UPSERT HEADQUARTERS – THE DAY BEFORE END OF QUARTER

You’re in a boardroom at UPSERT Headquarters and your boss, William Winters, Brand Strategist at Whipple, is asking you to figure out a way to protect the company’s data from Open AI. You’ve been researching the LM Studio and think it might be the answer.

We need to keep our data safe from Open AI.
I've looked into LM Studio, and it seems like it could be the answer.
But we need to decide how to use it.
What are our options? Do you have any ideas on how we can protect our data?\

LM Studio is an open source model created by Matter that is used to run models on a local computer. Despite being a smaller model than Chatpetite, LM Studio is slower and doesn't usually follow instructions as well as GPT-4 does. However, a new model created by Mystro 7 is getting closer to the results that one would normally get from GPT-4. 

For those looking to use LM Studio, it is important to understand the technical aspects of the model as running into errors is something that is common. Despite this, the text generated by LM Studio is still decent and with some editing, can be turned into something worthwhile. 

What makes LM Studio so unique is that it was created with the intention of creating narrative and character development. This is done by having two paragraphs per section. This allows for a unique fantasy style that is not found when using other models.

Despite the capabilities of LM Studio, it is still not as good as the free version of Chatpetite. This is why many people are hoping that the model will get better, as having something that is as good as GPT-4 would be extremely beneficial to those who want to create interesting stories. 

Overall, LM Studio is a great model that is able to generate interesting stories and narratives. Despite its shortcomings, if used properly, LM Studio can create some unique stories. It is important for those using the model to understand the technical aspects as well as the capabilities of LM Studio in order to have the best experience. With some practice and patience, LM Studio can be used to generate some great stories.

LM Studio

 Okay meet. Lama this is an open source model from matter. They release it which is really great because they spend all the money training it and then just released to open source. That means I can actually run this somewhere on computer and then there are different. Sources online where you can run this, like on hugging face or replicate. But I really wanted to run it. At my own computer, I'm using something called L M studio. Which you can download is just a Mac app. And and then once you've got that, Set up, you can download anything from hugging face. 

Like this is a downloaded the Lama to chat 13 B. Model and you can prompt it just like you would  So just going to paste in my prompt. And see how it does. What I've found in general is that obviously running it on your local computer is a little bit slower. So even though this is a smaller model than chatting petite that the response has actually come out relatively slower. The other thing is that it doesn't follow the instructions usually as well as GPT four, does. Does. These models, these episodes model is getting closer to what you would get from the free version of challenging.  And in fact, there's a new model out by Mistral which the Mystro seven. The model, which is actually pretty good. And pretty close to chat cheap T levels if you're comparing it to the free version, but nobody has managed to get to the actual results that you would normally get. From GPD for. 

So while this is generating, let's familiarize ourselves with what we came up with jazzy beauty. You can see. Wrote some pretty interesting stuff here. And, we have two paragraphs per section. And it's a unique fantasy style. With actual narrative and character development. Let's see if we can get that We run into an error. Sorry. You do run into this sometimes, unfortunately running these models require some technical ability in some cases. 

But I think in general, I would say these models aren't quite there yet. They're not as good as what you get from chat, GBT, even the free version. We're all hoping that these models will get better now because it would be very cool to have. Something that's as good. 

Now you can see here that the text isn't bad, it's come up with some interesting stuff here. It has, pretty decent introduction. But again, I prefer T's version.

What is the name of the open source model used in the tutorial?

What is the name of the software used to run the model?

What is the name of the open source model from matter?

What is the difference between running the model on a local computer versus online?

What is the name of the new model released by Mistral?

We're just now getting to the point where OS models are as good as ChatGPT (the free version), except they have one major advantage: no data sharing with OpenAI!

I don't want to share my data with OpenAI

Alright, team, here's the situation. We've been tasked with making some creative decisions for our coffee shop interiors, but we don't have enough data to work with. Our boss wants us to use memetic analysis to analyze and tag images of coffee shop interiors using AI. This will help us identify patterns and trends in the industry, and inform our design decisions. So, let's roll up our sleeves and get started!

I know it's frustrating that we don't have enough data to make these decisions, but memetic analysis can really help us out here. \nBy analyzing and tagging images of coffee shop interiors, we can uncover valuable insights that will guide our design choices. \nThis process will allow us to understand the trends in the industry and make informed decisions that resonate with our target audience. \nSo, let's dive in and see what we can discover through memetic analysis!

Memetic Analysis: Uncovering Insights with AI and Vision

In today's digital age, understanding consumer preferences and market trends is crucial for businesses to stay competitive. This is especially true for industries like coffee shops, where interior design and ambiance play a significant role in attracting customers. But how can businesses gain insights into their competitors' designs and make informed decisions about their own establishments?

One innovative approach is using memetic analysis, a method that combines artificial intelligence (AI) and computer vision to analyze images and identify patterns. This technique can help businesses gain valuable insights into the typical interiors of their competitors and make data-driven decisions about their own establishments.

The first step in conducting a memetic analysis is to gather a large dataset of images from various coffee shops. Manually analyzing these images can be time-consuming and inefficient. However, with the advancements in AI and computer vision, it is now possible to automatically tag these images using machine learning algorithms.

To scrape a large number of images from Google, a Google image scraper tool can be used. This tool automates the process of collecting images based on specific keywords, such as "coffee shop interiors." Once the images are downloaded, they can be analyzed using the AI-powered Google Cloud Vision API.

The analysis begins with inductive coding, where two different images are randomly selected and compared. The images are converted into base64 encoding and sent to the API for analysis. The prompt asks the AI to compare the two coffee shops using inductive coding and identify similar and different features and design elements. The response from the API provides valuable insights into the shared and unique attributes of the two coffee shops.

The next step is deductive coding, which involves analyzing each image against a set of predefined labels. This step is more time-consuming and expensive, but it provides a comprehensive understanding of the design elements present in each coffee shop. To speed up the process, asynchronous coding can be utilized, allowing multiple API calls to be processed simultaneously.

The results of the deductive coding are stored in a dictionary, which includes the labels and corresponding coffee shop images. These labels can be customized based on the specific design elements or features that the business wants to analyze, such as natural light, wooden elements, or suspended lighting.

Once the analysis is complete, businesses can gain valuable insights into the design choices of their competitors. By comparing the frequency of different labels across the dataset, businesses can identify popular trends and common design elements. For example, if a high percentage of coffee shop images include patrons,

Memetic Analysis

  Okay. Say you're designing a coffee shop and you want to figure out what the typical interiors for your competitors. So you want to understand what type of furniture they using, whether they have plants whether there's a chalk, a chalkboard on the wall for the menu. Like this. 

And you wanted to do that analysis and see how often a certain things come up versus not. So one interesting way to do this. Is instead of manually looking through a bunch of images. You could tag them automatically with AI because aegypti vision is actually pretty good at this now. What you need is you have to scrape. Google images, which is actually the hotpot. But thankfully there is a tool that does this. 

What do you say if you just search a Google image scraper? Yeah, literally just. That's just such a Google image of scraper. And that was the Fest result here. But however you get the data. It doesn't really matter, but I'll show you how it works. I.  I just, this is in the main.py. So when you download this to your computer from get hub then you have this curd you just put in here. What are the different keywords that you want to search for? 

I downloaded a bunch and you can see. Got a bunch of, coffee shops in Beijing. Got a cough coffee shops in the room. And then also New York, I'm willing to compare them potentially. So I'm going to just run an abbreviated. Part of this analysis I would say by the way, it takes a while to down the them say I downloaded a bunch and it doesn't always work. 

So you can see, I didn't get 80 every time we got 36 and Sydney. But once you literally just run Python, main dot PI. And you should see these images. Stop appearing in hand. But that's not the part I'm going to teach you because that is someone else's code. And I'll let them teach you that in that read me. But what I'm gonna teach you is what's due when you have the data, right? 

This is a script for the Jeep T vision API. And you just need to run. These libraries here, but I have all the code written here. I had to pull in. What are the different coffee shops, right? As you can see how many photos you got just looking at the first five here. See, I've got 4,500 just from New York. 

Got a bunch of Sydney. Et cetera. So. What I'm going to do is I'm just going to.  Just limit just to Let me just a little bit to Sydney.  

Just for testing because a visionary pair is expensive. If you're running a bunch of times, it also takes a little bit of time. So I'm just gonna run it on these 33 images and in Sydney.  All right. And there's two pastas. One is inductive coding. And then the second is deductive coding. 

Inductive coding is when you're looking at these and you look from, for patents and you're comparing the Migo. Okay. That one has a coffee. You know that one has a chalkboard for the menu. And then there's other ones that have chalkboard for many use as well. So maybe that's something that I want to hear again, is another chalkboard. 

So I've noticed that pattern. And now that I know there's a pattern. I want to find that everywhere. So there's another truck board. There's another chalkboards. So that's deductive coding, inductive coding is coming up with the patterns, comparing and contrasting to find what's different or what's similar. And then deductive coding is then going and finding those patents everywhere else. So we're going to do those two things here with a GP vision. All right. 

The first thing we're doing is inductive coding, and we need to be able to send an image to opening eyes. So the way that you send an image is with the base 64 encoding. This literally just takes an image and then turns it into some texts. And that you consent along with your API call.  And this could does, is it just looks in the folder and then it just chooses two images at random. From the different folders that we have. 

So we just have the one folder right now, but if we have multiple folders that. It would look in all of them. Oh, I did mention, I forgot to mention one thing when using Google images scraper you'll probably need to download. I had to download this Mac. 64 Chrome crim for testing. 

When it scraping these images you need that in that. Here I've just put us in folder called WebDriver and then it opens that up. That's, I've just mentioned that because I ran into an error. All right. So back to the inductive coding. So choosing an image pairs, choosing two different images at random. And then it's comparing them. So it's getting the base 64 string, and then it's using this prompt here compared these two coffee shops using inductive coding. What features attributes, elements of design are similar, different. 

And then I'm asking for a structured response here. That's just how you pass it into GPC vision, by the way. You just. To client chat completions. And then you pass the prompt. But then you also pass in the two images as well in the same content string. And I'm just using the user prom tear, but you could also have a system prompt at the top. Cool. 

