1 00:00:00,440 --> 00:00:02,640 And a very warm welcome to cursor. 2 00:00:02,680 --> 00:00:03,320 Here we are. 3 00:00:03,360 --> 00:00:05,040 We are in week four. 4 00:00:05,080 --> 00:00:09,480 Landgraf, we're going to lab two, which is the lab for day three. 5 00:00:09,520 --> 00:00:10,280 It's confusing. 6 00:00:10,520 --> 00:00:14,080 Uh, so we're going to start with some imports as we do. 7 00:00:14,120 --> 00:00:18,280 And we are also going to do the low dot env that always needs to be done. 8 00:00:18,560 --> 00:00:21,200 And we are now going to go and set up Lang Smith. 9 00:00:21,200 --> 00:00:22,880 So there's a link to Lang Smith here. 10 00:00:22,880 --> 00:00:25,000 When you follow this link you'll get to their website. 11 00:00:25,000 --> 00:00:27,560 And the first thing you'll need to do is create an account. 12 00:00:27,800 --> 00:00:29,520 Uh, and it's free. 13 00:00:29,560 --> 00:00:33,440 It's free as long as you stay within some very high number, which we definitely will. 14 00:00:33,720 --> 00:00:35,400 Uh, so you can set that up. 15 00:00:35,400 --> 00:00:38,840 And when you come in, you're going to get this sort of dashboard a bit like this, except it will be 16 00:00:38,840 --> 00:00:39,360 empty. 17 00:00:39,520 --> 00:00:43,880 And the first thing to do is to press the setup tracing button right here. 18 00:00:43,880 --> 00:00:45,200 And this is going to fly up. 19 00:00:45,360 --> 00:00:48,880 You have to generate an API key so that you've got an API key. 20 00:00:49,000 --> 00:00:53,160 And as soon as you press that it will then fill this in down here. 21 00:00:53,440 --> 00:00:59,040 And you just simply then want to copy that to your clipboard, all of your, uh, fields, all of the 22 00:00:59,080 --> 00:01:01,320 key variables that you'll see here. 23 00:01:01,560 --> 00:01:04,720 Um, but just don't obviously don't take the OpenAI API key as well. 24 00:01:04,720 --> 00:01:06,840 You don't need that, But you need this. 25 00:01:07,080 --> 00:01:12,240 And then you will it will actually populate that API key with whatever you generate right here, which 26 00:01:12,240 --> 00:01:13,000 is great. 27 00:01:13,240 --> 00:01:21,280 And then you will go into, uh, back back here into your EMV file, which is just there, and you will 28 00:01:21,280 --> 00:01:26,560 add this in to your EMV file so that we have these variables set. 29 00:01:26,600 --> 00:01:31,240 And then once you've done that come back and run load dot env again so that they load in. 30 00:01:31,280 --> 00:01:32,800 Maybe I should have done that in the other order. 31 00:01:33,440 --> 00:01:34,280 So that's great. 32 00:01:34,280 --> 00:01:37,880 Then you have langsamt configured and you'll be able to see things. 33 00:01:38,080 --> 00:01:42,960 Now before we, uh, go further, I will just just talk through a few of the things we can expect to 34 00:01:42,960 --> 00:01:43,360 see. 35 00:01:43,640 --> 00:01:48,000 Um, so I called the project mastering agents, but you can call it whatever you want. 36 00:01:48,040 --> 00:01:48,560 Of course. 37 00:01:48,880 --> 00:01:52,480 Um, and you can see in here there's there's lots of stuff that I've been doing. 38 00:01:52,600 --> 00:01:58,200 You'll see that it for every time that I've invoked Landgraf, I get some sort of a of an entry here. 39 00:01:58,200 --> 00:02:00,480 I get the input and the output. 40 00:02:00,520 --> 00:02:03,480 If there's an error, which I had a couple of errors, then we will see them. 41 00:02:03,680 --> 00:02:05,520 It tells you when it happened. 42 00:02:05,560 --> 00:02:08,040 It tells you the latency, which is very helpful. 43 00:02:08,040 --> 00:02:11,530 And there's a bunch of other useful stuff here too, which we don't often get to see. 44 00:02:11,770 --> 00:02:17,010 The cost in this column is telling us how much this cost us to make this call to OpenAI. 45 00:02:17,290 --> 00:02:23,570 And for those people that are concerned about about API costs, do have a look at how insanely small 46 00:02:23,570 --> 00:02:24,330 these numbers are. 47 00:02:24,370 --> 00:02:25,930 It just really brings it to life. 48 00:02:26,090 --> 00:02:31,450 I realize that the main problem people have is with the upfront $5 you have to put in at the beginning, 49 00:02:31,450 --> 00:02:36,850 but I hope that you see that that until you get to such point as you are scaling, we are talking about 50 00:02:36,890 --> 00:02:42,570 not just fractions of a cent, but fractions of fractions of a cent for most of these. 51 00:02:42,850 --> 00:02:46,210 Um, it also tells you the number of tokens, which is helpful to know. 52 00:02:46,570 --> 00:02:51,490 I'm not sure the zeros were because I had some bug that I luckily then fixed. 53 00:02:51,650 --> 00:02:55,890 Uh, so you get to see a bunch of stuff in here and this is going to be useful. 54 00:02:55,890 --> 00:03:00,650 And when we actually have things to to look at, we will come back and take a look at that. 55 00:03:00,930 --> 00:03:01,490 Okay. 56 00:03:01,770 --> 00:03:02,570 Onwards. 57 00:03:02,810 --> 00:03:03,570 All right. 