1 00:00:00,000 --> 00:00:01,000 Hello guys! 2 00:00:01,000 --> 00:00:06,000 In this video and in the upcoming series of video, we are going to discuss about a new module in long 3 00:00:06,000 --> 00:00:08,000 chain, which is called as lang graph. 4 00:00:08,000 --> 00:00:16,000 Now Lang graph is quite amazing because it actually helps you to build stateful multi actor application 5 00:00:16,000 --> 00:00:17,000 with Llms. 6 00:00:17,000 --> 00:00:21,000 It is used to create agent and multi agent workflow. 7 00:00:21,000 --> 00:00:22,000 So this is really important. 8 00:00:22,000 --> 00:00:28,000 Now there are lot of libraries a lot of open source libraries that are available which actually helps 9 00:00:28,000 --> 00:00:31,000 you to create multi agent workflow. 10 00:00:31,000 --> 00:00:35,000 But if I probably consider lang graph it's quite amazing. 11 00:00:35,000 --> 00:00:41,000 Uh so in this entire video and in the upcoming series of video, I will be discussing many things about 12 00:00:41,000 --> 00:00:42,000 land graph. 13 00:00:42,000 --> 00:00:46,000 First of all, the agenda of this particular video will be that we will try to discuss what exactly 14 00:00:46,000 --> 00:00:49,000 is lang graph, why lang graph, and we'll see. 15 00:00:49,000 --> 00:00:55,000 Or we'll try to create a chatbot wherein we will get just started with Lang graph, where I will be 16 00:00:55,000 --> 00:00:57,000 showing you with respect to all the coding things. 17 00:00:57,000 --> 00:00:57,000 Right. 18 00:00:57,000 --> 00:00:59,000 So all these things we will be covering. 19 00:00:59,000 --> 00:01:05,000 And when we discuss about why Landgraaf at that point of time, you will understand the importance of 20 00:01:05,000 --> 00:01:06,000 landgraaf. 21 00:01:06,000 --> 00:01:12,000 And through this, you know you will also be able to cover or you'll be able to just compare with all 22 00:01:12,000 --> 00:01:17,000 the libraries, open source libraries that are available to create multi agents workflows. 23 00:01:17,000 --> 00:01:18,000 Right. 24 00:01:18,000 --> 00:01:20,000 And I feel right now Landgraaf is quite amazing. 25 00:01:20,000 --> 00:01:27,000 And as you all know, Lang what Lang is also doing is that Lang is coming up with this own cloud platform 26 00:01:27,000 --> 00:01:33,000 through which you will be able to build your own, uh, agent multi agent workflow, uh, using Lang 27 00:01:33,000 --> 00:01:33,000 graph. 28 00:01:33,000 --> 00:01:36,000 And it, you can do it completely in a visualization way. 29 00:01:36,000 --> 00:01:37,000 Right. 30 00:01:37,000 --> 00:01:39,000 And right now it just supports for the Mac machine. 31 00:01:39,000 --> 00:01:43,000 So we'll be discussing all about that as we go ahead. 32 00:01:43,000 --> 00:01:47,000 But right now let's go ahead and focus on first of all we'll go ahead and see the definition of Lang 33 00:01:47,000 --> 00:01:48,000 graph. 34 00:01:48,000 --> 00:01:50,000 So if I talk about what is lang graph. 35 00:01:50,000 --> 00:01:56,000 Lang graph is a library for building stateful multi actor application with Llms used to create agent 36 00:01:56,000 --> 00:01:59,000 and multi multi-agent workflows. 37 00:01:59,000 --> 00:02:04,000 Compared to other LLM frameworks, it offers this core benefit cycles. 38 00:02:04,000 --> 00:02:05,000 So this is really important. 39 00:02:05,000 --> 00:02:08,000 Controllability and persistence okay. 40 00:02:09,000 --> 00:02:16,000 Line graphs allows you to define the flows that involves cycle essential for most agentic architecture 41 00:02:16,000 --> 00:02:19,000 differentiating it from Dag based solutions. 42 00:02:19,000 --> 00:02:26,000 Now if you have seen already my previous video, I hope everybody knows about graph DB. 43 00:02:26,000 --> 00:02:30,000 Okay, so what exactly is graph DB? 44 00:02:30,000 --> 00:02:36,000 It probably helps you to create, you know, if I probably just talk about creating a drag application 45 00:02:36,000 --> 00:02:38,000 using graph knowledge, right. 46 00:02:38,000 --> 00:02:41,000 So here specifically you have nodes. 47 00:02:41,000 --> 00:02:43,000 You have relationship between the nodes. 48 00:02:43,000 --> 00:02:44,000 Uh, like this. 49 00:02:44,000 --> 00:02:51,000 You know, and with the help of this kind of relationships you can actually build this graph knowledge 50 00:02:51,000 --> 00:02:51,000 okay. 51 00:02:51,000 --> 00:02:57,000 And graph knowledge is specifically built right now even in Google search engine you'll be able to see 52 00:02:57,000 --> 00:03:03,000 graph knowledge and with the help of this graph knowledge, you'll be able to develop some amazing application. 53 00:03:03,000 --> 00:03:08,000 Because the efficiency with respect to the graph knowledge search is quite amazing, you know? 54 00:03:08,000 --> 00:03:13,000 So graph knowledge has the combination of all the kind of search, the hybrid search, the graph knowledge 55 00:03:13,000 --> 00:03:19,000 search, you know, so whenever you have any information which is, uh, displayed or which is probably 56 00:03:19,000 --> 00:03:27,000 converted into a graph knowledge information, then your conversation with this kind of data store, 57 00:03:27,000 --> 00:03:28,000 right, can be quite amazing. 58 00:03:28,000 --> 00:03:33,000 So already I have discussed about this in our previous video, but in this video we will try to talk 59 00:03:33,000 --> 00:03:34,000 about line graph. 60 00:03:34,000 --> 00:03:39,000 And the main thing will be that how we have actually created this graph DB structure, right in the 61 00:03:39,000 --> 00:03:40,000 form of graph knowledge. 62 00:03:40,000 --> 00:03:44,000 Similarly line graph is also offers those kind of functionality. 63 00:03:44,000 --> 00:03:49,000 We can create the entire multi agent workflow using this graph knowledge itself. 64 00:03:49,000 --> 00:03:50,000 Right. 65 00:03:50,000 --> 00:03:52,000 So like how we have nodes relationship and all. 66 00:03:52,000 --> 00:03:54,000 Similarly in the line graph. 67 00:03:54,000 --> 00:03:55,000 Also we'll be able to do that. 68 00:03:55,000 --> 00:03:56,000 Okay. 69 00:03:56,000 --> 00:03:59,000 So till now we have just discussed about the definition. 70 00:03:59,000 --> 00:04:03,000 Don't worry if you are not able to understand because once we start the practical application everything 71 00:04:03,000 --> 00:04:04,000 will be able to understand. 72 00:04:04,000 --> 00:04:05,000 Okay. 73 00:04:05,000 --> 00:04:08,000 Now let's talk about the second question. 74 00:04:08,000 --> 00:04:10,000 The second most important question. 75 00:04:10,000 --> 00:04:12,000 Why land graph. 76 00:04:14,000 --> 00:04:15,000 Why land graph? 77 00:04:15,000 --> 00:04:22,000 Okay, now here I will be talking about some amazing benefits of using land graph in point wise. 78 00:04:22,000 --> 00:04:28,000 Okay, so let's go and talk about this amazing benefits of using land graph. 79 00:04:28,000 --> 00:04:29,000 So number one. 80 00:04:29,000 --> 00:04:30,000 Okay. 81 00:04:30,000 --> 00:04:41,000 Number one is that it really simplifies the development simplifies development. 82 00:04:41,000 --> 00:04:45,000 Now when I say simplifies development what does this basically mean. 83 00:04:45,000 --> 00:04:52,000 See whatever complexities usually whenever we develop any multi AI agents right. 