So let me just run this, see what we got. So it's selected to these images at random. Number 30. 25 and number 31.  And you can see, it takes a little bit of time for the image response is this is opening eyes, biggest modal. Here we go. So now we've got some labels the there's some things that they share. 

So coffee shop a and B. Both have modern designs. They both have wooden elements. But only cough shot B has natural light. And own the coffee shop a has a spacious interior. So that's really interesting. Now we have some labels. We have a dictionary of labels. We can run that and then save it. So if we look at. We should have hit some clean levels so you can see. 

Yeah, there's a bunch of labels here. For these different things and it's rewritten them. We've got the actual kind of folder that they're in the label. And then the phone name.  Cool. So now you have your level dictionary and that's useful in itself because you could run that multiple times across multiple images. 

So we just compared to those images, you could compare every single image against each other. It just takes a little bit of time. That you can run again as well and get a bigger dictionary of data. Now it comes to the deductive coding. And this is the one that's more time consuming, more expensive. 

The way, the reason why I've set this up as asynchronous is. Because otherwise it takes a very long time to run because you're going through every single image and saying and every single label and going, is this label in this image, does this coffee shop have wooden elements? Does this coffee shop? 

How bought-in elements. Does this coffee shop have wooden elements, right? And then you go through all the other labels about, does this coffee shop have suspended lighting and does this coffee shop have a seating areas? There are different tricks for doing this faster or slower. But for me, I found if I do an asynchronous. It means I can get all the labels at once for a single image. And they all run quite quickly. So I runs a little faster. So again, this is here, we're just passing one image in and we're just passing the user prompt, which is much simpler. 

If the label applies to this image, reten one, otherwise reten zero on the output one, a Sierra.  All right. If we get a one, then we are going to return the label. And if we don't, then we're not going to attend on. So this. This does this, the asynchronous code would just set up a bunch of tasks. 

So we run it for every image and then we wait until after all the tasks had done for that image. It's processing all the labels at the same time. And open AI can handle multiple API calls at the same time. What will happen is instead of waiting for each one to come back, it's going to process all of them said time. 

We're going to get through asset. If we're doing 10 labels, we'll get through all 10 at the same time, rather than waiting. If one takes a minute. We're not waiting 10 minutes. We're getting all of them in one minute. So that's the benefit of asynchronous. Cool. And then we're just going to return the labels. 

If the. If the label wasn't there.  Great. And then actually running the deductive code and we just pull open the cleaned labels, Jason, that we have before. And then we have the clean labels. Which which loads to Jason from that dictionary we had, and then it finds the values. 

I've also limited it to just five labels per coffee shop. Otherwise, it's going to take a bit of time.  Cool. All right. So let me just run this. And the processing coffee shop Sydney, you can see that all three of those came back to this in time. But some of them are taking a little bit longer. But we're not waiting for one to finish it before we got the other. 

Cool. So here we go. So now we're processing coffee, shop Sydney.  

And let's see how quickly they come back. Yeah, this is Sydney 30. Okay. Now we're processing Sydney 10. Getting hanging light fixtures. So this is only coming back. As positive if it does have that label, if that makes sense.  

Cool. That's how. Movantik analysis works with vision it's really powerful. Once you figure that you can apply this to pretty much anything. Like any time you have a lot of images, like maybe in your ads or on your website. You can do some analysis to figure out what labels are up. And you can define the labels as well. 

You could sell it. What sorts of things you're looking for. You could give it a D list of things. However you want to do it, that's fine too. You can just add new stuff to this. This clean labels thing, right? You could just add in some new.  New ideas, right? 

Like I want to. I wanna find, this is customers queuing, right? I want to find out if there's a barista that has a tattoo, right? Like you could just add that as another option, copy. This one has Tattooed.  

Barista.  

All right. And there's already funding. If the barista is present in this bit, then we're going to see if they have tattoos, visible tattoos, cool. That's how this works. And then what you're going to get back is you're going to get some, a file name like this. This is just a big list of all the different labels, right? 

So it says coffee shop, New York 42 has the label of street view. This one has the label patrons present, right? And then you can do some analysis after this. To basically figure out okay. How many time, how many does it, how many labels does this apply to you? 

So how many of the coffee shops has this label? I'll give you an example. I'll show you an example here, cause that's still processing. Cause it's going through 33, images is an example from New York. Then I ran earlier, so you can get a list of all the labels into a data frame. This is like an Excel spreadsheet. And then you can print out what percentage of the total images have these different labels? 

So here we're finding that 41% of the patrons that 40% of the coffee shop images, show patrons present. So to me you want to really pay attention to the ones that are on almost everything. Because that's almost like a rule of the game. If you don't have patrons present in your coffee shop image, that's probably really bad. And you definitely want to at least have a stance on that. 

Like maybe have a good reason for not having patrons present in the image of your coffee shop. When you're uploading that image to Google my business. But you should at least address that have the strategic choice here. Similarly, for things that are not very popular you also might want to think about these as a differentiator. 

So exposed brick interior, you could argue that, that's not very fashionable anymore, and that's why only 10% of people had it. Or you could say, this is going to be fashionable. I can see that this is a trend as, or I'm going to stop using this right. That's how. You do this type of analysis. 

Obviously what it doesn't tell you is like which choices to make and what designs to have. But if you're not a designer like me and you want to be a little bit more data to make your decision, this can help inform your decision to give you a map of. What is what are the different creative decisions you need to make? 

When you're doing something designed or visual. All right. Hopefully that's useful. This is my little hack for, being a data guy, but also playing in the world of branding. Hopefully you find it useful too.

What is one potential benefit of using AI to tag images in a coffee shop analysis?

What is the difference between inductive coding and deductive coding in the context of analyzing coffee shop interiors?

What is the purpose of using AI to tag images in the coffee shop analysis?

What is inductive coding in the coffee shop analysis?

How can the coffee shop analysis help inform design decisions?

There are millions of decisions you need to make when starting a business that are too small to test, but are too risky to make without data.

How can I make creative decisions when I don't have enough data

Ultra’s Offices – Quarterly Strategy Meeting

The hot topic being discussed is SEO: your blog content is good quality but not yet ranking on search engines. How do you build authority and start ranking on the first page of Google?

I think the quality of our blog content is great
But right now nobody is seeing it
Of course we all know SEO takes time
However if we don’t show tangible progress soon we won’t be able to justify the level of investment we’re at right now
The key issue has to be links
In my last company none of our content ranked until we got over 2,000 backlinks from a post that went viral
The rising tide lifts all boats…
We went from 200 to 20,000 visits a week
Of course we can’t expect to just go viral here with our skincare brand, that’s a bad strategy
But we can start building links
Let’s start with identifying broken links on competitor’s sites and redirecting them to us
Should be an easy place to start

In order to rank on Google you need authority. Google’s PageRank algorithm is somewhat of a popularity contest: if websites who have a lot of authority link to your website, they bestow authority on you, and your ranking increases. Of course the links still have to be relevant to the content that you produce. They also have to be legitimate: if our link profile looks unnatural like we’re buying links we can get penalized and de-indexed.
So we need to build authority in a legitimate way, ideally without spamming a bunch of people, or taking up a lot of time with websites that aren’t relevant. The cleanest, simplest and most useful way to do this, is to identify broken links to competitor websites. This occurs when other websites have linked to your competitor but the link is no longer working, it’s leading to a 404 page. This is an opportunity to contact the author and let them know, in the hopes that they’ll reciprocate and link to you as well, perhaps even replacing your competitor’s link with a link to your product instead.

