right.

260
00:13:54,000 --> 00:13:56,000
So that is what it is basically doing.

261
00:13:56,000 --> 00:13:58,000
Now let me show you how we can go.

262
00:13:58,000 --> 00:14:04,000
Go ahead and call a specific model from grok AI platform, uh, specifically the open source model.

263
00:14:04,000 --> 00:14:06,000
So first of all, I will go ahead and initialize Chad Grok.

264
00:14:06,000 --> 00:14:10,000
And I will say first parameter that I need to give is my model name okay.

265
00:14:10,000 --> 00:14:18,000
And the second parameter I will go ahead and write my grok API key which will be equal to my grok API

266
00:14:18,000 --> 00:14:18,000
key.

267
00:14:18,000 --> 00:14:19,000
Right.

268
00:14:19,000 --> 00:14:21,000
So this is what I'm actually initializing.

269
00:14:21,000 --> 00:14:24,000
Now you need to understand what model name we will give okay.

270
00:14:24,000 --> 00:14:26,000
So to give the model name.

271
00:14:26,000 --> 00:14:28,000
So I will just go ahead and use this one.

272
00:14:28,000 --> 00:14:32,000
This is the most newest model gamma two nine be it okay.

273
00:14:32,000 --> 00:14:35,000
So if you want to know about this particular model it is nothing.

274
00:14:35,000 --> 00:14:40,000
But it is a 9 billion parameter version of Google Gamma models, a family of lightweight, state of

275
00:14:40,000 --> 00:14:44,000
art language models from Google with open weights and pre-trained variants.

276
00:14:44,000 --> 00:14:47,000
Okay, so we are going to use this specific model out there so quickly.

277
00:14:47,000 --> 00:14:49,000
Let's go ahead and open this over here.

278
00:14:49,000 --> 00:14:51,000
Now I will just go ahead and write.

279
00:14:51,000 --> 00:14:55,000
Uh let me just see the model name gamma two nine.

280
00:14:55,000 --> 00:14:56,000
Be it okay.

281
00:14:56,000 --> 00:15:05,000
Gamma two nine, be it gamma two nine, be it okay.

282
00:15:05,000 --> 00:15:08,000
So this is specifically my model over here.

283
00:15:09,000 --> 00:15:12,000
And with respect to this particular model if I go ahead and execute it.

284
00:15:12,000 --> 00:15:15,000
So here you will be able to see that I'm able to call this model.

285
00:15:15,000 --> 00:15:18,000
And the model name is nothing but gamma two nine be it.

286
00:15:18,000 --> 00:15:21,000
So let's see gamma two nine be it okay.

287
00:15:21,000 --> 00:15:24,000
So this particular model is basically over here.

288
00:15:24,000 --> 00:15:28,000
Now with the help of this specific model we are going to develop our entire application.

289
00:15:29,000 --> 00:15:32,000
Uh I've already shown you how to call chat OpenAI a model name.

290
00:15:32,000 --> 00:15:35,000
Uh, already we have set up this particular environment variable.

291
00:15:35,000 --> 00:15:39,000
I can just go ahead and write, chat OpenAI AI and give the model name over there.

292
00:15:39,000 --> 00:15:40,000
That's it.

293
00:15:40,000 --> 00:15:42,000
Automatically the model will be initiated.

294
00:15:42,000 --> 00:15:42,000
Perfect.

295
00:15:42,000 --> 00:15:44,000
Uh, I hope you got an idea.

296
00:15:44,000 --> 00:15:44,000
Till here.

297
00:15:44,000 --> 00:15:47,000
Now in the next video we will continue this implementation.

298
00:15:47,000 --> 00:15:49,000
But in this video I have shown you how to.

299
00:15:49,000 --> 00:15:56,000
You can set your grok API key to access the open source model that has been hosted or deployed in the

300
00:15:56,000 --> 00:15:58,000
grok AI platform.

301
00:15:58,000 --> 00:16:03,000
And remember, uh, you will be able to use this particular API key for some number of requests completely

302
00:16:03,000 --> 00:16:04,000
for free.

303
00:16:05,000 --> 00:16:09,000
And I think, uh, I've never faced a problem with respect to the number of requests till now.

304
00:16:09,000 --> 00:16:10,000
I'm using it.

305
00:16:10,000 --> 00:16:12,000
Uh, uh, you can also go ahead and use it.

306
00:16:12,000 --> 00:16:13,000
Okay.

307
00:16:13,000 --> 00:16:14,000
So yes, this was it.

308
00:16:14,000 --> 00:16:20,000
Uh, in the next video, we are just going to continue the implementation of simple LM by LCL.

309
00:16:20,000 --> 00:16:24,000
And uh, then after loading this particular model, we are going to see what all things we will do.

310
00:16:24,000 --> 00:16:25,000
Okay.

311
00:16:25,000 --> 00:16:26,000
So yes, this was it from my side.

312
00:16:26,000 --> 00:16:27,000
I'll see you all in the next video.

313
00:16:27,000 --> 00:16:28,000
Thank you.