84 00:04:52,000 --> 00:04:59,000 They are multiple things that is involved the state management, state management, state management 85 00:04:59,000 --> 00:05:05,000 of the agent, like at which stage at what work it needs to really do, and agent coordination. 86 00:05:05,000 --> 00:05:09,000 Let's say one agent needs to communicate with any other agents, right? 87 00:05:10,000 --> 00:05:13,000 When we say agents we are basically talking about multi agents. 88 00:05:13,000 --> 00:05:14,000 Right. 89 00:05:14,000 --> 00:05:16,000 So this two things are very important. 90 00:05:16,000 --> 00:05:22,000 You know here if I probably see in most of the libraries that I've actually used, most of the open 91 00:05:22,000 --> 00:05:25,000 source libraries that I've used to probably develop multi agents. 92 00:05:25,000 --> 00:05:30,000 This two information that we have that is state management and agent coordination. 93 00:05:30,000 --> 00:05:34,000 I found out a lot of difficulties with respect to managing these things. 94 00:05:34,000 --> 00:05:35,000 Right. 95 00:05:35,000 --> 00:05:39,000 But with the help of Landgraaf it really simplifies it. 96 00:05:39,000 --> 00:05:43,000 Now when we talk about state management and agent coordination, what does this basically mean? 97 00:05:43,000 --> 00:05:49,000 Let's say that I'm using 3 to 4 multi agents in my generative AI application. 98 00:05:49,000 --> 00:05:52,000 One agent is probably doing some Wikipedia search. 99 00:05:52,000 --> 00:05:58,000 So let's say I probably need I require agent one, I require agent two. 100 00:05:58,000 --> 00:06:00,000 I require agent three. 101 00:06:00,000 --> 00:06:01,000 Right. 102 00:06:01,000 --> 00:06:04,000 So let's say all these specific agents are there right. 103 00:06:04,000 --> 00:06:09,000 Each and every agent probably needs to it does some specific task. 104 00:06:09,000 --> 00:06:10,000 Right. 105 00:06:10,000 --> 00:06:12,000 Let's say this will be doing a Google search. 106 00:06:14,000 --> 00:06:16,000 This will be doing a Wikipedia search. 107 00:06:18,000 --> 00:06:20,000 And this will probably do a vector search. 108 00:06:20,000 --> 00:06:22,000 Vector DB search. 109 00:06:24,000 --> 00:06:24,000 Right. 110 00:06:25,000 --> 00:06:31,000 And here is my chatbot which is specifically using all this multi agents. 111 00:06:32,000 --> 00:06:40,000 Now whenever we develop this kind of application it is very important that we have to do the state management 112 00:06:40,000 --> 00:06:46,000 efficiently for all the agents and also the agent coordination. 113 00:06:47,000 --> 00:06:54,000 What does agent coordination basically means the communication between the communication between this 114 00:06:54,000 --> 00:06:55,000 kind of agents. 115 00:06:55,000 --> 00:06:58,000 Let's say whenever a query is asked, first of all, we go and ask. 116 00:06:59,000 --> 00:07:03,000 Agent one hey, whether you really need to do a Google search, if you are doing it, you really need 117 00:07:03,000 --> 00:07:05,000 to provide that information to agent two. 118 00:07:05,000 --> 00:07:07,000 Then agent three will probably come into picture. 119 00:07:07,000 --> 00:07:12,000 So this kind of communication is basically a kind of agent coordination. 120 00:07:12,000 --> 00:07:13,000 Okay. 121 00:07:13,000 --> 00:07:18,000 So whenever we are developing this kind of things, you know, and there may be also scenario that when 122 00:07:18,000 --> 00:07:26,000 you're developing a use case the agent one response may be dependent on agent two or response, you 123 00:07:26,000 --> 00:07:26,000 know. 124 00:07:26,000 --> 00:07:30,000 So agent two will only be able to work when they get the response from agent one. 125 00:07:30,000 --> 00:07:33,000 I'm just giving some hypothetical scenarios okay. 126 00:07:34,000 --> 00:07:42,000 Now when we are developing this kind of chatbots, uh, as a developer we really need to define workflows. 127 00:07:43,000 --> 00:07:45,000 We need to define workflows. 128 00:07:45,000 --> 00:07:48,000 We need to define logics. 129 00:07:49,000 --> 00:07:51,000 Right without worrying, right? 130 00:07:51,000 --> 00:07:53,000 Without worrying about so many different things. 131 00:07:53,000 --> 00:07:54,000 Right. 132 00:07:54,000 --> 00:07:57,000 So that is what it actually does. 133 00:07:57,000 --> 00:08:03,000 Line graph actually provides you this entire simply it simplifies this entire development process. 134 00:08:03,000 --> 00:08:07,000 And it will actually help you to create an efficient multi AI agents. 135 00:08:07,000 --> 00:08:07,000 Right. 136 00:08:07,000 --> 00:08:12,000 So we will be discussing more about it when we go ahead and discuss about the practical implementation. 137 00:08:13,000 --> 00:08:17,000 Second thing is that uh why line graph you should use it. 138 00:08:17,000 --> 00:08:22,000 Second thing a very important point is related to flexibility okay. 139 00:08:23,000 --> 00:08:29,000 So whenever we talk about flexibility, I will just, uh, make sure to provide some description information 140 00:08:29,000 --> 00:08:31,000 over here so that you will be able to refer this. 141 00:08:31,000 --> 00:08:32,000 Okay. 142 00:08:34,000 --> 00:08:40,000 So with respect to flexibility, you can see with line graph develops developers have the flexibility 143 00:08:40,000 --> 00:08:43,000 to define their own agent logic communication protocols. 144 00:08:43,000 --> 00:08:48,000 This allows for highly customized application tailored to specific use cases. 145 00:08:48,000 --> 00:08:52,000 Whether you need a chatbot that can handle various types of user requests, or a multi-agent system 146 00:08:52,000 --> 00:08:54,000 that performs complex tasks. 147 00:08:54,000 --> 00:08:57,000 Lang graph provides the tools to build exactly what you need. 148 00:08:57,000 --> 00:09:01,000 Okay, so it's all about giving you the power to create. 149 00:09:01,000 --> 00:09:07,000 So, uh, with respect to flexibility, as I said, the kind of logics that you can basically write 150 00:09:07,000 --> 00:09:08,000 will be quite amazing. 151 00:09:08,000 --> 00:09:13,000 You'll be seeing that how granular level logics you can actually write with respect to each and every 152 00:09:13,000 --> 00:09:15,000 agents that you specifically create. 153 00:09:15,000 --> 00:09:19,000 I will be showing you, as we go ahead with one very good practical example. 154 00:09:19,000 --> 00:09:19,000 Okay. 155 00:09:20,000 --> 00:09:27,000 Then the third thing is that if I talk about the third important point, why specifically we should 156 00:09:27,000 --> 00:09:31,000 use lang graph, uh, it is related to scalability. 157 00:09:33,000 --> 00:09:33,000 Okay. 158 00:09:34,000 --> 00:09:42,000 Now whenever we talk about scalability here, when we are building this multi agent application we can 159 00:09:42,000 --> 00:09:51,000 actually build large scale multi agent application large scale multi agent applications. 160 00:09:52,000 --> 00:09:53,000 Now what? 161 00:09:53,000 --> 00:09:56,000 What do we mean by large scale multi agent application. 162 00:09:57,000 --> 00:09:59,000 See the kind of robust architecture. 163 00:09:59,000 --> 00:10:02,000 We basically use this large scale multi agent. 164 00:10:02,000 --> 00:10:10,000 We basically say this as large scale multi agent application because it can it can handle it can handle 165 00:10:10,000 --> 00:10:16,000 high volume of interaction high volume of interaction. 