Broken Links

Hey, let's do some broken link building. Uh, so we're going to use <inaudible>, uh, for this analysis. Uh, you can really do this in most of the SEO tools and potentially even, um, you know, use social operators to do this in Google.
Uh, but, um, I'm just going to show you a trust, cause that's what I use. Uh, I think you can pay $10 or something for a trial and, and do kind of the analysis that you need and then cancel.
Uh, so, uh, we are doing this for a skincare brand called ultra start-up and they compete with, uh, this competitive set here.
Uh, so, uh, they've done some surveys of the potential customers and they're finding that a lot of people use, uh, Harry's skincare, um, uh, solutions or they use, uh, Jack Black, which is the market leader in the U S um, and then they also use melamine guts, uh, because this is a very trendy skincare, which say usually encounter when they travel, uh, to different hotels.
Um, so, uh, we're going to go through these and figure out, uh, whether they have broken links, uh, because anyone that's looking to them, uh, could potentially be looking to us as well, especially if we notify them that one of their links is broken.
Cool. So, um, let's go to Harry's. Um, this is for the U S market. So you're going to copy your out, um, wherein within <inaudible> in the site Explorer, just going to put that in there and then hit enter.
Uh, so this is basically bringing up all the data on Harry's. You can see that they have a very high, um, you know, relevance in terms of, uh, domain, like they have very high authority.
Um, but, uh, the main thing we want to go to here and nature estimates is pretty simple to get to best by links.
Um, this is one of the best, uh, pages you could look at. It kind of shows you what pages have the most backlinks to them.
Uh, but, uh, the important thing for this link-building strategy is we can filter by HTTP code here. So we can basically say, um, four for not found.
Uh, and that's going to tell us all the different pages within Harry's that have a lot of links that, uh, haven't been, uh, found.
Um, so, um, we can, uh, you know, potentially search within the results of we're looking for something specific. We can export it into Excel and do some filtering.
Uh, but, um, I just like to kind of rank it based on, um, the Euro rating, cause it's a good proxy for like the most important URLs.
And then I just scroll down until, uh, there's not that many links coming through. So, uh, here they have a, you know, the social mission, which I guess say, give up on, uh, it's not found on the website anymore, our story.
So some of these are like, uh, mistakes. You can see, this is like the France page. It's got France, France.
Uh, so maybe there's some errors and that's why that's for a forum. Uh, but here's something interesting. Uh, they did a post for, um, I guess for, uh, pride week.
Um, and I, it's not showing up on the website anymore. So if we go to the way back machine, internet archive, this is sometimes a store, uh, different pages on the internet.
So maybe we get lucky and kind of see it hit. Okay. So it looks okay how one record and, uh, we can sometimes see what the website is.
So although it doesn't always load all of the, uh, all the images, uh, so let's just see what this page was just going to wait for that to load.
Hmm. It's taken awhile. Uh, it doesn't look like this living anything. Okay. Well, we can get kind of guessed what it is shave with pride set.
Um, we can see if there's another page on the left side That talks about this. Here you go. So they do have like a shave with pride set.
Now this is specific product, but I guess this was a blood post about this product and it's a pretty visually appealing one looks pretty cool.
Uh, so, um, so now we have an opportunity, I think because, um, we have here, um, there's 40 referring domains, uh, to this page that are going to a broken link.
So that's a user experience issue for the people who read about this. Um, there's also, uh, you know, from those 40 demands is 62 different links.
Um, so I like to kind of click through here and just see what they are and what you're seeing here.
Um, this is the referring page, the article that referred to them. Um, and then this is the anchor texts, like the texts that was highlighted and the URL, which is the shared with pride set.
So, um, we can see that this is about awesome packaging designs. That's kind of interesting. Um, this is the corporatization of pride month.
Maybe we don't know the year in here. Uh, that's kind of a negative article, um, you know, but like we would want to appear in packaging design reviews.
That's pretty cool, especially if we have a good package, uh, in terms of, uh, the, um, you know, the, the, uh, uh, the, the skincare products that we, that we created.
Um, there's also here 15 awesome limited edition product collaborations. Um, and then, uh, some article hit. Um, so there's some opportunities here we can go through.
Um, and, um, you know, we can contact these people. So if we click through to here and see the article, um, we can see, you know, we search the page for Harry's.
Um, we can see what they're read about. Um, and it looks like they're kind of listing different ones. So we have Harry's who gives us scrap.
So, um, this might be the sort of article that we want to get included into. And, um, if we, um, if we have a package that, um, in this case, uh, you know, fits the bill, we can contact the author of this post.
And so this is massly, um, Alrighty. And, um, you can usually click through and kind of, you know, find that Twitter or, um, you know, the, your, uh, their email.
Um, so, you know, you can just search for, uh, dialogue. Um, so that's like a little bit more about, uh, this is her personal website.
Uh, so she's on my crack as a PR kind of, uh, platform. So, um, yeah, ZoomInfo has a contact details.
It looks like. Uh, so, uh, yeah, that's, um, that's interesting, right? That's how you kind of go through, um, and then you can contact her and say, Hey, I noticed that, uh, the page you're linking to, um, isn't, isn't working anymore.
Uh, but, um, you know, I think actually, you know, we, we have a new package, uh, that you might want to check out that we might want to include.
Um, let me know if you want me to send you, um, you know, some of the products for free, just so you can check it out and, uh, you know, give, give it to a friend and see what they think, because it's a men's product in this case.
Uh, so, um, you know, that's a really good way to build that relationship, even if they don't link to you directly here, I, they might, you know, tweet about you or, um, you know, they might, uh, include you in a different article that they're working on.
Um, and, and you can't predict any of this. You also can't like specifically ask them, like, uh, pay them to do this, uh, because that goes against Google's guidelines.
Um, you know, but, uh, I think, you know, this is an opportunity to find someone who is looking to a competitor that is running about the space, um, that, um, you know, potentially will be influential and willing to, uh, to link through to you, uh, in the article or in a few trout skills.
So that's really what we're trying to find. Okay. So that's, that's one opportunity, uh, let's move on from Harris and see if we have anything for Jack Black.
This is the school, this is the leader here. So this is telling those that total, um, backlinks is good to hear best buy links again, um, and then filter it down to four, four.
Okay. So no, uh, for a force for their websites. So this is pretty good for them, uh, bad for us.
I mean, so they, uh, you know, whoever is managing our website, uh, you know, it hasn't made some of these messy changes.
Um, so they haven't taken off any of the pages in their site. So that's good. I would also look internal.
Um, it looks like none of the internal links are for, for either. Um, so that's, that's a, you know, that that's going to happen like, uh, relatively frequently.
Um, there, isn't always an opportunity to kind of have to search for the next one we're going to look at is not an, a goats.
Uh, this is the really trendy one, and we're on best by links here. So let's filter it down for, for, for, and here we go.
There's a lot of two TCS, so they have this face, grapefruit face cleaner. Um, so, uh, that has, uh, some, uh, it looks like they've changed some of these, uh, the URL structures here.
So, um, you know, him, men's journal fashionista.com, Jacob, Jacob, and Sebastian. Um, so it looks like there's a lot of these companies that have, um, you know, looking through to this and to hear that you're washing your face or wrong, et cetera.
Now in here we go. So they just have a few links to the bottom, so we can go to them and say, Hey, by the way, that link is broken and also, you know, did you want to look at our product, um, and, and see, see if you like it, if we have a face cleanser and then, um, and then maybe they'll add us as the fourth one here.
Uh, so I think that's, uh, that's like pretty straightforward. This is like ideal. This is exactly what we wanted. This is a lot less complicated than the, uh, than the pride week, uh, opportunity.
Um, the, uh, the other thing I think is useful to do is just see if they actually have that product elsewhere on the site.
Maybe they just change the URL, I guess. So they do, um, this is, this is useful to know just because, um, if they, if that product still exists, uh, then it's, um, I think like good practice to give them the updated link, uh, to the, uh, you know, remember, like you're not trying to do this at scale you're, should we get good quality links from influential people and build that relationship?
Um, so if you think about it that way, it's worth the extra effort to say, Hey, here's the correct link for that grapefruit face cleaner, because he now doesn't have face in the Euro, whereas before it did have face, um, and now it has the different fluid ounces in hairs off.
So, uh, that's, that's very useful. Um, I think that the, um, if, if the, this product doesn't exist, uh, then that's an opportunity for you to change the messaging and say, Hey, they didn't actually sell that anymore, but we think we have a good replacement.
So think about that. Uh, it's, it's, you know, trying to spot these opportunities. Um, but it's not really about scale.
It's more about quality. We're trying to find, um, you know, relationships with people who are LinkedIn to similar content and therefore, um, you know, this is just an opportunity to reach out.
Um, it's not like the end of the relationship. Um, so try and invest as much as you can into each one.


What part of Ahrefs do you need to go to in order to find broken links from a competitor?

What are the benefits of broken link building?

How would you pitch a broken link backlink opportunity?

How do we build authority

The difference between a website that gets 200 visits a month and 20,000 is backlinks. It’s night and day: if you don’t have authority on a relevant topic, Google won’t rank you anywhere near the first page.

GoolyBib Offices – Product Growth Standup Meeting

The CEO is at the product growth standup meeting. He's discussing the challenges of generating a long-tail keyword list for the company's programmatic SEO program. His latest obsession is AI.

We need to find a way to generate a long-tail keyword list for our programmatic SEO program, and I thought… why not get ChatGPT to do it?
My daughter showed me it in the elevator on the way up and it’s remarkable
Is anyone here using it? Do you think it can give us a good starting point for the baby recipe content site we’re building?
Look into it and find out for me

Programmatic SEO is a completely different approach to traditional content writing. Instead of hand-picking a few keywords with decent volume and low difficulty, you’re looking for an entire category of long tail keywords that will add up to something.

The key to successful programmatic SEO is to find the keywords that don’t show up in the keyword tools. This requires a deep understanding of search intent, user behavior, and how people talk about the topic at hand.

The best way to start is to look at the top 10 search results for a given topic. These are the pages that are currently ranking in the search engine results pages (SERPs). Take a look at the content and note the common words and phrases used.

Next, use a keyword tool to find related keywords and phrases. Look for keywords that have decent search volume but aren’t overly competitive. These are usually the long tail keywords that you’re looking for. You want to look for niche keywords, which are highly specific searches that are often overlooked, but they must be part of a wider pattern. 

For example you might not rank on “cheap flights” (head term) or “cheap flights to barcelona” (mid term), but there’s likely to be less competition and volume for “cheap flights to BCA”. More importantly, there’s a long list of airport codes, so having a page for every code can add up to a lot of search traffic. The category must be something people who buy your product would be interested in, otherwise the traffic won’t be worth anything.

Typically when you have a category that fits well, you then want to take that to an AI tool like ChatGPT to build out a larger list. ChatGPT can be prompted to add additional context from its training data and output it in table format, leaving you something you can easily parse into a spreadsheet.

Once you’ve gathered your long tail keywords, you can begin to create content around them. Create content that answers user questions and provides useful information. Be sure to use your target keywords throughout the content when generating the post.

Programmatic SEO involves a lot of research and analysis, but it’s worth the effort. By finding the right keywords and creating content around them, you can improve your search engine rankings and drive more organic traffic to your website.