58 00:03:04,050 --> 00:03:09,210 So I found a useful function that's in the long chain community folder. 59 00:03:09,490 --> 00:03:16,090 Uh and it's called Google Sherpa API wrapper, which means that it's a nice little convenient wrapper 60 00:03:16,130 --> 00:03:22,450 around the same thing that we set up before the Sherpa API, where we already have the API key in our 61 00:03:22,450 --> 00:03:24,970 env file, which is convenient to use. 62 00:03:25,290 --> 00:03:29,210 And so we can create an instance of this thing Google soap API wrapper. 63 00:03:29,210 --> 00:03:33,610 And we can call Sherpa with something like what's the capital of France? 64 00:03:33,650 --> 00:03:36,050 And if we do this, then it will think for a moment. 65 00:03:36,050 --> 00:03:41,850 And indeed we get Paris is the capital and largest city of France, and with some stuff about it, from 66 00:03:41,850 --> 00:03:44,810 doing an internet search on this, which is great. 67 00:03:44,810 --> 00:03:50,530 And again, this is something that's part of what's free and included in the plan up until some several 68 00:03:50,570 --> 00:03:51,490 thousand calls. 69 00:03:51,490 --> 00:03:55,530 I think unlike OpenAI, which is charging us two and a half cents for each one. 70 00:03:56,410 --> 00:03:59,170 So that is, uh, that is good. 71 00:03:59,650 --> 00:04:06,090 Now, this is showing you some of the nice stuff that's actually in Long Chain rather than Landgraf, 72 00:04:06,090 --> 00:04:07,530 but Landgraf uses it to. 73 00:04:07,570 --> 00:04:11,650 I mentioned to you that Long chain already does sort of simple agent interactions. 74 00:04:11,650 --> 00:04:15,050 It already gives some some wrapper code, some abstraction code. 75 00:04:15,090 --> 00:04:16,690 And here is here is one of them. 76 00:04:16,690 --> 00:04:19,890 I kept the import here so we could see that it's from, from long chains. 77 00:04:20,050 --> 00:04:20,810 Long chain. 78 00:04:21,130 --> 00:04:21,570 So? 79 00:04:21,570 --> 00:04:27,850 So you can say that, uh, you can wrap a function like this with a tool object. 80 00:04:27,850 --> 00:04:32,330 You give it a name like search a function serpent run. 81 00:04:32,330 --> 00:04:35,730 That's what it will actually do when it needs to call this tool. 82 00:04:35,770 --> 00:04:43,770 And a description is what will be will be called in order to, um, when, when building the JSON around 83 00:04:43,770 --> 00:04:44,410 this tool. 84 00:04:44,770 --> 00:04:50,690 Uh, so that's wrapped it in a tool object, a long chain tool object. 85 00:04:50,690 --> 00:04:55,970 And as you can probably guess, this is going to take away all of the gumph about building that JSON 86 00:04:55,970 --> 00:04:59,130 object with all the stuff and the properties and everything else. 87 00:04:59,130 --> 00:05:04,010 It's going to take care of all of that for us, so we can now try out the same, the same question, 88 00:05:04,010 --> 00:05:10,410 what's the capital of France which we can do using tool search dot invoke the long chain way we are 89 00:05:10,410 --> 00:05:12,290 calling this tool and there we go. 90 00:05:12,330 --> 00:05:15,770 We get an answer of the capital of France, same thing. 91 00:05:15,770 --> 00:05:18,610 But now we're doing it by calling invoke. 92 00:05:18,850 --> 00:05:19,370 Okay. 93 00:05:19,410 --> 00:05:23,530 And now let's just show you what it's like to build a tool from scratch ourselves. 94 00:05:23,530 --> 00:05:24,610 It's super easy. 95 00:05:24,930 --> 00:05:28,660 Uh, so we'll use the same old thing that we like to do because it's nice. 96 00:05:28,700 --> 00:05:30,180 It's so tangible. 97 00:05:30,420 --> 00:05:36,420 Uh, using pushover, this is the same kind of function that is able to send a push notification to 98 00:05:36,460 --> 00:05:36,940 me. 99 00:05:36,940 --> 00:05:42,620 So we give it the usual docstring, we give it, uh, the information about it. 100 00:05:42,860 --> 00:05:45,100 Um, and, uh, here we go. 101 00:05:45,140 --> 00:05:45,980 That's that. 102 00:05:46,260 --> 00:05:51,700 I put that into a tool again, the same construct, the long chain construct. 103 00:05:51,740 --> 00:05:53,820 The name is send push notification. 104 00:05:53,820 --> 00:05:56,260 The function is push and that's a description. 105 00:05:56,460 --> 00:06:01,460 And now I can then call tool push invoke with me. 106 00:06:04,740 --> 00:06:05,300 There we go. 107 00:06:05,340 --> 00:06:05,700 Oh, yeah. 108 00:06:05,740 --> 00:06:06,020 Hello. 109 00:06:06,060 --> 00:06:06,340 Me. 110 00:06:06,700 --> 00:06:10,340 Uh, so now we have made, uh, a tool ourselves. 111 00:06:10,380 --> 00:06:11,540 A custom tool. 112 00:06:11,540 --> 00:06:16,980 So now we have an off the shelf tool for searching using the same API. 113 00:06:17,220 --> 00:06:22,220 And we have a custom tool for sending a push notification using the nifty pushover package. 114 00:06:22,540 --> 00:06:22,980 Okay. 115 00:06:23,020 --> 00:06:27,220 And we can put both of these tools in a list of tools. 116 00:06:27,900 --> 00:06:28,500 All right. 117 00:06:29,140 --> 00:06:30,860 Then we actually get to use it.