166 00:10:17,000 --> 00:10:17,000 Right. 167 00:10:17,000 --> 00:10:20,000 The interaction can be between agents. 168 00:10:20,000 --> 00:10:25,000 And it also has a really amazing or complex workflows. 169 00:10:25,000 --> 00:10:29,000 And you'll be seeing when we define about complex workflows. 170 00:10:29,000 --> 00:10:33,000 It it will be very simple to develop this entire workflow itself. 171 00:10:33,000 --> 00:10:34,000 Right. 172 00:10:34,000 --> 00:10:37,000 And even long chain is coming up with a feature. 173 00:10:37,000 --> 00:10:42,000 And probably many people, many companies are going to use specifically in enterprise. 174 00:10:42,000 --> 00:10:42,000 Right. 175 00:10:42,000 --> 00:10:45,000 And there is also an enterprise version. 176 00:10:45,000 --> 00:10:49,000 We can specifically develop this as an enterprise level application, right? 177 00:10:49,000 --> 00:10:50,000 With all the features. 178 00:10:50,000 --> 00:10:55,000 And it is also coming up with its own cloud where you can just do drag and drop and you can actually 179 00:10:55,000 --> 00:10:55,000 create this. 180 00:10:55,000 --> 00:11:04,000 Right, uh, final, uh, important feature, uh, if I talk about is something called as fault tolerance. 181 00:11:05,000 --> 00:11:07,000 Fault tolerance. 182 00:11:07,000 --> 00:11:11,000 So it also has this amazing feature line graph okay. 183 00:11:11,000 --> 00:11:16,000 So the kind of libraries you'll be seeing, line graph libraries will include. 184 00:11:16,000 --> 00:11:16,000 Right. 185 00:11:16,000 --> 00:11:19,000 Uh, it will be able to handle errors. 186 00:11:20,000 --> 00:11:23,000 You'll be seeing that it will be able to handle errors. 187 00:11:24,000 --> 00:11:30,000 Uh, it will be ensuring, uh, even though your application fails, it should be continuously working. 188 00:11:30,000 --> 00:11:36,000 And, uh, let's say that one individual agent encounters an error, right? 189 00:11:36,000 --> 00:11:37,000 Then. 190 00:11:37,000 --> 00:11:43,000 Also there will be some fault tolerance mechanism it will basically have wherein it will not just stop 191 00:11:43,000 --> 00:11:45,000 the application, but instead it will keep on running, right? 192 00:11:46,000 --> 00:11:52,000 So this is one of the very important core core feature that is reliability, right. 193 00:11:52,000 --> 00:11:54,000 Whenever we talk about reliability. 194 00:11:55,000 --> 00:12:00,000 So this was two important things we have discussed about the definition of land graph. 195 00:12:00,000 --> 00:12:01,000 We have discussed why land graph. 196 00:12:01,000 --> 00:12:07,000 Now it's time that I show you some of the amazing applications, how we can actually go ahead with the 197 00:12:07,000 --> 00:12:09,000 development here. 198 00:12:09,000 --> 00:12:13,000 What we are basically going to do is that we are going to create a chatbot, okay. 199 00:12:13,000 --> 00:12:17,000 And we'll try to create an agent, let's say in the form of chatbot. 200 00:12:17,000 --> 00:12:21,000 And again in the back, back side or right or in the back end. 201 00:12:21,000 --> 00:12:22,000 You'll be able to see that. 202 00:12:22,000 --> 00:12:27,000 We'll also be able to create a graph like how that entire agent specifically works. 203 00:12:27,000 --> 00:12:29,000 So quickly I will go ahead. 204 00:12:29,000 --> 00:12:31,000 And this I'm executing in the Google Colab. 205 00:12:31,000 --> 00:12:33,000 You can also go ahead and use it okay. 206 00:12:33,000 --> 00:12:37,000 So let's say that I will just use any of the GPU that I have. 207 00:12:37,000 --> 00:12:38,000 Okay. 208 00:12:38,000 --> 00:12:39,000 I will just go ahead and connect it. 209 00:12:40,000 --> 00:12:40,000 Anyhow. 210 00:12:40,000 --> 00:12:46,000 You don't require GPU in this, uh, but, uh, definitely we will be seeing that if you have any kind 211 00:12:46,000 --> 00:12:51,000 of, uh, if you if you require any kind of keys over here, and when I say that I'm going to create 212 00:12:51,000 --> 00:12:56,000 a chat bot, let me just go ahead and discuss about this architecture of the chat bot. 213 00:12:56,000 --> 00:12:58,000 So what I am going to create over here. 214 00:12:58,000 --> 00:12:58,000 Right. 215 00:12:58,000 --> 00:13:05,000 So let's say that, uh, there is a chat bot over here, this chat bot, I will try to create some kind 216 00:13:05,000 --> 00:13:06,000 of node. 217 00:13:06,000 --> 00:13:09,000 Let's say this will be my start node okay. 218 00:13:11,000 --> 00:13:19,000 Whenever any user query comes, you should be able to see that I will create a chat bot over here. 219 00:13:20,000 --> 00:13:25,000 This chat bot can basically interact with any LM models okay. 220 00:13:25,000 --> 00:13:32,000 And once it probably gives you the output we should end this entire flow. 221 00:13:32,000 --> 00:13:37,000 Okay, so the reason why I'm drawing this in the form of graph. 222 00:13:37,000 --> 00:13:43,000 Because land graph also does the same thing Okay, so line graph also creates the entire flow in the 223 00:13:43,000 --> 00:13:45,000 form of graph itself where you'll have nodes. 224 00:13:45,000 --> 00:13:50,000 And all right now there are two main important things when we see this. 225 00:13:50,000 --> 00:13:54,000 These are specifically nodes right start and end node. 226 00:13:54,000 --> 00:13:56,000 This chat bot is one node. 227 00:13:56,000 --> 00:14:01,000 And when I write chat bot that basically means it is having some kind of definition, right? 228 00:14:01,000 --> 00:14:07,000 If a chat bot needs to move from one step, let's say from one state to the other state, we basically 229 00:14:07,000 --> 00:14:12,000 call that as a state management, right? 230 00:14:12,000 --> 00:14:17,000 So probably after executing this the chat bot is moving towards the end state. 231 00:14:17,000 --> 00:14:19,000 So something is basically happening. 232 00:14:19,000 --> 00:14:20,000 So let's go ahead and create this. 233 00:14:20,000 --> 00:14:23,000 And then you'll be able to understand more about it okay. 234 00:14:23,000 --> 00:14:29,000 So first of all we will go ahead and install pip install lang graph. 235 00:14:29,000 --> 00:14:35,000 So we are going to specifically use lang graph lang graph okay. 236 00:14:35,000 --> 00:14:38,000 And we will also use lang Smith. 237 00:14:38,000 --> 00:14:40,000 So let's go ahead and execute this line. 238 00:14:40,000 --> 00:14:42,000 Smith I hope everybody knows what exactly is. 239 00:14:42,000 --> 00:14:47,000 So till then, I will also go ahead and show you the documentation of line graph. 240 00:14:47,000 --> 00:14:50,000 So this is what a line graph is all about right. 241 00:14:50,000 --> 00:14:52,000 It has Python. 242 00:14:52,000 --> 00:14:54,000 It has it supports JavaScript and all. 243 00:14:54,000 --> 00:15:00,000 But uh uh if I just go ahead and show you line graph tutorials. 244 00:15:00,000 --> 00:15:01,000 Right. 245 00:15:01,000 --> 00:15:04,000 So here you can see this is the tutorial. 246 00:15:04,000 --> 00:15:04,000 Right. 247 00:15:04,000 --> 00:15:06,000 And uh not this. 248 00:15:06,000 --> 00:15:07,000 Sorry. 249 00:15:07,000 --> 00:15:09,000 Uh let's see. 250 00:15:09,000 --> 00:15:09,000 Yes. 251 00:15:09,000 --> 00:15:10,000 Here you go. 252 00:15:11,000 --> 00:15:13,000 Right in the line graph page. 253 00:15:13,000 --> 00:15:15,000 It should be somewhere here. 254 00:15:15,000 --> 00:15:17,000 Or let me just go to lang chain. 