Programmatic SEO

00:01 Hey let's walk through how to create your long tail keyword list when you're doing programmatic seo. So I'm using chat g p t for this by OpenAI.
00:13 You could also use G P T three you know, the powers chat g p t in the background as well.
00:19 So I'll, I'll show you that in a second. But my starting point here is usually chat, G P T. And the reason why I use this to start with is you could use keyword tools like ats.
00:33 I found in general that they don't have very good keyword coverage on like long tail keywords. So, you know, for example, I once built a, you know, website that listed all the different recruiters in tech.
00:48 And when I did keyword research I found that basically there was nobody you know, no traffic for these keywords.  But it's just because ats can't crawl the entire web.
00:58 The, the sample size isn't massive, right? Of, of people browsing the web, so they don't always get like the full picture.
01:07 And also I think in general anything that has a lot of traffic on one of those keyword tools is gonna be looked at so many times by competitors or, you know, other people are trying to own the space.
01:18 So you know, almost by definition, if it appears in there, then it's gonna be saturated pretty quickly. So what I try and do is come up with keyword ideas based on my own intuition, my experience, and, and also talking to customers to see what they search for.
01:34 So, you know, re reason we did the recruiter thing is we found that a lot of the people we talked to in tech said that they would google the name of a recruiter to check if they're legit before they you know, before they responded to them on LinkedIn.
01:50 So you know, we created a website by scraping LinkedIn found you know, all the recruiters names associated with the different companies they worked for and then also gave kind of a simple rating system.
02:02 So that's, that's one example. In the example today, we're gonna try and do this with baby food like recipes. So you know, I, I think like Chak now is where I start to generate ideas usually.
02:18 You know, rather than kind of using that to write the finished product, I think it's really good for ideation and kind of quickly checking whether something has interesting stuff.
02:27 Cool. So I'm just gonna say, you know, list you know recipes list of dishes that you can cook for. So this, this product is a baby bib.
02:47 And therefore they want to, you know, rank on terms that are related to babies. So there's certain things that their customers would be searching for but not directly commercial necessarily, right?
02:57 So your traditional SEO strategy, you would maybe write a blog post or, you know, write some content specifically targeted to specific keywords.
03:07 This isn't really what we're covering here. What we want to do today is like, you know, have a category of keywords, something that's like very, very you know broad in terms of like, it's, there's gonna be lots and lots of keywords in that category but the each individual keyword won't get that much traffic.
03:26 So it's called the long tail. And this is a good example that I came up with. So, you know, there's a list of different dishes that you can cook for babies.
03:38 We do have to be a little bit careful here because, you know, AI is not always correct and it warns you that of that you know, says you know, the babies shouldn't have specific foods.
03:53 You know, some of the recipes that we come up with might not actually be edible <laugh>, right? So we'd have to try to check that.
03:59 But I think it's very good for ideation as long as you have like a human checking it afterwards. Cool. So we have, we have a list of dishes here.
04:08 So are period fruits, period vegetables, pure meats, period legumes. So that's pretty cool. So it looks like there are certain dishes that we could potentially you know, do for babies.
04:22 I mean, I can bring up interest here and then just kind of show you what traffic those keywords get. So just piece that in here and search United States.
04:36 Okay, so these are the, the core keywords, like Turkey, you'll get <inaudible>. So it looks like some of these keywords have a lot of search traffic.
04:45 But it's saying yeah, here we go. So like, period meses. Yeah, so, you know basically like there's not that much.
04:59 Here we go. I think it's past it out a little bit funny. So let's just see, make sure this is correct.
05:19 Rentals. Yeah. So, yeah, it's still kind of keywords that they couldn't find. Here we go. So here's a good example, like oatmeal or rice cereal, like that keyword specifically doesn't have a lot of traffic but maybe ind individually it would.
05:35 So anyway, I mean, you can go this, this path, but I think that these tools are very good for finding like, which head terms Turkey for example has a lot of traffic, but if I say you know, Turkey recipe that's gonna have a, a decent volume for babies, like almost it says no traffic, right?
05:59 So this is kind of what I was saying. So here's our list. If we have like a basic list you know, but like, that's not all we need, right?
06:08 Like, we need a lot of other information if we're gonna create a programmatic SEO page, we can't just like have the word y'all get, right?
06:18 So what, how do you get kind of structured information out of out of open ai? So you know, what you can say is like if you said, you know, that you present this in a table with you know, the dish Difficulty and,   The ingredients, The dish,  Then it'll probably tend no, oh, no, sometimes it does, Sometimes It does say yes.
07:00 Okay. Yeah. So if you, if it does say no to you then one of the things you can do is like ask it to format the table in a specific way.
07:14 So like, you know, usually say like Create A list in the following format.  And it'd be like a Dishy ingredients.
07:32 And then you can also,  Like an example input, and there'd be Like period roots, it's, And then example, Output fruit Difficulty, Ingredients,  Ingredients would be apples, vanilla And Difficulty would be easy.
08:08 So you could kind of format it in that way. You know, that's that's like a pretty straightforward you know, that's like a pretty straightforward way to get structured data out.
08:21 In this case, it's actually given me you know, some good structured data in the table. You know, when we copy this and paste it, it's gonna be, it's gonna work out okay into Excel.
08:33 But just to kind of show you, I'm just gonna add like another thing on here. So these are all easy dishes.
08:42 Like maybe maybe we could also have like, time to cook and then and then have like a recipe. And then let's have like a health rating.
09:09 Cool. So, so we've got dish, and then we've got difficulty health rating. So let's had a health rating, so pure fruit to be five.
09:24 And then let me see ingredients. And then time to cook, say five minutes. Then recipe would be pause One, Pause pair, and, and that back slash n is like a new line.
09:56 And then we're gonna say two and four, five minutes. Cool. Let's make this five outta five, just so it knows that, like that's the healthiest.
10:12 Or you could also say like, very healthy, whatever. So let's see what it says. Sometimes if it, if it's wrong, then you know, you just want to stop it and then read it.
10:38 So maybe let's say let's create table in the format. Here we go. That's working. There we go. It's kind of working great.
11:15 Nice. Okay. All right. So now we've got a structure and we say like use the same structure but list 10, 10 dishes.
11:39 Perfect. So it is the good thing about chat GT is that you don't have to keep repeating the instructions. It understands what happened in the last, you know, few bits of the conversation which is cool.
11:54 So what we're gonna get out of this now is kind of basically a spreadsheet of the different data we're going to use you know, for these you know, for these recipes, right?
12:04 So like when we go to build our website you know, and, and write blog posts about these, et cetera then we'll have like a list to work from.
12:14 And you could just inject the recipe directly into the page. You could also use GPC three to then, you know, kind insert this data.
12:23 Just gonna stop generating.  Here we go. Cool. Hmm. I guess I'm having some issues. <laugh>.  Just few, five Takes a little bit of coaxing.
12:58 Here we go Now since you were working. Cool. So this is a great way to get structured data out of chat, G p T three.
13:19 And you know, once we have this you know, in this format, then we can kind of put it in Excel and, and use that you know, for our SEO site.
13:29 So these would be different fields in our cms you know, and then we would get a writer to, you know, write up more information to include.
13:40 So so that, that'd be really helpful to, to begin with. And it kind of gives us a good kind of list that A we know that, you know, the AI is aware of, and, and b is something that's obviously popular on the web, if the AI is aware of it.
13:54 And then three you know, it's kind of a quick and easy way to get this structured data. So we might remove some of these if we don't think they're very good.
14:02 We might add more whatever as we need to. The other thing we can do here is just kind of be targeted.
14:08 So we say like, these are all easy and healthy, Easy And healthy And you provide options. So sometimes issues, all right, so this is a good opportunity for us to kind of copy here and then just gonna, you know, create a new spreadsheet and then a, so I did a command or control shift v you know, command shift fee if you're on a Mac control shift fee if you're under pc.
14:52 Cool. So we have we have these now and chat gpt is running into some issues. Hopefully you aren't running into the same things but just to kind of show you that you can do the same thing.
15:04 Hopefully GT three isn't down <laugh> but let's see. Okay. All right. So we're gonna go into the playground here. And this is using the same kind of engine in the background.
15:19 What we're gonna do is we're gonna dial up the tokens to 2048 and then we're gonna say here we go.
15:36 Okay. So create a table in the following format. So I like a table of food of dishes for babies In A table in the flowing format.
16:02 Cool. So that is all you need to do. It's the same sort of thing as you know, chat gt. Oh, okay.
16:17 So it's continued here. So what we can do, there's two different things here. So one is so this is a little bit dumber in terms of the user interface.
16:41 So sometimes we need to kind of present a list first. Actually let's get from our spreadsheet. Let's get a list first.
16:51 And then we can say input, and then we're just gonna submit, and then here we go. So now it's, you know, giving us the output for this input, which is great.
17:09 So this is, you can see this is a types a lot faster than chat gt, so it can be a little bit better if you're doing a lot.
17:16 But then now we have this, we can kind of just build on it and then say, okay, gimme some more input, right?
17:25 So I'm gonna say stop token. Sometimes it gets confused and stops. So we're gonna but these hashes at the end, and then we're gonna tell it stop when you just get to this, because sometimes it just stops when it thinks it's finished the sentence.
17:49 And that isn't exactly like what you want <laugh>, right? Like we saw here, we were hitting it and it wasn't generating more ideas, right?
17:59 Here we go, Yogurt. Okay, so it doesn't work. List. I dunno, 10 more. Here we go. I got it. So this is the, the work with prompt engineering.
18:25 You know, it's sometimes takes a little bit of coaxing. I'm sure if you're watching this in the mid to late future <laugh>, this will be a lot easier to do and it'll kind of understand.
18:37 But you know, this is really like a mental model. You need to think of that, you know, you're just, just like working with a human.
18:44 You're trying to give it input in a way that it understands. Give it examples and then let it rip, right?
18:49 So here we've got, you know, another 10 here. Like we can just say, okay, you do 10 more, right? We can just kind of keep going.
19:03 Let's use our stop sequence and then it's gonna keep going. Hopefully,  Let's try. There we go. Yeah. So you do have to play around with it all a bit once you ha you know, have something that works, you can save it as a preset.
19:31 We also view the code and use that as a as a way to like you know, run this as an API call.
19:40 So if you wanted to kind of turn this into like some, you know, something that you can call externally from your code and, and kind of work into your product, then you can do that.
19:49 But yeah. Now we have a really good list here of oh, sorry. If I formatting, I have a really good list.
19:59 Oh yeah, here we go. So this is one last thing to show you. Sometimes the formatting doesn't work out great.
20:06 So in which case you're gonna go to data and then wanna split text to columns.  And rather than detect automatically now, let's just put the pipe in there.
20:18 Here we go. Cool. So now that, now that knows you know how to split those out Beth, why you want to do things as structured data, right?
20:29 Because then it's easier to pass and turn it into something like this. So by telling it to you know, split by the pipe, then the pipe isn't really ever used in normal text.
20:43 So you know, that's really gonna help you. You know, you're not gonna have any issues you know, with this sort of thing you know, like splitting it into different data.
20:55 So that's how, that's how that works. You know, you can pass this now to your writing team and say like, here are the different recipes I want you to write for, you know, dishes.
21:06 And, you know, then potentially have someone who knows how to cook you know, or a health expert, nutrition expert. Just review like the, the ingredients and recipes are correct because AI can sometimes hallucinate and, you know, put the wrong things together.
21:20 Cool. Hopefully that, that works. And that's kind of taught you a little bit how to work with AI in order to generate, you know, large sheets of data cuz you know, you can keep going with this and, you know, do a hundred or 200.
21:31 Alright, hopefully that was.

