1 00:00:00,000 --> 00:00:00,000 Hello guys! 2 00:00:00,000 --> 00:00:05,000 So in our previous video we had seen that how we created this lantern demo with gamma model with the 3 00:00:05,000 --> 00:00:06,000 help of Lama. 4 00:00:06,000 --> 00:00:10,000 And here you could see that I asked any question and is able to give me the answer. 5 00:00:10,000 --> 00:00:13,000 Let's say if I go ahead and ask what is machine learning? 6 00:00:13,000 --> 00:00:16,000 I'll be able to see that once I press enter, I will be able to get the response. 7 00:00:16,000 --> 00:00:21,000 And again, this is interacting with the gamma model that is downloaded locally with the help of Lama. 8 00:00:21,000 --> 00:00:22,000 Right. 9 00:00:22,000 --> 00:00:27,000 One thing that I forgot to tell you about, you know, like how, uh, see, in my code, uh, which 10 00:00:27,000 --> 00:00:32,000 I was actually running right here, we are making sure that the tracking also happens right in the Lange 11 00:00:32,000 --> 00:00:33,000 Smith. 12 00:00:33,000 --> 00:00:38,000 So in this video I'll be talking about like how this entire information is basically getting, uh, 13 00:00:38,000 --> 00:00:39,000 tracked in the Lange Smith. 14 00:00:39,000 --> 00:00:42,000 And the best thing is that no cost is involved in open. 15 00:00:42,000 --> 00:00:45,000 I usually cost was involved, but in this nothing is there. 16 00:00:45,000 --> 00:00:47,000 So let me just go ahead and open this. 17 00:00:47,000 --> 00:00:49,000 So this was my projects okay. 18 00:00:49,000 --> 00:00:51,000 So Jen I or app with open I. 19 00:00:51,000 --> 00:00:53,000 So here you can see what is machine learning. 20 00:00:53,000 --> 00:00:54,000 What is generative AI. 21 00:00:54,000 --> 00:00:55,000 This was the question that I asked. 22 00:00:55,000 --> 00:00:57,000 So let's open this first one. 23 00:00:57,000 --> 00:00:59,000 So see how is the runnable sequence. 24 00:00:59,000 --> 00:01:01,000 So first of all I got the chat prompt template. 25 00:01:01,000 --> 00:01:05,000 So let me just hide my face so that you'll be able to clearly clearly see it. 26 00:01:05,000 --> 00:01:08,000 So my input question was what is machine learning. 27 00:01:08,000 --> 00:01:09,000 Right. 28 00:01:09,000 --> 00:01:15,000 And here you could basically see that, uh, I'm getting some kind of content to my AI assistant. 29 00:01:15,000 --> 00:01:17,000 It is saying, hey, you are a helpful assistant. 30 00:01:17,000 --> 00:01:20,000 Please respond to the question that is asked. 31 00:01:20,000 --> 00:01:20,000 Right. 32 00:01:20,000 --> 00:01:26,000 And then, uh, once we go from here to Olama, right now here with respect to Olama here we are going 33 00:01:26,000 --> 00:01:27,000 to use the llama three model. 34 00:01:27,000 --> 00:01:28,000 right? 35 00:01:28,000 --> 00:01:30,000 You can also open the playground if you want. 36 00:01:30,000 --> 00:01:35,000 But here you can see my human question is that what is machine learning then? 37 00:01:35,000 --> 00:01:40,000 Uh, this entire message is basically getting displayed by the ulama itself, right? 38 00:01:40,000 --> 00:01:42,000 Ulama which is using this gamma model. 39 00:01:42,000 --> 00:01:43,000 Right. 40 00:01:43,000 --> 00:01:45,000 And this is what is basically getting returned. 41 00:01:45,000 --> 00:01:45,000 Okay. 42 00:01:46,000 --> 00:01:52,000 Now, after using this prompt and completion from Ulama, I will go ahead into the string output parser 43 00:01:52,000 --> 00:01:54,000 that is the str output parser. 44 00:01:54,000 --> 00:01:59,000 And with respect to this you are able to see this entire output that is basically getting displayed 45 00:01:59,000 --> 00:02:00,000 along with the styling. 46 00:02:00,000 --> 00:02:00,000 Right? 47 00:02:00,000 --> 00:02:01,000 Which is amazing. 48 00:02:01,000 --> 00:02:05,000 So this entire chain here, you can see that it is being tracked. 49 00:02:05,000 --> 00:02:07,000 How much latency is there? 50 00:02:07,000 --> 00:02:11,000 How much time is basically taking up, you know, with respect to more information? 51 00:02:11,000 --> 00:02:15,000 Let's say if I want more information over here, you know, if you go to the right side, right. 52 00:02:15,000 --> 00:02:18,000 How much token see cost is zero. 53 00:02:18,000 --> 00:02:19,000 There is no cost involved over here. 54 00:02:19,000 --> 00:02:20,000 Right. 55 00:02:20,000 --> 00:02:21,000 So this is also amazing. 56 00:02:21,000 --> 00:02:23,000 See no cost is involved. 57 00:02:23,000 --> 00:02:24,000 Right. 58 00:02:24,000 --> 00:02:28,000 So over here, uh, no cost is involved because I'm using the complete open source model. 59 00:02:28,000 --> 00:02:29,000 Right. 60 00:02:29,000 --> 00:02:34,000 So I hope, uh, you are able to understand this, uh, with respect to the kind of thing that we have 61 00:02:34,000 --> 00:02:35,000 developed. 62 00:02:35,000 --> 00:02:39,000 If you still feel that OpenAI, you don't have credit card, you don't want to use any balance. 63 00:02:39,000 --> 00:02:41,000 As such, you can go ahead and use open source models. 64 00:02:41,000 --> 00:02:42,000 Right. 65 00:02:42,000 --> 00:02:46,000 And that is what I'm actually going to show you as we go ahead, more amazing end to end projects that 66 00:02:46,000 --> 00:02:47,000 I'll try to create. 67 00:02:47,000 --> 00:02:47,000 Right? 68 00:02:47,000 --> 00:02:49,000 So yes, this was it for my side. 69 00:02:49,000 --> 00:02:50,000 I hope you liked this particular video. 70 00:02:50,000 --> 00:02:52,000 I will see you all in the next video. 71 00:02:52,000 --> 00:02:52,000 Thank you.