255 00:15:18,000 --> 00:15:19,000 Lang chain.com. 256 00:15:20,000 --> 00:15:24,000 And here here is your line graph. 257 00:15:24,000 --> 00:15:25,000 Yes. 258 00:15:25,000 --> 00:15:29,000 So here you can actually see we will try to create this kind of nodes. 259 00:15:29,000 --> 00:15:29,000 Right. 260 00:15:29,000 --> 00:15:34,000 And I hope everybody has seen this kind of nodes specifically. 261 00:15:34,000 --> 00:15:34,000 Right. 262 00:15:34,000 --> 00:15:37,000 So what does Lang graph actually supports you to. 263 00:15:37,000 --> 00:15:37,000 too. 264 00:15:37,000 --> 00:15:41,000 It provides controllable cognitive architecture for any task. 265 00:15:41,000 --> 00:15:44,000 It is designed for human agent collaborations. 266 00:15:44,000 --> 00:15:44,000 All right. 267 00:15:44,000 --> 00:15:45,000 This kind of graphs. 268 00:15:45,000 --> 00:15:47,000 Also you'll be able to see all these things. 269 00:15:47,000 --> 00:15:49,000 I will try to show you in this video. 270 00:15:49,000 --> 00:15:56,000 So it has this fault tolerant scalability optimized for real world interaction and integrated developer 271 00:15:56,000 --> 00:15:57,000 experience. 272 00:15:57,000 --> 00:15:58,000 Amazing features. 273 00:15:58,000 --> 00:16:00,000 And I feel right. 274 00:16:00,000 --> 00:16:05,000 If you probably get the access of the beta server right, and you'll just be able to see the power of 275 00:16:05,000 --> 00:16:06,000 this. 276 00:16:06,000 --> 00:16:10,000 But at the end of the day, we will be creating some amazing agents, you know? 277 00:16:10,000 --> 00:16:14,000 So here you can see I have installed both the libraries Lang and Lang Smith. 278 00:16:14,000 --> 00:16:19,000 Now let's go ahead and start more things over here. 279 00:16:19,000 --> 00:16:26,000 Now as we go ahead we are also going to install Lang chain because we definitely require lang chain. 280 00:16:26,000 --> 00:16:30,000 And then we are going to use lang chain underscore grok. 281 00:16:30,000 --> 00:16:34,000 Along with this we are also going to use lang chain underscore community. 282 00:16:34,000 --> 00:16:34,000 Right. 283 00:16:34,000 --> 00:16:40,000 So these are all libraries will be specifically required in order to build our entire chatbot. 284 00:16:40,000 --> 00:16:40,000 Right. 285 00:16:40,000 --> 00:16:44,000 So here you can see the installation is basically taking place. 286 00:16:44,000 --> 00:16:45,000 Okay. 287 00:16:45,000 --> 00:16:46,000 Perfect. 288 00:16:47,000 --> 00:16:49,000 Now let's go ahead and import OS. 289 00:16:49,000 --> 00:16:56,000 Or what I will do is that I will right from Google Dot Colab okay. 290 00:16:56,000 --> 00:16:59,000 Import user data. 291 00:16:59,000 --> 00:16:59,000 Okay. 292 00:17:00,000 --> 00:17:07,000 Uh, now see, as you all know, when we worked specifically with VS code, you know, we used to create 293 00:17:07,000 --> 00:17:10,000 environment variables to access any keys. 294 00:17:10,000 --> 00:17:13,000 It can be grok API, it can be Lang Smith keys. 295 00:17:13,000 --> 00:17:18,000 Now similarly, with respect to Google Colab, whenever you are working with Google Colab here you can 296 00:17:18,000 --> 00:17:20,000 see one option. 297 00:17:20,000 --> 00:17:20,000 Here. 298 00:17:20,000 --> 00:17:23,000 You can actually go ahead and upload all your secret keys. 299 00:17:23,000 --> 00:17:28,000 Let's say if you want to use grok API, if you want to use open API, if you want to use Lang Smith 300 00:17:28,000 --> 00:17:33,000 API, if you want to use Hugging Face API, you can just go ahead and enter it over here. 301 00:17:33,000 --> 00:17:36,000 Add a new secret key and you can add the key and value pair. 302 00:17:36,000 --> 00:17:38,000 Okay, here is your password. 303 00:17:38,000 --> 00:17:39,000 Here is your key name. 304 00:17:39,000 --> 00:17:44,000 Now in order to access this key you can actually see that I have already uploaded it over here. 305 00:17:44,000 --> 00:17:44,000 Right. 306 00:17:45,000 --> 00:17:51,000 So let's say since I'm going to use a chatbot which will be interacting with my API. 307 00:17:51,000 --> 00:17:56,000 So if you don't know about grok API, you can just go over here and search for grok.com. 308 00:17:56,000 --> 00:18:00,000 Uh, when you go to grok.com you can sign it with your email ID. 309 00:18:00,000 --> 00:18:05,000 Let's say I'm going to sign it because it provides you free API to access the open source models, you 310 00:18:05,000 --> 00:18:06,000 know. 311 00:18:06,000 --> 00:18:08,000 So I will go to grok API over here. 312 00:18:08,000 --> 00:18:13,000 And here you'll be able to see that a lot of different different models are basically available right. 313 00:18:13,000 --> 00:18:15,000 Llama 3.1. 314 00:18:15,000 --> 00:18:17,000 You also have llama three. 315 00:18:17,000 --> 00:18:21,000 You have gamma 29B you have distilled whisper large V three encoding. 316 00:18:21,000 --> 00:18:24,000 Uh n so all these kind of models are there. 317 00:18:24,000 --> 00:18:25,000 You can specifically use this particular model. 318 00:18:26,000 --> 00:18:28,000 And I have already covered this in my previous videos. 319 00:18:28,000 --> 00:18:29,000 Okay. 320 00:18:29,000 --> 00:18:33,000 Now in this scenario, what I'm actually going to do, I will be using some APIs for this. 321 00:18:33,000 --> 00:18:40,000 So if I go and click on Start Building here, you can see that I will go to my Grok Cloud console. 322 00:18:40,000 --> 00:18:43,000 Then here you can go to API keys. 323 00:18:43,000 --> 00:18:47,000 Once you go to API keys you can probably create your own API key. 324 00:18:47,000 --> 00:18:49,000 I've created so many different API keys. 325 00:18:49,000 --> 00:18:52,000 Or you can go ahead and create your own API key, right? 326 00:18:52,000 --> 00:18:55,000 I've already shown that also in my previous videos. 327 00:18:55,000 --> 00:19:00,000 Once you create an API key, just go ahead and click over here, add a new secret key. 328 00:19:00,000 --> 00:19:03,000 Just go ahead and write grok underscore API key and put it over here. 329 00:19:03,000 --> 00:19:05,000 Write all the API keys itself. 330 00:19:06,000 --> 00:19:10,000 Now once you're able to add in the secret, the next thing is that I will try to read that particular 331 00:19:10,000 --> 00:19:13,000 API key in my Google Colab. 332 00:19:13,000 --> 00:19:17,000 So in order to read, I will go ahead and write from Google Colab, import user data. 333 00:19:17,000 --> 00:19:23,000 And let's say that I want my grok underscore API underscore key. 334 00:19:23,000 --> 00:19:29,000 I can just use this user data dot get grok API key. 335 00:19:29,000 --> 00:19:35,000 So if I go ahead and just print this, you'll be able to see that I'm actually able to read it. 336 00:19:35,000 --> 00:19:38,000 You know proc API underscore key. 337 00:19:38,000 --> 00:19:41,000 This is just to show you don't use this anyhow. 338 00:19:41,000 --> 00:19:43,000 Uh so here you can see it is Grant. 339 00:19:44,000 --> 00:19:48,000 It is asking should we access this particular secret name grok API key. 340 00:19:48,000 --> 00:19:54,000 The notebook title untitled 106. Ipy in B does not have access to secret name grant access. 