What type of keywords are beneficial to use when creating a programmatic SEO page?

What is one trick to get structured data from OpenAI when it doesn’t want to give you a table?

What is the main reason for using Chat GPT to generate keyword ideas?

What is an example of a keyword that might not have much search traffic individually, but in aggregate the category should give good volume?

What is an example of a dish that can be cooked for babies that wasn’t in our list?

Name one of the advantages of using chat GPT 3 to generate structured data.

Most people don’t realize programmatic SEO is a completely different game to traditional content writing. You don’t hand-select keywords with decent volume and low difficulty: you have to find a whole category of long tail keywords that will add up to something.

Generating a long-tail keyword list

MARKETING WING - CAMPAIGN PLANNING SESSION

Sally, our Head of Marketing, wants us to dive deep into analyzing landing pages and competitor landing pages using this powerful tool.

I'm really excited for today's session, everyone. 
Landing page analysis is such an important skill for us to have, especially as we're constantly striving to improve our campaigns and stay ahead of the competition. 
With GPT-V, we'll be able to analyze landing pages with precision and efficiency. 
Trust me, this skill is going to make a huge difference in our marketing efforts. 
Let's dive in and become landing page analysis experts!

Landing pages are crucial for any website as they play a significant role in attracting and converting visitors into customers. Analyzing landing pages, both your own and your competitors', is essential to gain insights into what is working and what can be improved. In this blog post, we will explore how you can analyze landing pages using GPT vision.

The first step is to set up the script by specifying the domain you want to analyze. This will be used as the base domain for comparison. The script uses functions to load a headless browser, create a page, and take screenshots. It also includes options to emulate different device types like mobile and desktop, ensuring a comprehensive analysis.

After taking screenshots of the landing pages, we convert them to base64 format for further processing. We then set up a LangChain pydantic model to receive responses from the GPT vision API. The vision model provides feedback on strengths, areas for improvement, and general recommendations for each landing page. This standardized output allows for easy integration into applications.

To demonstrate the analysis process, we provide a prompt to the model, acting as a marketing user researcher. The prompt includes the URLs of the landing pages and asks for a brief analysis of the screenshots, focusing on areas for improvement. The model generates a JSON schema following a specific format, providing valuable insights for optimization.

While the current script provides a solid foundation for landing page analysis, there are some edge cases and future improvements worth considering. One such case is handling cookie banners and pop-ups. Automating the process of clicking on these elements would enhance the analysis by accounting for their impact on user experience. Another improvement involves creating an X, Y coordinate grid to have complete control over the vision model's actions, allowing for greater autonomy and interaction with the website.

In conclusion, analyzing landing pages, including your own and those of your competitors, is crucial for optimizing user experience and conversion rates. The combination of GPT vision, and LangChain provides a powerful toolkit for conducting in-depth analysis. By leveraging these tools and considering potential edge cases, you can gain valuable insights into your landing pages and make informed decisions to enhance their performance.

Landing Page Analysis

 All right. So in this video, what we're going to have a look at is how you can analyze landing pages, your landing page, and competitors, landing pages, using GPC vision. We're going to use something called Piper tear, which is a puppeteer port for  And this allows us to run puppets here, browsers. , and to execute some commands on some headless browsers. , so there's a couple of different types of installations that were running in this Piper tear, stealth Piper tear. , and we're also going to using Lang chain as well. , we're also going to add in some use agents. 

Now use agents are a way for us to potentially spoof. To other websites and pretend that we're actually a real browser. , and then what you're going to need to do is when you run this script, make sure that you put your domain. In here, because this is what's going to be. Inside of the prompt later on. 

So I'm going to be using the home page. , for, for analysis, but the homepage of my website is still under this specific domain. Now once you've changed that domain. We have this function here, which is called a screenshot full page. And what it does is it loads a headless browser. It creates a page. 

And then if the, that the device type is mobile, it emulates a different view. Por. And, , sets the user agent for the mobile user agent and some other little bits, but if it's a desktop, , that's entered into this, , specific type of function. , as a parameter, then we set the viewport to be slightly larger. 

And we also, , , emulate , the viewport should be that size and also updating the user agent here.  And then we've also got a function which is meant to improve the stealthiness of your browsers. , and that comes from property, a stealth. , and then what we got is a bet that says we're going to wait until that the network is idle. 

And this means that if the browser is downloading resources after has visited the page, , then what's going to happen is, , you can specifically, , wait until the library source downloaded. And then what we do is we scroll to the bottom to ensure that all the lazy loaded images are loaded. , and then after that we wait around two seconds and then we scroll all the way back to the top. And then what we do is we take a screenshot of the entire page by changing the viewport so that the width is equal to the body dot scroll with. And the height is equal to the,  the scroll height of the document of body. 

We take a single screenshot and we save that screenshot.  , and so now what you do is you provide you a severe ELLs and you can see here. , I'm going to be analyzing is the home page. , and then I'm going to be comparing it against these two data engineering pages. Now, if your domain wasn't inside of this first one, so you can see my domain is understanding dates. So calm that it raised an Arabic, cause you do need to update that domain. 

That's at the top of the, , of the script and then we get some clean names and then we basically say, ah, let's create a screenshot. And then we set up an asynchronous function, which allows us to loop over every year row for the both desktop and mobile devices. And then you'll see, we get this kind of output here, where it says taking a screenshot of understanding data. 

And we've also got this other one do frame.co UK and FDM group.com. , and then what we do is we then decide, okay.  We've got all these individual screenshots and I can show you a couple of examples of those. So this is the desktop. This is the mobile. This is the desktop for DeFrain. This is the mobile for the frames. 

Quite large, as you can see. , and then we've also got the desktop for FDM group and the mobile for FDM group. , so they're pretty good. There's a couple of different edge cases that we're wanting to talk about, , in terms of how will you know how you'd want to improve the script in the future. , but for now, , we'll say that these images are good enough. 

, and so what we then do is we need to convert these images to base 64. , and we've got all the images in this folder. They'd been written out to this folder. And so we're going to use glob, which is going to allow us on the left-hand side to go and access all these individual PNG files. , and so we basically go through and , we'll go in and get all the screenshot files and we'll encode those into basically four encoded images. , and then after that, then we set up a Lang chain pedantic model. 

And the idea behind this is that we want to not only get the vision model to respond to us. But we want the vision model to respond to us in a standardized way that we could include , in a application. So this could be the backend of the application and we could provide a standardized output. Bye Jason. , and so what we've got is a feedback aspects of what the aspect is, the description and the recommendations. , and then you've got a website year, row. 

You've got them some strengths, some areas for improvement, which are a list of feedback aspects. And then we've got some general feedback there's optional and also some additional comments as optional, too. , and so what happens is,  we then set up a kind of interesting. Approach where we  say, , act as a marketing research, a user researcher, , you've received that screenshots for, , my website.  And there'll be some different websites. , and then, , please provide brief analysis of the screenshots and we must provide adjacent. , Jason schema, and this is this output Paso with the get format. 

Instructions allows us to, , convert the vision models, response to a standardize output. Now the vision model doesn't currently support Jason mode and it doesn't support function calling. So this is the only way that we can actually get Jason data out of GPC vision at the moment. , but you will see what we do is we also then say a message saying, here's my website pages. , and, , then we pretend to be the AI and say, thanks for providing your web pages and both desktop and mobile versions. , before analyzing them on its research at different websites to understand the competition. 

Can you please provide some information on the different websites? And then we provide it. All of the ones that aren't our domain. , in that specific a screenshot, basically fours dictionary. , and so then we get a response from the vision model. , and you can see the vision model gives us a range of strengths and some areas for improvement. , and so that's basically what we've got at the moment, , you've got this chat model and that takes the prompt into the model into the output pass. 

So we invoke the, , We invoked the chain. And then once we get that back, then you've got this pedantic model. Now, I think, , just to  talk on a couple of different edge cases that have propped up whilst making this, , I think the next steps would be, can we automatically, , click on cookie banners? And can we also click on any popups, , banner ads? , and could we also create an X, Y coordinate grid that will allow us to completely control? , the vision model. , because that's also going to be important from, , like these two ones. 

What we're really trying to do is figure out, can we reliably generate X, Y coordinates. , to automate actions. , the other way we could do cookies as by, , the popups is by specifically looking at all the HTML data and getting rid of any JavaScript. , and just looking at the pure, dome and then asking chat TPT, can you see any Dom elements that look worthy of being clicked on, , pop up elements? , but I suspect that, , an X, Y coordinate grid will allow us to like completely control the vision model. , and drive that to be a lot more autonomous in terms of interacting with the website and also clicking away banners before it takes screenshots. , so hopefully you found this useful. 

Yeah.  , there's a lot to go through, but the main premise is we are guessing lots of images, asynchronously. , from using a browser on your local machine. And then after that, then what you can do is you can use all those images to perform a competitor analysis or multiple landing pages. 

What is the purpose of using user agents in the script?

How does the script ensure that all lazy-loaded images are loaded before taking a screenshot?

Why does the script convert the screenshots to base64?

How does the script handle different device types (mobile vs desktop) when taking screenshots?

What are some potential next steps mentioned in the tutorial to improve the script?

Learn how to leverage computer vision models to analyse and optimize your landing pages with unprecedented efficiency.

Automating Landing Page Analysis with GPT-V

Zoom Meeting – THE DAY BEFORE the Deadline

The CEO has asked you and your team to deliver a Strategy to generate more Leads through social media. You have hired 3 social media managers in the last month but not satisfied with the results. You understand the solution is to Create content at scale on LinkedIn but don't know how to execute it.


We know we need to generate more leads by creating content at scale on LinkedIn
But I know we can't have you writing content full time, and those social media managers we've tried just haven't worked out
Have you heard of a tool called Taplio?
It's a tool that helps you create content for LinkedIn on a daily basis using AI
You can create a whole month of content in an hour apparently
Let me send you a link


Imagine waking up to an account filled with notifications, meetings on your calendar, and a personal brand that builds itself on autopilot.

