1 00:00:00,400 --> 00:00:01,720 So please humor me. 2 00:00:01,720 --> 00:00:05,560 I've got a couple more admin things before we get into action. 3 00:00:05,560 --> 00:00:10,640 So I wanted to talk about how I've positioned this course and whether it's right for you. 4 00:00:11,400 --> 00:00:15,720 You may be new to coding someone that's never written a line of code before. 5 00:00:16,040 --> 00:00:20,480 You might be someone that's already considers yourself an agent engineer. 6 00:00:20,920 --> 00:00:22,800 Those are the two extremes. 7 00:00:22,800 --> 00:00:24,200 Or you might be in the middle. 8 00:00:24,240 --> 00:00:29,160 You're already a Python coder or you are an AI engineer. 9 00:00:29,160 --> 00:00:34,000 Maybe you're even someone that's taken my LLM engineering course, in which case, thank you and welcome. 10 00:00:34,880 --> 00:00:42,240 But I'm here to tell you that this course is designed to appeal to everyone across that entire continuum. 11 00:00:42,240 --> 00:00:44,480 There is something here for everyone. 12 00:00:44,520 --> 00:00:47,040 The people in the yellow boxes in the middle. 13 00:00:47,080 --> 00:00:49,240 You're going to have the best time with this. 14 00:00:49,280 --> 00:00:52,920 It's most well positioned for you, that is for sure. 15 00:00:52,920 --> 00:00:54,280 That goes without saying. 16 00:00:54,600 --> 00:00:58,000 For the people that are new to coding, it's going to be challenging. 17 00:00:58,000 --> 00:01:02,830 There's no doubt you're going to have to have a lot of patience, but this course is okay. 18 00:01:02,870 --> 00:01:05,950 You'll be able to get there and build amazing things. 19 00:01:06,350 --> 00:01:10,630 For someone who's already an agent engineer that's built some agent platforms before. 20 00:01:10,630 --> 00:01:15,830 You may want to speed through some of this, but I've made sure that there's advanced material covered 21 00:01:15,830 --> 00:01:16,230 too. 22 00:01:16,270 --> 00:01:20,830 We're going to be doing some really interesting things at every point and building some great projects 23 00:01:20,830 --> 00:01:21,270 too. 24 00:01:21,590 --> 00:01:26,590 So I'm here to say, if you're new to coding, take some time with the guides that I've written. 25 00:01:26,590 --> 00:01:29,990 You'll find them in the guides folder when we install the repo. 26 00:01:30,150 --> 00:01:35,830 And I've used that as a way to build up your basic, your foundational expertise so that you can hit 27 00:01:35,830 --> 00:01:40,470 the ground running for Python coders and particularly for AI engineers. 28 00:01:40,510 --> 00:01:43,070 If you've taken the LLM engineering course, it's perfect. 29 00:01:43,270 --> 00:01:45,750 Then you're going to have a great time. 30 00:01:46,190 --> 00:01:49,150 And for agent engineer, focus on the projects. 31 00:01:49,150 --> 00:01:51,150 That's when we really put things into action. 32 00:01:51,190 --> 00:01:53,230 I'm really proud of the projects we've built. 33 00:01:53,230 --> 00:01:56,910 I think you're going to enjoy them, even if you've got some experience with this already. 34 00:01:57,830 --> 00:02:04,010 And for anyone that hasn't taken the LM engineering course, I'll be sure to put links to it in the 35 00:02:04,010 --> 00:02:05,690 course resources. 36 00:02:05,690 --> 00:02:12,130 And it's something that I really do see that as complementary, and it's not necessarily a prerequisite 37 00:02:12,130 --> 00:02:13,050 to this course. 38 00:02:13,050 --> 00:02:17,690 You can come into this course without having taken it for sure, but if you have taken it, you will 39 00:02:17,690 --> 00:02:24,130 be really well equipped for this course because it builds up a lot of depth of expertise in terms of 40 00:02:24,130 --> 00:02:29,770 what it means to work to to choose and apply LMS to solve problems. 