341 00:19:54,000 --> 00:19:56,000 So if I click on grant access. 342 00:19:56,000 --> 00:19:57,000 But right now what happened? 343 00:19:57,000 --> 00:19:58,000 Timeout happened. 344 00:19:58,000 --> 00:19:58,000 Right. 345 00:19:58,000 --> 00:20:00,000 So I'll go ahead and execute it once again. 346 00:20:00,000 --> 00:20:03,000 And now you'll be able to access this right. 347 00:20:03,000 --> 00:20:05,000 So this is my grok API key that you are able to see. 348 00:20:05,000 --> 00:20:08,000 Perfect right. 349 00:20:08,000 --> 00:20:10,000 So now this grok API key I can actually use it. 350 00:20:10,000 --> 00:20:15,000 I can use it for creating my application anything that I want okay. 351 00:20:16,000 --> 00:20:21,000 Now once this is done what I'm actually going to do I'm also going to use Lang Smith okay. 352 00:20:21,000 --> 00:20:24,000 And I hope everybody knows what exactly is Lang Smith. 353 00:20:24,000 --> 00:20:24,000 Right. 354 00:20:24,000 --> 00:20:28,000 So here I will go ahead and write Lang Smith. 355 00:20:29,000 --> 00:20:31,000 Uh, Lang Smith actually helps you to. 356 00:20:31,000 --> 00:20:37,000 So if I go ahead and just do sign up right, it will be able to help you to track each and every information 357 00:20:37,000 --> 00:20:41,000 with respect to the interaction that you have actually created in your chatbot, right? 358 00:20:41,000 --> 00:20:47,000 So if you go to Lang Smith over here, here you also you'll be able to get the dashboard right. 359 00:20:47,000 --> 00:20:50,000 So I'll go to settings. 360 00:20:51,000 --> 00:20:52,000 Here is my API key. 361 00:20:52,000 --> 00:20:55,000 If you don't have an API key go ahead and create an API key. 362 00:20:55,000 --> 00:21:00,000 But if you go ahead and see my secret key I've already added that Lang Smith underscore API key. 363 00:21:00,000 --> 00:21:01,000 Okay. 364 00:21:03,000 --> 00:21:06,000 Now let's go ahead and read the Lang Smith key also. 365 00:21:06,000 --> 00:21:07,000 So I will go ahead and write. 366 00:21:07,000 --> 00:21:13,000 Lang Smith is equal to user data dot get. 367 00:21:13,000 --> 00:21:20,000 And here also I'm going to use Lang Smith Lang Smith. 368 00:21:20,000 --> 00:21:22,000 Let's see what is the key name. 369 00:21:26,000 --> 00:21:27,000 Okay. 370 00:21:29,000 --> 00:21:33,000 so I will just go ahead and print my Lange Smith. 371 00:21:34,000 --> 00:21:35,000 Okay. 372 00:21:36,000 --> 00:21:40,000 So here you will be able to see that I will also be able to get it. 373 00:21:40,000 --> 00:21:41,000 So it will ask for grant access. 374 00:21:41,000 --> 00:21:43,000 I will give the grant access over here. 375 00:21:43,000 --> 00:21:45,000 And it should be able to display it. 376 00:21:45,000 --> 00:21:47,000 And it is displaying a f. 377 00:21:47,000 --> 00:21:48,000 E is the last term. 378 00:21:48,000 --> 00:21:49,000 F is also over here. 379 00:21:50,000 --> 00:21:53,000 So I have read both this particular key and both. 380 00:21:53,000 --> 00:21:57,000 This key will be specifically used for creating my chatbot application. 381 00:21:57,000 --> 00:22:01,000 Lange Smith will be specifically used for tracking everything that is basically happening over here. 382 00:22:02,000 --> 00:22:05,000 Now the next thing will be that I will go ahead and import OS. 383 00:22:06,000 --> 00:22:09,000 Then let's go ahead and import OS dot environ. 384 00:22:09,000 --> 00:22:12,000 I will just go ahead and keep save all these things right. 385 00:22:12,000 --> 00:22:20,000 So first of all I need Lange chain or sorry Lange Smith API key okay I can also go ahead and write Lange 386 00:22:20,000 --> 00:22:20,000 Smith. 387 00:22:20,000 --> 00:22:24,000 Or I can also go ahead and write Lange chain API key. 388 00:22:24,000 --> 00:22:27,000 So let's go ahead and do this Lange chain an API key. 389 00:22:27,000 --> 00:22:30,000 I will set this to my lamb-smith. 390 00:22:30,000 --> 00:22:34,000 Okay, we need to set up this specific key itself. 391 00:22:34,000 --> 00:22:34,000 Okay. 392 00:22:35,000 --> 00:22:38,000 Um, then my end point end point is specifically not required. 393 00:22:38,000 --> 00:22:41,000 I will just go ahead and copy this. 394 00:22:41,000 --> 00:22:42,000 Two things. 395 00:22:42,000 --> 00:22:45,000 And this is basically just used to set up the basic requirements. 396 00:22:45,000 --> 00:22:45,000 Right. 397 00:22:45,000 --> 00:22:48,000 Like chain tracing V2 and Lang chain project okay. 398 00:22:48,000 --> 00:22:54,000 So let's say this will basically be my course lang graph okay. 399 00:22:54,000 --> 00:22:56,000 So this is what is my project name that I'm actually writing. 400 00:22:57,000 --> 00:23:02,000 I'm saying that hey, we need to make sure that you need to keep the tracing underscore v2 as true. 401 00:23:02,000 --> 00:23:06,000 And lang lang chain API key is nothing, but it is assigned to lang with API key. 402 00:23:06,000 --> 00:23:09,000 Now you may be thinking, Chris, why did you use lang chain underscore API key? 403 00:23:09,000 --> 00:23:11,000 No, you can also use Lang Smith. 404 00:23:11,000 --> 00:23:14,000 But according to our documentation, when I saw both of them were satisfied. 405 00:23:14,000 --> 00:23:17,000 So I just used lang chain underscore API key. 406 00:23:17,000 --> 00:23:19,000 So let's go ahead and execute this. 407 00:23:20,000 --> 00:23:24,000 So once this is executed you'll be able to see all the information over here. 408 00:23:24,000 --> 00:23:33,000 Now quickly let's go ahead and write from long chain underscore grok import Chad grok because I need 409 00:23:33,000 --> 00:23:35,000 to use the Chad grant open source models. 410 00:23:35,000 --> 00:23:36,000 Okay. 411 00:23:36,000 --> 00:23:38,000 Now this is done. 412 00:23:38,000 --> 00:23:42,000 Now I will go ahead and create my LM model, which is nothing but Chad Grok. 413 00:23:42,000 --> 00:23:50,000 And inside this I will be using my grok underscore API underscore key which is equal to grok API key. 414 00:23:51,000 --> 00:23:54,000 And my model underscore name will be nothing. 415 00:23:54,000 --> 00:23:57,000 But you can use multiple models any models that you want. 416 00:23:57,000 --> 00:24:00,000 So in the grok cloud I can see there is llama 3.1. 417 00:24:00,000 --> 00:24:04,000 Anything that you want I will just go ahead and use this gamma two nine be it. 418 00:24:04,000 --> 00:24:05,000 Okay. 419 00:24:05,000 --> 00:24:08,000 So this specific model I will go ahead and use it. 420 00:24:08,000 --> 00:24:09,000 It is up to you now. 421 00:24:09,000 --> 00:24:12,000 Nothing compulsory which model you really need to use. 422 00:24:12,000 --> 00:24:15,000 You can use any model that is provided by grok right. 423 00:24:15,000 --> 00:24:16,000 So this is done. 424 00:24:16,000 --> 00:24:19,000 This is my LM model okay. 425 00:24:21,000 --> 00:24:23,000 Now the next step will be that. 426 00:24:23,000 --> 00:24:26,000 Now here you can see here I'm able to access all the models. 427 00:24:26,000 --> 00:24:28,000 I'm able to access the model gamma two nine. 428 00:24:28,000 --> 00:24:29,000 Be it. 429 00:24:29,000 --> 00:24:39,000 Okay, now it's time we start building a chat bot using line graph. 430 00:24:39,000 --> 00:24:40,000 Right. 431 00:24:40,000 --> 00:24:43,000 So here is what we are going to basically start. 