That’s what you get by growing and monetizing your Linkedin account!

But t takes time to create content, build your network, identify the right prospects and then reach out to them

Unless you are going to do content creation the whole day, your LinkedIn account won’t generate leads.

But what If there's a solution for this?

What if you don't want to spend your entire time working on content? 

What if you can Create a month worth of LinkedIn content under 10 Minutes??

Introducing Taplio.com

Taplio helps you to Drive more business from LinkedIn In 10min a day!

Let's take a tour through Taplio


What are the Top Features of Taplio?

AI Generated content
Industry news
Search the database
collections
Taplio feed
Analytics
Contacts
LinkedIn outreach
Engage on LinkedIn

Let's look into each of them


AI Generated content

Our custom AI engine will suggest ready-to-post content to you on a daily basis.


Industry news

Taplio collects all the latest news about your industry and arranges it in one place for you, from where you can edit and post to your linkedin profile 

Or you can use Taplio's opinion feature to instantly create content that matches your personal opinions on news articles!


Search the database

This feature lets you find any content on any topic that you want as long as it's In our database and the Taplio robot can rewrite any post to a original new piece of LinkedIn content 


Collections

Taplio collects a bunch of quality content from Twitter and LinkedIn on various topics, which you can use as inspiration for new posts 

You can create your own collection to use for later!


Taplio feed

Taplio feed helps you to schedule your linkedin posts to whatever time you want, date you want and even if you mess up the timings and posts you can always re-cue them.


Analytics

Monitoring your stats will allow you to grow even more quicker on linkedin by seeing what worked in the past and improving it

Taplio organizes all of your linkedin numbers in one single tab, So that you can optimize your profile accordingly

(Follower count, engagement ratio, views that you are getting etc)


Contacts

Contacts tab helps you to visualize your linkedin account and create lists of people


LinkedIn outreach

Outreach section in Taplio helps you to send upto 500 messages a day on linkedin


Engage on LinkedIn

The engage feature on Taplio helps you to get lot more of likes and comments on your linkedin posts by liking and commenting on other people who are inside the taplio system


LinkedIn Strategy

Welcome to this vex power course. How are we going to create this LinkedIn content at scale? I'm Alex Berman, founder of TAPO author of cold email manifesto. And that's what I wanted to go through today. This client has given us this goal. The goal is they wanna scale in the tech or digital marketing space and generate more inbound leads from LinkedIn.
How do we do that? And here are the keywords they give us. They wanna write content on cold email, lead generation and B2B sales. Our mission for today in today's ex power is to create 10 usable LinkedIn posts in under 10 minutes. How are we gonna do it? TAPO here's this tool called TAPO. And by the way, if you wanna follow along, there's a free trial.
Just click the link down below in the bottom of this vex power. And you can see TAPO here. So let's start by connecting our LinkedIn account. Uh, if you are doing this for a client, you would connect their LinkedIn account, but let's just do ours to start. I'll log to LinkedIn, and now I can close this window.
And inside of Tapio, I'm presented with the onboarding form. The AI is now analyzing the client account and it'll give us this onboarding form. Now here is where we put in the topics that the client provided. So the client wants content on cold email, lead generation and B2B sales. So let's grab these keywords and we'll put them right in.
Tapio make sure that they're all separated by commas. Then we describe the client. What am I? I am a salesperson for a rapidly growing SAS, uh, B2, B company, right. There we go. And I'm trying to hit as many keywords as possible that are relevant to this. Cuz the AI is gonna use these as the input for all of the posts that they write for us.
I usually talk about. B2B sales and how to grow your company with cold email, then we'll put timezone for me. I'm filling this from India right now. So I'll put this in India and we'll let. Go. So now tap Leo is writing some content for us. And the first thing that we see is the post inspirations page.
This is pulled from a database of thousands of LinkedIn posts that fit our criteria. This is our personalized feed here, and we can look at this as inspiration off the bat. Don't say that, say this prospect, what benefits does your product offer over other solutions? Don't say Acme is the only lead generation platform that uses.
AI to verify this, say, this sounds like you're familiar with B2B databases. Okay. Then they have this whole conversation. We'll see how AI does this. So then we click this Tapio robot and it will rewrite this post for us. And it looks like it has just boiled it down to don't sell features, sell benefits, which actually is the core of this.
But let's say we wanted it to be a little longer. We would hit the AI robot. And it would give us another version. That's what's so cool about AI is anytime you don't like what's given you, just give it a little poke, give it a little, poke, a little prod. I'm actually gonna go. Don't sell feature. Cell benefits can be a post.
So that's one way to do it. Another way to do it would be you can click one of these.
Here lead generation is the prologue. Okay. Are you struggling with email outreach? Another option would be to hit this edit and post, and then the post itself would just be copy, pasted into Tapio and then we can use the beginning as a prompt for the AI. Are you struggling with cold email outreach? If so, listen very carefully and then hit the AI.
And there we go limit your contact to one to two emails per day. You don't need a thousand daily emails focus your time on cold emails, only monitor who opens your message. And you can use the AI to just write the full post that way. Keep in mind that I like to think of AI as the first draft writer and I still need a human or you still need a human to write or, and read and punch up these posts before sending sometimes they hit it outta the park right away.
But other times it's just good as an idea generator or as a, uh, a first draft writer kind of like an intern, like one of, one of your best. Now you've seen how to use post inspirations. Let's have the AI write some content for us. So we'll click on AI generated, and now we will get some short form content written directly by the AI.
The difference between B2 C and B2B is that you're selling to people in the second case.  I think you're selling to people in both cases. So we wouldn't use that one again. This is an editor, right? You're the editor, social media manager is still needed here, but the AI helps you write content faster. B2B lead generation is hard with the right approach to exing.
Your efforts is not that hard done. That's actually usable. B2B lead generation is hard in this article. You'll learn how to two X your sales starting from day one. So check this out. I also wanted to show you how to ping the AI. So B2B lead generations is hard in this article. You'll learn how. To two X your sales efforts starting from day one, just make sure you ping the AI the right way.
So B2B generation is hard in this article. You'll learn how to two X your sales efforts starting from day one. Here's how to two X your sales get used to rejection, make it personal. And there's your article right there. Then you can add your call to action. If you want for more. Sales tips. Follow me on LinkedIn.
There you go. Add to queue. We can also go to search mode. Let's say we want something very specific and we weren't seeing it there. So let's type in one of the keywords let's type in B2B sales. And now we have a bunch more on B2B sales, specif. There is still tons of opportunity in building B2B sass. I think we could do about 50 X more entrepreneurs.
Let me hit this robot and see what it says. There's still a lot of space for B2B SAS, and we should do 50% more entrepreneurs before we start to feel the space is getting crowded. I would say 50 X more. There's still a lot of space for B2B SAS. So we can say that we could also say, here are five reasons why you should start your B2 B SAS today, one, and then it'll build a list for you.
More demand, more competition, et cetera, all the way down. So that's AI. And that's basically all you need in order to create content at scale. There's some other features in here, industry news, there are stats, there is a queue of your posts, but in order to create content at scale, all you need to remember is AI is your friend.
If you need to create a lot of content and make sure that it's hyper valuable. AI is the way to do it. So check out TAPO you can do that. Clicking the link down below and go through, use that to fulfill the obligations of this vex power course, then hit that quiz at the bottom and let's get you started on LinkedIn.
LinkedIn is a great way to generate leads and the reason why is because everybody is on LinkedIn. So get in there, make some content, generate some leads for your clients, and I'll see you soon. Thanks for. I'm Alex Berman.

LinkedIn Strategy with Taplio

What is most important when it comes to creating content at scale?

What do you think is the kind of data that you’ll need when you’re looking to scale content creation inside of LinkedIn?

What's the benefit of using AI to write content?

How are we going to create this LinkedIn content at scale?

575 million. That's how many potential prospects are on LinkedIn. LinkedIn has become the core component of the selling process, whether for professional sales, solo founders or consultants. But... It's hard. It takes time to create content, build your network, identify the right prospects and then reach out to them.


You're a planner in a branding agency but all the creatives are busy, and the client needs some mockups.

I know this isn't really your job
But all the creatives are busy and the client wants some mockups of how the new product shoot will look
He wants to emulate the style of Batman
You know, dark and gritty
The christopher nolan one, not the new one
Anyway, can you try and figure out the style we need?
We need a detailed description to go in the brief
Thanks

Prompt reverse engineering is a powerful tool for anyone looking to create images that match a particular style. Midjourney's new feature, "Describe," makes it easy to take an existing image and reverse engineer the prompt for it. This is especially helpful for those who are not familiar with art styles or don't know how to replicate an image.

Describe works by allowing users to type in "describe" and then upload an existing picture. It then generates four examples of what the prompt might be for that picture. This can be used as a starting point for creating a new image. It also provides keywords, such as those associated with iconic Hollywood stars or memes, to guide the user's creative process.

For example, if a user wanted to replicate a Batman movie image, they could use the Describe feature. This would generate four prompts based off the style of the original image. The user could then choose one and hit submit to generate a new image based on that style. The feature is also capable of understanding different art styles and provides similar images for reference.

The Describe feature is also extremely helpful for understanding art styles. It can provide a user with insight into what aspect ratio, color scheme, and other elements were used in the original image. This can be used to create new images that capture the same style, even if the original image is not used.

Clip Interrogator works in a similar way, but takes a longer time to run. Describe is much faster and provides more useful results. This makes it much easier for users to find the perfect image for their project.

In conclusion, prompt reverse engineering is an incredibly useful tool for anyone looking to create images that match a particular style. Midjourney's Describe feature makes it easy to take an existing image and reverse engineer the prompt for it. This feature is also useful for understanding art styles and provides helpful suggestions for creating new images. With Describe, users can quickly and easily create images that capture the same style as their original source.