41 00:02:30,290 --> 00:02:33,410 So in just a moment, we're going to be starting to code. 42 00:02:33,450 --> 00:02:34,570 I know you're antsy. 43 00:02:34,570 --> 00:02:35,610 I know you're waiting for this. 44 00:02:35,690 --> 00:02:37,370 Can't he stop talking and get to it? 45 00:02:37,410 --> 00:02:38,290 We will be. 46 00:02:38,410 --> 00:02:43,250 But I do want to tell you that the first thing we're going to have to do is set up your environment 47 00:02:43,250 --> 00:02:47,730 and setting up an environment, a big data science environment at the frontier of what's possible. 48 00:02:47,890 --> 00:02:50,130 It can be a bit of a painful process. 49 00:02:50,450 --> 00:02:51,450 I'm here to help. 50 00:02:51,450 --> 00:02:53,090 I'm here to make it go smoothly. 51 00:02:53,090 --> 00:02:58,320 But please do have something of a thick skin for knowing that you may hit some challenges. 52 00:02:58,320 --> 00:02:59,240 We'll figure them out. 53 00:02:59,240 --> 00:03:00,280 We'll get them fixed. 54 00:03:00,320 --> 00:03:02,920 We'll get you up and running the. 55 00:03:03,120 --> 00:03:09,080 This time, though, we're going to be helped out by a couple of really great friends in the form of 56 00:03:09,080 --> 00:03:12,640 the platform cursor, which we'll be using as our IDE. 57 00:03:12,840 --> 00:03:14,640 And I just love cursor. 58 00:03:14,680 --> 00:03:21,760 Cursor, of course, is the AI platform that's powered by Llms that allows us to be so productive, 59 00:03:22,040 --> 00:03:25,560 and it's built on VSCode and and it's just great. 60 00:03:25,720 --> 00:03:28,160 And so it's going to be a lot of fun working with that. 61 00:03:28,160 --> 00:03:34,120 But perhaps more specifically for building the environment, we're going to be using this product called 62 00:03:34,160 --> 00:03:40,120 UV, which is you can think of as something which is replacing Anaconda that I used in the LLM engineering 63 00:03:40,120 --> 00:03:40,680 course. 64 00:03:40,720 --> 00:03:44,680 And it's a sort of built on top of, of using virtual environments. 65 00:03:44,960 --> 00:03:50,080 It's really fast and it's really simple and it just works. 66 00:03:50,080 --> 00:03:52,000 I am such a fan of UV. 67 00:03:52,200 --> 00:03:58,030 It's actually a student on the LLM engineering course that that first drew my attention to it and said, 68 00:03:58,030 --> 00:03:59,350 this is what we should be using. 69 00:03:59,550 --> 00:04:01,830 And and it was too late for LM engineering. 70 00:04:01,830 --> 00:04:03,750 But it's not too late for this course. 71 00:04:03,750 --> 00:04:09,630 And it turns out that UV has become so popular that most of the agent frameworks that we'll be looking 72 00:04:09,630 --> 00:04:12,110 at already have UV at their core. 73 00:04:12,310 --> 00:04:16,190 Crew is, in a way, crew is kind of like built with UV, as you'll see. 74 00:04:16,350 --> 00:04:18,950 So UV is really easy to use. 75 00:04:18,950 --> 00:04:22,070 It is nothing like Anaconda for people that have done this before. 76 00:04:22,070 --> 00:04:26,710 And it's it's basically very, very similar to using virtual AMS and you are going to love it. 77 00:04:26,710 --> 00:04:30,470 So I know it's always annoying to have to bring in something new to the mix, but it will be worth it. 78 00:04:30,470 --> 00:04:31,510 You're going to thank me for this. 79 00:04:31,550 --> 00:04:35,710 You're gonna you're gonna love UV and it's written in rust and everyone loves things that are written 80 00:04:35,710 --> 00:04:36,390 in rust. 81 00:04:36,390 --> 00:04:37,230 So there you go. 82 00:04:37,230 --> 00:04:38,150 Get ready for that. 83 00:04:38,990 --> 00:04:43,830 There's actually one more difficult conversation that we have to have, and it's about APIs. 84 00:04:44,310 --> 00:04:51,270 So look, this course does involve making calls to frontier models like OpenAI and Deep Seek. 85 00:04:51,470 --> 00:04:53,510 And they come at a price. 