432 00:24:43,000 --> 00:24:45,000 And this is the most important thing right. 433 00:24:45,000 --> 00:24:47,000 So if I probably go ahead and say this okay. 434 00:24:48,000 --> 00:24:55,000 So first of all uh understand there are multiple things which we really need to start with the importing 435 00:24:55,000 --> 00:24:55,000 part. 436 00:24:55,000 --> 00:24:56,000 Okay. 437 00:24:56,000 --> 00:25:00,000 So first of all I will be importing something called as annotated. 438 00:25:00,000 --> 00:25:01,000 Right. 439 00:25:01,000 --> 00:25:06,000 So from typing I will be importing annotated from typing extension I will be importing type dict. 440 00:25:06,000 --> 00:25:06,000 Okay. 441 00:25:07,000 --> 00:25:13,000 Uh along with this I will be importing two important libraries from Lang graph. 442 00:25:13,000 --> 00:25:19,000 So I will go ahead and right from lang graph, uh you'll understand why this importing is done just 443 00:25:19,000 --> 00:25:20,000 in some time. 444 00:25:20,000 --> 00:25:20,000 Okay. 445 00:25:20,000 --> 00:25:21,000 From lang graph. 446 00:25:21,000 --> 00:25:23,000 dot graph. 447 00:25:23,000 --> 00:25:27,000 Okay I'm going to just go ahead and import two things. 448 00:25:27,000 --> 00:25:29,000 One is state graph. 449 00:25:29,000 --> 00:25:33,000 State graph actually helps you to manage the entire state management. 450 00:25:33,000 --> 00:25:38,000 Then your start node start node and your end node. 451 00:25:38,000 --> 00:25:38,000 Right. 452 00:25:38,000 --> 00:25:44,000 You remember that I actually created a diagram right where we had a start node. 453 00:25:44,000 --> 00:25:50,000 Then we had an end node which actually, uh, shows the flow of the entire chatbot itself. 454 00:25:50,000 --> 00:25:51,000 Okay. 455 00:25:51,000 --> 00:25:55,000 Along with this, uh, I will also be showing like this. 456 00:25:55,000 --> 00:25:58,000 See, the state graph is basically used for the state management purpose. 457 00:25:59,000 --> 00:26:04,000 Now the state graph needs to keep on changing based on some parameters. 458 00:26:04,000 --> 00:26:05,000 Okay. 459 00:26:05,000 --> 00:26:15,000 So for that what I will be doing I will go ahead and write from line graph, line graph dot graph dot 460 00:26:15,000 --> 00:26:18,000 messages message. 461 00:26:18,000 --> 00:26:22,000 I'm just going to go ahead and import add underscore messages. 462 00:26:22,000 --> 00:26:23,000 Okay. 463 00:26:23,000 --> 00:26:25,000 Now this is one of the function. 464 00:26:25,000 --> 00:26:29,000 What it does is that we have this something called as messages right. 465 00:26:29,000 --> 00:26:35,000 As we keep on adding the messages over here, we will be able to see that our state management, our 466 00:26:35,000 --> 00:26:37,000 state of the agent will keep on changing. 467 00:26:38,000 --> 00:26:43,000 Now this messages is just like you can understand like a when a user is giving a query, the LM model 468 00:26:43,000 --> 00:26:44,000 is giving a response. 469 00:26:44,000 --> 00:26:48,000 When it is giving a response, the message will get added over here. 470 00:26:48,000 --> 00:26:51,000 And then my state of the chatbot will also get changed. 471 00:26:51,000 --> 00:26:52,000 Right. 472 00:26:52,000 --> 00:26:55,000 So this messages is basically keeping track of all those things. 473 00:26:55,000 --> 00:26:56,000 Okay. 474 00:26:56,000 --> 00:26:58,000 So now let's go ahead and execute this. 475 00:26:58,000 --> 00:27:01,000 So this has got executed successfully. 476 00:27:01,000 --> 00:27:04,000 You can understand each and every thing I have actually explained. 477 00:27:04,000 --> 00:27:07,000 We will talk about this two right just in some time. 478 00:27:08,000 --> 00:27:11,000 Now we will go ahead and create our own class. 479 00:27:11,000 --> 00:27:18,000 Let's say this is my class state which will be uh, making sure to, uh, properly control the entire 480 00:27:18,000 --> 00:27:19,000 state management. 481 00:27:19,000 --> 00:27:23,000 Here I will go ahead and write typed dict. 482 00:27:23,000 --> 00:27:23,000 Okay. 483 00:27:24,000 --> 00:27:28,000 So I will go ahead and write typed dict typed dict. 484 00:27:28,000 --> 00:27:29,000 Okay. 485 00:27:31,000 --> 00:27:32,000 Typed dict okay. 486 00:27:32,000 --> 00:27:38,000 So this class is basically inheriting this particular type of dict. 487 00:27:38,000 --> 00:27:39,000 Okay. 488 00:27:39,000 --> 00:27:41,000 Now what we will do. 489 00:27:41,000 --> 00:27:44,000 We will go ahead and write some comments over here. 490 00:27:44,000 --> 00:27:44,000 Okay. 491 00:27:44,000 --> 00:27:48,000 So that you'll be able to understand messages that have the type list. 492 00:27:48,000 --> 00:27:54,000 The add message function in the annotation defines how this state key should be updated. 493 00:27:54,000 --> 00:27:57,000 It appends the message to the list rather than overwriting. 494 00:27:57,000 --> 00:28:01,000 So inside this class I've created a variable called as messages. 495 00:28:01,000 --> 00:28:01,000 Okay. 496 00:28:01,000 --> 00:28:05,000 And this messages is of type annotated. 497 00:28:05,000 --> 00:28:08,000 And this annotated is basically saying hey it is a list type. 498 00:28:08,000 --> 00:28:11,000 And here I'm using this function called as add messages. 499 00:28:11,000 --> 00:28:18,000 This add messages will be responsible on adding or appending the messages to this list okay. 500 00:28:18,000 --> 00:28:23,000 Which is basically created in the form of list in this messages variable, and it will not override 501 00:28:23,000 --> 00:28:23,000 them. 502 00:28:23,000 --> 00:28:27,000 The entire state management will be controlled as we keep on adding this particular messages, because 503 00:28:28,000 --> 00:28:30,000 on every add we will be changing our state. 504 00:28:30,000 --> 00:28:31,000 Okay. 505 00:28:32,000 --> 00:28:38,000 Now the next thing that we will go ahead and define, since I have defined my class state, I will go 506 00:28:38,000 --> 00:28:41,000 ahead and write my graph builder. 507 00:28:41,000 --> 00:28:41,000 Okay. 508 00:28:41,000 --> 00:28:43,000 I will go ahead and define my graph builder. 509 00:28:43,000 --> 00:28:47,000 So this is what we start our graph building process. 510 00:28:47,000 --> 00:28:52,000 So here I'm going to use state graph the state graph which I have actually imported it over here. 511 00:28:52,000 --> 00:28:58,000 And this state graph will have this particular class which is called as state because this state knows 512 00:28:58,000 --> 00:29:02,000 which messages are there, what messages are basically getting appended. 513 00:29:02,000 --> 00:29:06,000 And this graph builder should be responsible in managing the entire state management. 514 00:29:06,000 --> 00:29:06,000 Right. 515 00:29:06,000 --> 00:29:10,000 So once I execute this here is my graph builder. 516 00:29:10,000 --> 00:29:12,000 So let me just go ahead and execute this. 517 00:29:12,000 --> 00:29:15,000 So this is my graph builder over here right. 518 00:29:15,000 --> 00:29:18,000 So here you can see line graph dot graph dot state. 519 00:29:18,000 --> 00:29:21,000 State graph at this specific location. 520 00:29:21,000 --> 00:29:27,000 So guys now after we have created the graph builder uh what we are basically going to do is that uh 521 00:29:27,000 --> 00:29:29,000 already in this diagram you saw that right. 