Prompt Reverse-Engineering

0:01 Hey, I'm going to teach you about prompt reverse engineering. So this is a new feature in MidGeni called describe. The way it works is you just type in describe and then you can you know, an existing picture and hit enter.
0:18 And it's going to reverse engineer what the prompt is for that picture. So this isn't actually an AI generated image, right?
0:24 Like you can see here, I uploaded a picture of Batman movie. And it gives you four examples of what it might be.
0:31 So this is really useful because one is you can, you know, kind of click one of these and say, okay, I like this one.
0:39 I think the sounds the most similar. So I'm just going to hit submit and now it's kind of generating a new image based off that you know, that style.
0:52 So that's really useful. Like if you have an image that you kind of want to replicate. And, or at least as a good starting point, you can use that.
0:59 But I think where it's mostly sort of understanding what are the different art styles or similar art styles being used.
1:05 So you can see here, it's looking to David LaChapelle or Cara Cionnet. Or Dusan Jukerich you know, it's kind of showing the aspect ratio.
1:15 It's giving you different ideas, like in the style of snapshots of iconic Hollywood stars. Burned chart, right? So these are different keywords.
1:23 Memes, you can basically replicate you know, when you're generating new images. So it doesn't have to be of Batman. You could just take this and you could change it and say instead of, you know, You can make these pictures more videos instead of happening and you can see the you know, how you can
1:38 put in. Imagine you could say a spider man and put that in. Now you can get a sense of you know, what would the.
1:51 A spider man look like if he was more dark and gritty, right? And you can also, if this art styles, you don't really know about or like, you know, what types of kind of illustrations being used.
2:04 You know, you can, you can. And you can use this, which is, I think, pretty helpful. So so that's Majorini described as also the clip interrogator, which does something similar.
2:16 It takes a long time to run. But it's basically, I think, using the same sort of thing underneath. Mid-journey's much faster, it's much more useful, and it gives you f- forward it from examples.
2:27 So I highly recommend you do that, but I just wanted to kind of let you know that that's possible. So here we go.
2:31 Let's see what this Spiderman looks like. It's shaping up now, which I think is pretty cool. You know, so actually while we're doing this, this is a replication, right?
2:44 So we just took the prompt here, don't not raise as well papers inside of Duke Rich, which is the third one that we had here.
2:51 And you know, we have like a. Very similar style, right? So it's, it's replicated it, even though it's, you know, it's not the same image, right?
3:00 Like it's kind of learning from the style. So this is really, really powerful. It's really good. So it's a great way to, you know, take images that you like, especially if you don't know much about art and kind of find similar images and kind of give you a really good sign point.
3:15 So here you go. This is Christaman Ellen's Spiderman. Looks really cool. Alright, hopefully that was useful.

What is the benefit of using the Describe feature in Midjourney versus CLIPInterrogator?

Does the image need to be AI generated for Midjourney Describe to work?

How can the Describe feature be used to generate more creative images?

I don't know about you, but I didn't go to art school, so when I look at an image I don't know how to describe it in the proper terms.

Can we make our product shoot like Christopher Nolan's Batman?

We are in the boardroom at Whipple Consulting getting ready to discuss strategy for our client's thought leadership posts. We have the data from our research and a plan for getting the most out of our professional writer. Now we just need to figure out how to make the posts unique and save time in the process.

I know that we don't have a lot of time, but I think we should take a look at a process called repurposing. We can take existing content and build on it to create something new, and it should save us a lot of time.
Plus, it should give us the unique content we need to stand out.
What do you think?\n
Janet Jones at Copywriter:
That sounds like a great idea! I think I can take what we have so far and build on it quickly. 
What kind of timeline are we looking at?\n
William Winters at Brand Strategist: 
I think with the help of the professional writer, we should be able to have our posts ready in a couple of days. Let's get started!

Thought leadership posts are an important way to establish yourself as an expert in your field and gain recognition for your work. They can also be a great way to grow your business and network with like-minded individuals. But how can you create a thought leadership post that stands out and gets noticed?

One trick I’ve found to be useful is to rewrite my post in the style of the blog or website I want to be published on. For example, if you’re writing for the HubSpot blog, you can read some of their recently popular posts and rewrite your post in their style. You can also use the SEO keywords of their popular posts to make sure yours ranks well in search results. This helps you tailor your post to the exact audience you’re trying to reach.

Another great tip is to use analogies to explain complex concepts. This makes your post easier to digest and more engaging for the reader. For instance, when discussing the concept of dynamic pricing, you can use the analogy of painting to illustrate how it works and why it’s important. This helps to make the concept more accessible to readers who may not be familiar with it.

Finally, it’s important to treat your post like a conversation. Share personal stories, anecdotes, and opinions to make your post more interesting and engaging. This also helps to make your post unique and stand out from the crowd.

By following these tips, you can create thought leadership posts that stand out and make an impact. Not only will you be able to demonstrate your expertise, but you’ll also be able to establish yourself as a leader in your field and build relationships with other professionals.

Thought Leadership Posts

Uh, really the world is your oyster. Um, but, uh, I find this as a really powerful way to, um, basically, you know, get it in a good format. Uh, one, one, actually one trick. You can use by the way, um, is if you're running a guest post or, you know, you're kind of wanting it to get it past someone like an editor.

Like say you wanted to publish on the HubSpot blog. Uh, you know, you could actually have it rewritten, like read it yourself, have a rewritten in the style of the HubSpot blog. So it's like much more likely to get published. You know, you could actually, even if it's a smaller book that, that, you know, change, which he doesn't know about, you could actually then just go and, you know, copy.

A bunch of the recent posts are the ones that ranked the highest in SEO. Um, and then paste them in here and then ask it, um, you know, Tell me, you know, Briefly describe and bullet points. Like what the stylist. Cool. So. Here we go. Now it's been rewritten and I think it's much better. It's much more concise actually. So in the dynamic.

AGC pricing. Is it, uh, its appeal. Okay. Yeah. I've had my share of encounters. Now it talks about lotto, which is cool. And yeah, I think this is much better, right? Like it's much cleaner. Um, no, it's it's uh, yeah, here we go. It gives a really good analogy. It's like trying to pace it and price it. Painting.

Yeah, this is brilliant. Okay, cool. Uh, now we're at a much better post. And, um, now the, I think the ethics of this is much better as well. Like, you know, I really don't like the idea of just having chats empty. Right. All my posts. Right. Like I actually have interesting stuff. I think it's a show with the world. And, um, and now using it as a ghostwriter, I think is much more ethical because I'm contributing to the training data, right. I'm not just consuming it. I'm actually giving chatty T a lot of direction here saying like, here's what I think about the topic and, you know, hear my opinions. I think this is much more likely to rank on SEO. But it's, uh, more importantly, uh, going to be more uniquely interesting to other human beings as somebody to be just like the average of the internet. Uh, like you would get, if you, if you didn't follow this process. Cool. So, uh, hopefully that's useful to you and, uh, yeah, I'm using it. Um, yeah, a fair bit now. Uh, and, uh, you know, finding that saves me a ton of time. You know, this, this post. You know, it's taken us 24 minutes. I've had to explain it all to you, but, um, you know, I find that I can actually write like a four hour posts sometimes in, in half an hour, which is pretty amazing. Uh, you know, normally take me half a day, uh, or even a day to write some of these things. And now I can just get it out of my head and onto paper and, you know, use my professional rider to, to make it professional for me. Uh, and that helped me move on quickly to the next post.

What is one trick you can use to increase the chances of a post being accepted?

How much time can be saved by using this ghostwriting technique?

What does the author think about the ethics of rewriting content?

You don't have enough clients coming in, but you're also too busy to write content to attract new clients. You tried AI but it comes out sounding dull and uninteresting.

I just started consulting... now how do I get clients?

DOG SHED HEADQUARTERS – MARKETING STRATEGY MEETING

Alright team, we've got a big marketing strategy meeting today at Dog Shed Headquarters. We'll be diving into the world of automating content workflows with LangGraph.

I've been doing some research on automating our content workflows with LangGraph and it seems like a powerful tool.
But I'm a bit concerned about the learning curve involved. Will we be able to pick it up quickly?
I think it's worth the effort though. Imagine how much time and effort we could save by automating our SEO content briefs and blog articles.
And if we can improve our content output with reflection, we'll be able to stay ahead of the competition.
Let's dive in and see how we can make LangGraph work for us!

LLMs, or Language Models, have become increasingly popular in various industries, including content creation and automation workflows. By combining LLMs with state machines, we can automate the process of generating SEO content briefs and blog articles.

The first step is to clone the open-source repository provided in the transcript and set up the necessary environment variables, including the LangChain API key and the OpenAI API key. These keys allow the LLM to access the language generation capabilities and perform tasks such as generating content briefs and blog articles.

Once the environment is set up, the next step is to define the graph type and topic for the content workflow. Depending on whether you want to generate a content brief or a blog article, you can specify the appropriate graph type. The state machine will then follow a series of steps, including research, reflection, and generation, to produce the desired output.

One of the key features of this automation workflow is the ability to incorporate feedback and reflection. After generating the initial content brief or blog article, the LLM goes through a reflection stage where it receives feedback and critique. This feedback is then used to improve the subsequent iterations of the content generation process. This iterative approach ensures that the output meets the desired quality and relevance.

The use of state machines allows for flexibility in the content workflow. For example, the transcript mentions the possibility of incorporating competitor web page scraping into the initial content brief, as well as subsequent stages. This level of customization enables users to tailor the automation to their specific requirements and objectives.

By leveraging LLMs and state machines, content creators and marketers can streamline their content production processes. The automation of SEO content briefs and blog articles saves time and effort by reducing manual tasks and automatically checking content.

Using LLMs with State Machines

 Hey welcome. And in this video, we're going to have a look at how we can use land graph, Jess, to automate content workflows. You'll be specifically interested in looking at how to automate SEO content briefs, and also SEO blog articles. Now we've created an open source repo. That's got the first kind of steps. 

You can have a lookout for looking at how you can use land graph, but before you dive into that land graph is a specific thing that Lang chain has released recently, which allows you to build cyclical patterns of inside of your LLM workflows. So we've created an open source repo, which is a TypeScript version. , and it has a good starting point for how you can get side. 