86 00:04:53,510 --> 00:04:55,350 There is a price point there. 87 00:04:55,790 --> 00:04:59,980 And I want to make the point that it is completely up to you. 88 00:05:00,220 --> 00:05:01,020 You can choose. 89 00:05:01,020 --> 00:05:07,460 I use both open AI and deep seq, but you can choose to only use deep seq throughout for a much lower 90 00:05:07,460 --> 00:05:08,140 cost. 91 00:05:08,140 --> 00:05:09,740 And Gemini you can also use. 92 00:05:09,780 --> 00:05:12,060 And right now Gemini has a free tier. 93 00:05:12,060 --> 00:05:17,180 I don't know how long that will last, but so you can use Gemini for free for most of the course. 94 00:05:17,500 --> 00:05:24,460 You can also use Alama completely free just running open source models locally on your computer. 95 00:05:24,500 --> 00:05:25,540 No cost at all. 96 00:05:25,580 --> 00:05:27,460 But there are some trade offs here. 97 00:05:27,460 --> 00:05:31,220 If you want to use any kind of good model, it will take a very long time. 98 00:05:31,220 --> 00:05:37,540 If you use the quick models like llama 3.2, then it might have troubles being coherent, and you certainly 99 00:05:37,540 --> 00:05:42,740 won't get to see the kinds of results that I'll be getting when I'm using the frontier models, but 100 00:05:42,740 --> 00:05:44,220 that allows you to have a sort of balance. 101 00:05:44,220 --> 00:05:49,380 You can run things locally for free and see one set of results, and you can watch me do it with the 102 00:05:49,380 --> 00:05:50,140 frontier models. 103 00:05:50,140 --> 00:05:52,980 If you don't want to spend, the API charges yourself. 104 00:05:53,780 --> 00:05:55,380 So what are these API charges? 105 00:05:55,440 --> 00:05:57,800 Well, different countries might have different pricing. 106 00:05:57,800 --> 00:06:04,840 What I can tell you is that for me, running this entire course, I spent well under $5 on any of the 107 00:06:04,840 --> 00:06:06,680 LLM model costs. 108 00:06:06,800 --> 00:06:08,120 It's very cheap. 109 00:06:08,280 --> 00:06:13,360 OpenAI the first time you use it, you need to put down at least $5 upfront. 110 00:06:13,400 --> 00:06:15,840 And I kind of pay as you go that you spend against. 111 00:06:15,840 --> 00:06:16,560 So that's annoying. 112 00:06:16,560 --> 00:06:18,760 So you might have to do that if you haven't done it before. 113 00:06:19,080 --> 00:06:23,520 But other than that, the actual amount that we'll spend will be relatively small, a matter of a few 114 00:06:23,520 --> 00:06:24,200 dollars. 115 00:06:24,200 --> 00:06:27,760 And it's very hard to spend very much on deep sea because it's so cheap. 116 00:06:28,240 --> 00:06:35,440 Now, I will say that in the last week I have an option to use a proper real time market data provider 117 00:06:35,440 --> 00:06:37,800 that I use, and that cost me $20. 118 00:06:37,800 --> 00:06:38,880 But that's not necessary. 119 00:06:38,880 --> 00:06:43,480 There are free options as well, but if you get into it like I do then, then you might do that. 120 00:06:43,840 --> 00:06:45,760 And you know, I just want to make the point at the end. 121 00:06:45,800 --> 00:06:49,680 People do have like like people get frustrated about API costs. 122 00:06:49,720 --> 00:06:54,360 There's something about them that are a bit galling, because it feels like everyone is sort of nickel 123 00:06:54,470 --> 00:06:55,230 and diming you. 124 00:06:55,270 --> 00:06:58,390 You're getting charged a little bit here, a little bit there, another API cost. 125 00:06:58,430 --> 00:07:02,990 And I understand that even though I say these things are very cheap, a few dollars, it adds up. 126 00:07:02,990 --> 00:07:04,710 And that's not always cheap. 