522 00:29:29,000 --> 00:29:31,000 We are going to create this chat bot. 523 00:29:31,000 --> 00:29:34,000 Now this chat bot should be interacting with our LLM. 524 00:29:34,000 --> 00:29:36,000 So for this we will go ahead and write some definition. 525 00:29:37,000 --> 00:29:43,000 So let's quickly go ahead and create a function definition chat bot. 526 00:29:43,000 --> 00:29:51,000 And remember whenever we are creating any node right in this entire graph builder, it needs to take 527 00:29:51,000 --> 00:29:53,000 the parameter as state. 528 00:29:53,000 --> 00:29:55,000 Okay, whatever state we are giving over here. 529 00:29:56,000 --> 00:30:02,000 And this will be important because the reason is very simple because based on this state message, right. 530 00:30:02,000 --> 00:30:07,000 Whatever messages, whatever interaction that we are doing, the state management will keep on changing. 531 00:30:07,000 --> 00:30:12,000 So here we go ahead and define this chat bot where we take the parameter as state. 532 00:30:12,000 --> 00:30:14,000 And then we return. 533 00:30:14,000 --> 00:30:20,000 You know that after any response that we get from the chatbot, we need to update this messages variable. 534 00:30:20,000 --> 00:30:24,000 So here I will go ahead and create this messages. 535 00:30:24,000 --> 00:30:28,000 And here I will just go ahead and write LM dot invoke. 536 00:30:28,000 --> 00:30:28,000 Okay. 537 00:30:28,000 --> 00:30:36,000 And this invoke will be specifically invoking from the state message which will have the user queries. 538 00:30:36,000 --> 00:30:36,000 Right. 539 00:30:36,000 --> 00:30:41,000 So whenever a user queries you will be able to see that this messages will get appended in this particular 540 00:30:41,000 --> 00:30:42,000 message variable. 541 00:30:42,000 --> 00:30:45,000 And once it does that we are just going to invoke that. 542 00:30:45,000 --> 00:30:49,000 And whatever response we are getting it we are again appending it over here. 543 00:30:49,000 --> 00:30:49,000 Right? 544 00:30:49,000 --> 00:30:51,000 Or we are putting in this particular value. 545 00:30:51,000 --> 00:30:54,000 We are returning this entire in this particular format. 546 00:30:54,000 --> 00:30:57,000 When we return this when we are inheriting the state class. 547 00:30:57,000 --> 00:30:58,000 Right. 548 00:30:58,000 --> 00:31:03,000 It is going to understand, hey, whenever we return this kind of message, it is going to trigger this 549 00:31:03,000 --> 00:31:06,000 add message and it is going to add this in this messages variable. 550 00:31:06,000 --> 00:31:07,000 Okay. 551 00:31:07,000 --> 00:31:13,000 So just understand in this way is that here I have a chatbot function which is invoking the previous 552 00:31:13,000 --> 00:31:18,000 messages given by the user, and we are returning some kind of messages over here. 553 00:31:18,000 --> 00:31:22,000 Okay, so once we execute this I will be getting my chat bot. 554 00:31:22,000 --> 00:31:26,000 Now this chat bot needs to get added in this graph builder. 555 00:31:26,000 --> 00:31:33,000 So here I will go ahead and write graph underscore builder dot add underscore node. 556 00:31:33,000 --> 00:31:40,000 And here I'm going to specifically use chat bot as my node name which will have the functionality of 557 00:31:40,000 --> 00:31:42,000 this particular chat bot. 558 00:31:42,000 --> 00:31:42,000 Okay. 559 00:31:42,000 --> 00:31:47,000 So once I execute this you'll be able to see that this entire node is basically getting added. 560 00:31:47,000 --> 00:31:53,000 So now if I go ahead and just display this you'll not be able to see much things over here. 561 00:31:53,000 --> 00:31:56,000 But we will be seeing the entire diagram. 562 00:31:56,000 --> 00:32:01,000 So step by step you can see that what we have done first of all we have created this class state. 563 00:32:01,000 --> 00:32:03,000 Then we have created our graph builder. 564 00:32:03,000 --> 00:32:06,000 Then we have defined our chatbot. 565 00:32:06,000 --> 00:32:09,000 What functionality is basically doing and what it is returning. 566 00:32:09,000 --> 00:32:10,000 It is returning. 567 00:32:10,000 --> 00:32:13,000 Just message colon some some output that we are getting over here. 568 00:32:13,000 --> 00:32:14,000 Right? 569 00:32:14,000 --> 00:32:17,000 And remember, the chat bot is inheriting the state class. 570 00:32:17,000 --> 00:32:21,000 And the state class has one variable messages in the form of list. 571 00:32:21,000 --> 00:32:27,000 And there is a function called as add underscore message, which will keep on appending whatever message 572 00:32:27,000 --> 00:32:29,000 we are specifically getting over here. 573 00:32:29,000 --> 00:32:29,000 Right. 574 00:32:29,000 --> 00:32:31,000 So that is what it is basically doing. 575 00:32:32,000 --> 00:32:38,000 Now since we have created this graph builder, now it's time that we connect this chatbot to the start 576 00:32:38,000 --> 00:32:39,000 and the end node okay. 577 00:32:40,000 --> 00:32:46,000 So here I'm going to go ahead and write Graph Builder dot add edge okay. 578 00:32:46,000 --> 00:32:48,000 So add edge start chatbot. 579 00:32:48,000 --> 00:32:49,000 Okay. 580 00:32:49,000 --> 00:32:52,000 So we are basically going to add the start and the chatbot. 581 00:32:52,000 --> 00:32:55,000 And similarly we are going to add chatbot till the end. 582 00:32:55,000 --> 00:32:56,000 Right. 583 00:32:56,000 --> 00:33:01,000 So then only we will be able to find out or will be able to get this kind of flow. 584 00:33:01,000 --> 00:33:03,000 So start is basically appended with chatbot. 585 00:33:03,000 --> 00:33:09,000 And chatbot is basically getting appended with end start basically means whenever we get a user query 586 00:33:09,000 --> 00:33:13,000 it will just start the process, then chatbot will do the interaction with LLM. 587 00:33:13,000 --> 00:33:18,000 It will give us the value and it will go to the end state and how the state management basically happening 588 00:33:18,000 --> 00:33:22,000 because of this state class, which we have inherited in Graph Builder. 589 00:33:22,000 --> 00:33:23,000 Okay. 590 00:33:23,000 --> 00:33:26,000 So once we execute this, this is done. 591 00:33:27,000 --> 00:33:32,000 So finally what we do after creating this, after adding all this nodes we go ahead and write Graph 592 00:33:32,000 --> 00:33:33,000 Builder. 593 00:33:34,000 --> 00:33:35,000 We need to compile it. 594 00:33:35,000 --> 00:33:38,000 So we'll go ahead and write dot compile. 595 00:33:38,000 --> 00:33:41,000 So once we compile it we'll be getting our entire graph ready. 596 00:33:41,000 --> 00:33:44,000 So here is my graph itself. 597 00:33:44,000 --> 00:33:47,000 So once I execute this my graph is ready. 598 00:33:47,000 --> 00:33:49,000 Now let me just go ahead and display this. 599 00:33:49,000 --> 00:33:55,000 So in order to display this in the documentation I saw this code where they are importing this image 600 00:33:55,000 --> 00:33:55,000 and display. 601 00:33:55,000 --> 00:33:58,000 And there is something called as graph dot get graph. 602 00:33:58,000 --> 00:34:03,000 So here instead of graph I will write graph builder okay or sorry. 