127 00:07:04,750 --> 00:07:09,270 And particularly with exchange rates and different economies, that might be quite a burden. 128 00:07:09,270 --> 00:07:13,830 But I do want to make the point that you have to keep in mind what's going on. 129 00:07:13,830 --> 00:07:20,470 When we run inference on these large llms, there are trillions of floating point calculations going 130 00:07:20,470 --> 00:07:20,910 on. 131 00:07:20,950 --> 00:07:23,110 This is heavy machinery. 132 00:07:23,110 --> 00:07:28,190 And so it's not like these companies are just just making extra cash off you. 133 00:07:28,590 --> 00:07:34,230 I'm sure they are quite profitable, but but most of it, the margins are relatively slim because there's 134 00:07:34,230 --> 00:07:38,550 a lot of compute costs associated with running these massive models. 135 00:07:38,550 --> 00:07:44,590 And if you think of the price of buying a new laptop or even a big like a gamer box that could actually 136 00:07:44,590 --> 00:07:48,830 run larger models itself, you'd be talking about thousands of dollars. 137 00:07:49,030 --> 00:07:55,300 So this kind of API pricing, while it can feel, as I say, a little bit galling sometimes having to 138 00:07:55,340 --> 00:07:57,220 pay each of these different APIs. 139 00:07:57,500 --> 00:08:01,420 It is worth keeping in mind the context of what's going on behind the scenes. 140 00:08:01,420 --> 00:08:03,620 These companies need to pay their electricity bills. 141 00:08:03,620 --> 00:08:08,100 There's a lot of compute, and we're getting real value from what we use. 142 00:08:08,100 --> 00:08:11,300 So I don't know if that helps or not, but it gives you some context. 143 00:08:11,340 --> 00:08:16,180 Please do keep in mind you don't need to spend anything on APIs if you don't want to. 144 00:08:17,620 --> 00:08:20,540 So there are three things for you to remember. 145 00:08:20,700 --> 00:08:26,100 The first of them is that there are resources that accompany this course, and they're really great. 146 00:08:26,220 --> 00:08:31,740 There's a website where I've put links, and I've got extra content in the form of YouTube videos that 147 00:08:31,740 --> 00:08:32,820 should should be helpful. 148 00:08:33,140 --> 00:08:38,820 There's in GitHub, there's a whole section with different guides to teach different kinds of skills 149 00:08:38,820 --> 00:08:39,700 that you might need. 150 00:08:39,740 --> 00:08:44,860 And there's some troubleshooting guides in there too that will fix problems for you and the labs. 151 00:08:44,860 --> 00:08:52,140 So the labs I'm updating them all the time, the labs you can think of them as like an ongoing a fluid 152 00:08:52,290 --> 00:08:53,010 resource. 153 00:08:53,010 --> 00:08:57,810 Every time you do a git pull to get the latest, you'll get refreshed with new content. 154 00:08:57,810 --> 00:09:03,690 Maybe not every time, but most times I'm trying to keep them to be a living, breathing resource for 155 00:09:03,690 --> 00:09:04,050 you. 156 00:09:04,850 --> 00:09:07,170 Then remember to stay patient. 157 00:09:07,490 --> 00:09:12,650 Remember that if you hit problems, if you hit roadblocks, that's actually a great learning opportunity. 158 00:09:12,650 --> 00:09:18,530 Because figuring out what's going on, figuring out how to solve this is one of the best ways to learn 159 00:09:18,530 --> 00:09:19,930 and try and go with it. 160 00:09:19,970 --> 00:09:21,970 Try and enjoy it as much as you can. 161 00:09:22,090 --> 00:09:26,090 There's some juicy projects and figuring out why they don't work first time. 162 00:09:26,090 --> 00:09:27,130 That's part of the fun. 163 00:09:27,530 --> 00:09:33,770 And then the third point is that if all else fails, or even if nothing else fails, then contact me. 164 00:09:33,770 --> 00:09:34,650 I'm here. 165 00:09:34,850 --> 00:09:35,850 I love this stuff. 166 00:09:35,850 --> 00:09:37,850 I'm actually super responsive. 167 00:09:38,090 --> 00:09:42,650 If you email me or if you LinkedIn with me, then I'll respond very quickly. 168 00:09:42,650 --> 00:09:45,690 Unless I'm in a meeting or I'm traveling or something, or I'm asleep. 169 00:09:45,970 --> 00:09:49,570 For people in different time zones, I do tend to reply really quickly. 170 00:09:49,570 --> 00:09:50,850 People are always surprised. 171 00:09:50,890 --> 00:09:53,350 In fact, a lot of people think that I'm I'm an AI agent. 172 00:09:53,350 --> 00:09:55,790 When I reply, they're like, do you have an agent of yourself? 173 00:09:55,790 --> 00:09:59,710 But no, it's the real me, I will reply, I love getting questions. 174 00:09:59,710 --> 00:10:03,590 I love answering so, so do feel free to reach out. 175 00:10:03,630 --> 00:10:04,630 Be in touch. 176 00:10:04,750 --> 00:10:08,510 I welcome ideas and thoughts and questions and whatever you got. 177 00:10:08,550 --> 00:10:14,870 And by all means, if you if you're up for it, then LinkedIn with me I some people uh, like to uh, 178 00:10:14,950 --> 00:10:18,310 don't feel comfortable doing that for some reason, but I'm very open to it. 179 00:10:18,310 --> 00:10:23,910 I love building a community of people in data science and that can support each other. 180 00:10:23,910 --> 00:10:28,350 That can if people are looking for for to hire someone or if they're looking for jobs. 181 00:10:28,390 --> 00:10:29,910 And I can help connect people. 182 00:10:29,910 --> 00:10:34,110 So it's a really great way for me to build and contribute to the community. 183 00:10:34,430 --> 00:10:35,790 And this is really important. 184 00:10:35,790 --> 00:10:41,430 But one of the things that people did from my last course is they would post projects that they've done 185 00:10:41,470 --> 00:10:46,350 and tag me on them, or things that they've done from the course, and I can then amplify it, because 186 00:10:46,350 --> 00:10:51,260 I can then jump in with some comments and, and make some observations or say how great it is, they've 187 00:10:51,260 --> 00:10:54,940 done something, and that will then be available to all the other students from the course. 188 00:10:54,940 --> 00:10:56,220 You can weigh in as well. 189 00:10:56,220 --> 00:11:00,020 And this has really happened, and it allows you to share things and amplify them. 190 00:11:00,020 --> 00:11:02,060 And LinkedIn is a great place to do that. 191 00:11:02,100 --> 00:11:07,060 And it will be something that that will be seen, perhaps by future clients of yours or perhaps by future 192 00:11:07,060 --> 00:11:08,300 employers of yours as well. 193 00:11:08,300 --> 00:11:09,500 So it's a really good thing to do. 194 00:11:09,500 --> 00:11:11,020 So I strongly encourage it. 195 00:11:11,060 --> 00:11:13,700 LinkedIn with me and share on LinkedIn. 196 00:11:13,740 --> 00:11:17,140 It's a great resource and I can't wait to see what you're doing. 197 00:11:17,500 --> 00:11:21,180 So at this point, you've put up with half an hour of me yammering away. 198 00:11:21,420 --> 00:11:23,780 Finally, it's time for action. 199 00:11:23,780 --> 00:11:25,020 We're going to the lab. 200 00:11:25,020 --> 00:11:26,780 We're going to set up your environment. 201 00:11:26,780 --> 00:11:29,140 The next video is for PC people. 202 00:11:29,140 --> 00:11:35,820 We're going to have a video for PC setup, and then the video after that is for Mac people and Linux. 203 00:11:35,820 --> 00:11:37,540 You should probably join in with the Mac people. 204 00:11:37,540 --> 00:11:39,260 It'll be similar enough for you. 205 00:11:39,380 --> 00:11:43,100 And then we will reconvene on the video after that. 206 00:11:43,100 --> 00:11:49,820 So it's going to be PC, followed by Mac, followed by us all back together again with fully built environments. 207 00:11:49,860 --> 00:11:50,700 Let's do it.