603 00:34:04,000 --> 00:34:05,000 It should be graph only because we have compiled it. 604 00:34:05,000 --> 00:34:12,000 Get graph draw mermaid png okay so once I execute this, you'll be able to see that I'll be getting 605 00:34:12,000 --> 00:34:13,000 this entire flow. 606 00:34:13,000 --> 00:34:21,000 So start and end are just like one private, uh, functions that are present inside the, uh, state. 607 00:34:21,000 --> 00:34:22,000 State? 608 00:34:22,000 --> 00:34:26,000 Uh, if I probably say this particular class, the state graph class. 609 00:34:26,000 --> 00:34:27,000 Right. 610 00:34:27,000 --> 00:34:31,000 Uh, which is present inside this line graph, dot graph, lang lang graph or graph. 611 00:34:31,000 --> 00:34:32,000 Right. 612 00:34:32,000 --> 00:34:37,000 And now this will basically as soon as the user queries we will go to the start state. 613 00:34:37,000 --> 00:34:38,000 Then it goes to the chat bot. 614 00:34:38,000 --> 00:34:40,000 Here the interaction will basically happen. 615 00:34:40,000 --> 00:34:43,000 And once the interaction happens the state should change right? 616 00:34:44,000 --> 00:34:46,000 Once we get the response it will go to the end state. 617 00:34:46,000 --> 00:34:49,000 Now let's go ahead and execute this. 618 00:34:49,000 --> 00:34:50,000 And then only you'll be able to see the output. 619 00:34:50,000 --> 00:34:51,000 Okay. 620 00:34:51,000 --> 00:34:53,000 Uh and we are just going to start this. 621 00:34:53,000 --> 00:34:54,000 Okay. 622 00:34:54,000 --> 00:34:56,000 So here I will just go ahead and write. 623 00:34:56,000 --> 00:35:04,000 While true user underscore input is equal to input 624 00:35:07,000 --> 00:35:11,000 User input user. 625 00:35:11,000 --> 00:35:20,000 And here I'm going to just go ahead and write f user underscore input dot lower in. 626 00:35:22,000 --> 00:35:29,000 Let's say I will go ahead and say hey if you are just going and typing in quit or Q right. 627 00:35:29,000 --> 00:35:32,000 You're just going to stop the conversation with the flow, right? 628 00:35:32,000 --> 00:35:34,000 So here I'm just going to write print. 629 00:35:36,000 --> 00:35:37,000 Goodbye. 630 00:35:38,000 --> 00:35:38,000 Okay. 631 00:35:39,000 --> 00:35:42,000 And then we are just going to break from here. 632 00:35:42,000 --> 00:35:42,000 Okay. 633 00:35:43,000 --> 00:35:46,000 But if the user inputs something else. 634 00:35:46,000 --> 00:35:51,000 So here I will go ahead and write for event in graph dot stream. 635 00:35:51,000 --> 00:35:52,000 Okay. 636 00:35:52,000 --> 00:35:53,000 We are just going to stream. 637 00:35:53,000 --> 00:35:59,000 And here we are going to use this messages as my key variable messages is a colon. 638 00:35:59,000 --> 00:36:02,000 And here I'm going to give based on user. 639 00:36:02,000 --> 00:36:03,000 See. 640 00:36:03,000 --> 00:36:09,000 Initially whenever a user gives a input message I need to set this as user right as the parameter, 641 00:36:09,000 --> 00:36:12,000 and here will basically be my user input. 642 00:36:12,000 --> 00:36:20,000 Okay, then I will go ahead and write print event dot values. 643 00:36:21,000 --> 00:36:22,000 We are just going to print the values. 644 00:36:22,000 --> 00:36:28,000 Then here more we can go ahead and probably convert this or explore these values. 645 00:36:28,000 --> 00:36:33,000 So here I will write for value in event dot values print value. 646 00:36:33,000 --> 00:36:37,000 And inside that value there will be a key which is called as message messages. 647 00:36:37,000 --> 00:36:38,000 Okay. 648 00:36:38,000 --> 00:36:42,000 And then we will go ahead and print our assistant. 649 00:36:42,000 --> 00:36:51,000 Message assistant basically means the message that is basically coming from our uh LMS. 650 00:36:51,000 --> 00:36:58,000 So here you will be able to see value messages dot content. 651 00:36:59,000 --> 00:37:01,000 So here let's explore this code. 652 00:37:01,000 --> 00:37:03,000 First of all a user is giving an input. 653 00:37:03,000 --> 00:37:08,000 If it is not giving given, quit and Q so it will go to graph dot stream with respect to all the messages 654 00:37:08,000 --> 00:37:10,000 that users have already given. 655 00:37:10,000 --> 00:37:13,000 Then we are going to get that event dot values for value. 656 00:37:13,000 --> 00:37:14,000 We are going to get two important things. 657 00:37:14,000 --> 00:37:18,000 One is value of messages and one is the value of message of content. 658 00:37:18,000 --> 00:37:22,000 So this value of messages I think it should have the user message. 659 00:37:22,000 --> 00:37:25,000 And this should have the LM model response response. 660 00:37:25,000 --> 00:37:27,000 So let me go ahead and execute it. 661 00:37:28,000 --> 00:37:30,000 So I will go ahead and write hello. 662 00:37:31,000 --> 00:37:31,000 Let's see. 663 00:37:32,000 --> 00:37:34,000 So here assistant you can see right. 664 00:37:34,000 --> 00:37:34,000 Hello. 665 00:37:34,000 --> 00:37:38,000 How can I help you see all these messages are basically coming in the form of big value right. 666 00:37:38,000 --> 00:37:39,000 So here. 667 00:37:39,000 --> 00:37:40,000 Hello. 668 00:37:40,000 --> 00:37:41,000 How can I help you? 669 00:37:41,000 --> 00:37:42,000 Today is the response. 670 00:37:42,000 --> 00:37:43,000 And I'm able to get it. 671 00:37:43,000 --> 00:37:48,000 So let me go and ask what is generative AI right. 672 00:37:48,000 --> 00:37:53,000 So here you will be able to see that all the response is there right. 673 00:37:53,000 --> 00:37:55,000 Generative AI is a type of artificial intelligence. 674 00:37:55,000 --> 00:37:56,000 Think of it. 675 00:37:56,000 --> 00:37:57,000 So it's amazing right? 676 00:37:57,000 --> 00:37:59,000 You are able to get the entire response. 677 00:38:00,000 --> 00:38:03,000 And here also you can see response metadata content is over here. 678 00:38:03,000 --> 00:38:08,000 So if you just go ahead and explore this, some of the other keys will be available over here. 679 00:38:08,000 --> 00:38:08,000 Right. 680 00:38:08,000 --> 00:38:13,000 And uh, uh, if you go ahead and see down. 681 00:38:13,000 --> 00:38:15,000 So this is my entire generated message. 682 00:38:15,000 --> 00:38:20,000 So if I just go ahead and write Q it should be exiting over here. 683 00:38:20,000 --> 00:38:20,000 Right. 684 00:38:20,000 --> 00:38:22,000 So here you can see it says goodbye. 685 00:38:22,000 --> 00:38:25,000 So guys, I hope you liked this specific video. 686 00:38:25,000 --> 00:38:31,000 And you were able to understand how to basically create a simple chatbot in the form of Lang with the 687 00:38:31,000 --> 00:38:33,000 help of Lang graph. 688 00:38:33,000 --> 00:38:38,000 And here we have basically used the graph itself right from start till the end node. 689 00:38:38,000 --> 00:38:44,000 We have understood that whenever we create any node, it also needs to have a definition and uh, how 690 00:38:44,000 --> 00:38:46,000 we can connect each and every node. 691 00:38:46,000 --> 00:38:52,000 Now in the upcoming videos we are going to develop more complex projects on Lang graph where we will 692 00:38:52,000 --> 00:38:54,000 be using external tools. 693 00:38:54,000 --> 00:38:59,000 Uh, there will just not use one node, but there will be multiple nodes as we go ahead. 694 00:38:59,000 --> 00:39:00,000 So I hope you like this particular video. 695 00:39:00,000 --> 00:39:02,000 I will see you all in the next video. 696 00:39:02,000 --> 00:39:02,000 Thank you.