So in the tutorial, make sure that you go to this. , repo after you've arrived, go and copy this URL to the clipboard. Then go into visual studio code or want to go coding editors and type get clone. And then the name of the repo, and you should end up with a repository of the looks just like this. Now on the left-hand side, you've got, for example, this ENV dot example file and you'll need to input your Lang train chasing V2, your long chain API key. , and also your open AI API key. 

Now you don't need to do the first two, but it can be very good for having a look at what's happening inside of the land graph agent. , now we're specifically, you must enter this open AI API key. That's definitely a requirement. Now inside of the repo, let's actually go and have a look at some of the different source files. 

So a lot of the magic for the graph creation happens in index dot JS, and you'll see your enter a topic and also a graph type. Now, depending upon what type of graph you create. , let's say we wanted to do a blood post. We would do bop blog. Generation. But if you do dot brief generation, It will only produce a content brief. , now, we've designed this credit girl function that we'll create a graph and then it will invoke the results and a wait for those to come back. 

And then it will also then go and write that data to. The blood poster MD file or the content brief file, or if it's doing the blog, generational, do both. , and then also there's a bit here where if you want to use the event stream, we've also designed an easy way for you to pass the event stream inside of TypeScript. 

And this could be useful for if you wanted to build out a front end UI with that.  Now actually let's go and have a look and run this graphs. I'm going to set this to graph type brief generation, and then to run the actual application, firstly are needs. , make sure you've got all of the node modules, packages, and sword. 

You also need to have no JS running on your system. So make sure you install no jazz. And then after that, , You'll need to then run NPM install, which will install the packages. After running NPM install, then. Run this command NPM run down.  Then what will happen is this index. , dot Ts file is then going to be used to specifically produce a file that's listened for. 

, and then we'll, we can have a look at is in Lang Smith. Lang Smith. , and then you'll see inside of this application. We can go and have a look and my project and see what's happening. And what we're doing here in land graph is we're first. We've got a research step that doesn't actually do anything yet, but we have a blog brief that's pre produced. , and what we're doing here is inputting a block brief.  And let's put this back to the default way of seeing this. 

So go to the chat, open AI, and you can see it's asking you to produce a brief. And then after that, then we reflect on this brief. So we're doing a couple of rounds of reflection so that the LLM could improve the brief. So it provides a bit of critique. , which is then provided back into the blog brief. 

And so the aim of this graph is to, you can see this as finished now, so you've done. A four. , so three briefs. , with two rounds of reflection. So what's really interesting about this is that we can use the reflection and the critique that open AI producers to, to improve the briefs. , again and again now,  you know, we can also change this to blog generation, and then I'm just going to hit command S and a. The Ts file is then going to basically just double-check and that will then rerun. 

So this all happening from this,  this dev, , Command, which has concurrently running MPM, , watch. , and then this MPN watch run and this one here. So you've basically got a mixture , of the TypeScript being checking and watch mode. And also we're looking in, , running that. That index such as well.  Now, if we have a look at what's happened here. , we're doing the exact same thing. 

So doing the research, the blood post, , in terms of the brief. But after the reflection ends for the blog brief we're then actually going to go and produce a blog post, and then we'll go through several rounds of reflection. So you'll see. We're , still going through this and then probably like another five or so seconds. We'll start entering and start producing our first blog posts. 

You'll see what we've started and answered the generate blog post stage. , and what's really nice about this is, , with the reflection, the aim is that with these reflection steps, You're able to improve the outputs of the blog brief and the same is true for the generate blog post function. Now, , we could also add in a section up here, which is what , we've just done, which is a dummy section for now, but we could add in the ability to scrape competitor to web pages. And include that inside of the initial blog brief, , and all of the following subsequent bulk brief steps, and also inside of the blood post generation. , so that's  one thing we'd like to do to improve this now, actually having a look at the different types of things, you've got a bunch of chains that are responsible for doing brief generation. The SEO brief reflection, the blog post production and the blog reflection. 

So a couple of different chains here. And you'll see that we using a couple of different models. And the reason why we're using different models is so that we can add metadata. Two different types of steps. , and we use that for, if we want to pass the event stream. , the other thing , that we've got in here is we've got some states. 

So we pass some initial state to our land graph. , and we've added some types for that as the agent state. , and then that's basically all, we've got to got a couple of different ones. Here's your graph types. , and in the actual graph itself is where a lot of the different types of things are happening. 

So you've got different types of nodes. , that are all returning different types of state and what you'll see in land graph, as you often want to spread the state. , updating it with the latest feedback and then spreading the state to pass on the state. , and you can see we're doing things where we're also doing the same for this block generation, and you've got some ones for reflection.  Now these conditional nodes check to see whether we should go back into the reflection stages. 

, this one saying if it's   ending on the brief, then if there's been, , more, , less than three, then go back into the blood brief reflection. But if there's more than that, , then you should, , end, right? So end the workflow. , but if we're ending on a blood post, then we'll want to, after going through blog, , blood brief reflection, we'll want to generate the blood post. , and yeah, so this is how you create the graph that you pass in that agent state. 

And you've got a load of different types of notes that we're always doing here. , but depending upon whether the graph type that we've defined is over a block generation, we're doing all of this. Elsewhere, doing all of that.  So hopefully this gives you a good understanding of how to get started with land graph and doing an application where you can specifically apply this to content workflows

What is the purpose of the open source repo mentioned in the tutorial?

What is the difference between "brief generation" and "blog generation" in the context of the tutorial?

What is the purpose of the reflection steps in the content workflow?

What is the purpose of LangGraph, as discussed in the tutorial?

Which file in the open source repo contains the code for the graph creation and invocation?

Transform your approach to content creation by mastering LangGraph, a revolutionary tool designed to automate and streamline complex content workflows.

Automating Content Workflows with LangGraph

It can be hard to come up with something new staring at a blank canvas. Whether it’s a social media post, blog or email, start by explicitly copying something that already exists and is proven to work. Then you can modify it to make it your own.

Hey I was hoping you could help me out with something while you're between projects?
We have a Twitter but we haven't posted anything in a while.
I don't suppose you could write up some tweets about data science?
Write two to start with and send them to me to check before you post

When you hear the word 'meme' you probably think of internet memes, but that's actually a hijacking of the word. It was coined by british evolutionary biologist Richard Dawkins, and it means the information version of a gene. Unlike genes which reproduce via DNA, memes reproduce by being shared from person to person.
Every creative work builds on what came before it. Listen to the White Stripes and hear Lenny Kravitz. Listen to Kravitz and hear Led Zeppelin. Listen to Zeppelin and hear The Blues. Steve Jobs stole the Graphical User Interface from Xerox. George Lucas lifted the scrolling opening credits from Flash Gordon. Iron Man was Marvel's response to the success of DC Comic's Bat Man, which in turn was heavily inspired by Zorro. 
If everything is a remix and nothing is original, maybe the way we create is all wrong. What if instead of staring at a blank canvas and trying to come up with an original thought, we started by explicitly copying instead? Rather than starting from scratch, we have a solid foundation to build on. We can “stand on the shoulders of giants” and focus our energy on improving and adapting memes that are already proven.

Meme Jacking

Okay, this is meme jacking. So you need to write some social media posts and you have a bank page ahead of you right here. Really hard to write a a hundred blank page. You needs a little bit of inspiration to get you going. So me and Jackie is basically taking something that already has. A lot of proven worth.
It's something that's already quite popular. So is there any filtered, like, you know, that people are, I've already found it useful in the past? And you're using that as a starting point. And then I kind of building on that. Kind of extracting the content and then making it original kind of innovating on it.
So you know, you could go into specific quotes. You know, there's a lot of popular quotes in here. If you think about it this is you know, these memes double validated, first of all someone thought it was good enough to write in a book. And then second of all someone thought it was going to have to quote from that book.
You can even say triple validated because, you know, even after it was quoted, then there was, you know, 161,000 likes. So the chances are, if you start with this and kind of start the concept behind it and then make it your own, make it. Then you're already starting with something that's always guaranteed to work.
So we're going to talk about data science specifically because you know, we are looking for that topic to write about that's what you know, if we're just doing kind of a general account we can just choose more broader quotes, but we want specifically stuff to do data science. Cool. So you get a lot of code sometimes they're big you know, sometimes smaller you typically want to just kind of search through to find something that jumps out at you.
So here we go. Sherlock Holmes, it's a capital mistake to theorize before one has data. So obviously that's you know, a pretty popular quote. Like he wouldn't want to just copy that, you know, it shouldn't just take that and say. I think it's stage to theorize before. You have data, you know, that's, that's like pretty close to plagiarism.
So you wouldn't want to do that, but you know, we're not here to copy something. Exactly. We're heads, you remix it. We want to make it our own. So let me think about what you know, what, from my experience what scenarios I've kind of been in where fear of. Before I had data and kind of make it unique to me.
And I think that that's really key to making it you know, not plagiarism but you're kind of using it as inspiration. So it's saying it's a mistake to theorize before you have data. So let me see. Here we go. So there was a, I remember there was a scenario when I was running my agency. I had you know, I was talking to one of the team members.
They had the ones to run retargeting ads for the client. And and you, they have the stereo already, that retalk team would work really well. Because the product was a really considered purchase. And you know, they kind of had all these theories as to why it would work but they didn't have any data.
So I asked them to look at Google analytics and we saw that the website was only getting, I think it was 3000 visits a month. It doesn't have to be precise or accurate, but it's close enough to illustrate the point. So let's say 3000 visits per month. And if you do the calculations with retargeting, you're going to have you know, probably 1%.
So 0.01 of the people click on your ad. Even if you reach all of them, let's just assume that we will. So 0.0 is your printer or one times 3000. So we're gonna get 30 clicks and then. Let's say it was like 0.03 conversion rate. So we're going to get less than 1 0 9 per month. So it's not really worth the time for us to set this up yet.
Right. So three targeting and the problem was I didn't have the data before we came up with the theories. So now let me just write this out in social media. I would client account the analyst, the account
pitching retired,
but he had all these theories.
one problem. When we looked at,
I only have 3000 visits, three K visits and.
That's the one.
Cool. Okay. So that's what we have for our post. Let me just see what the word count is. Okay. So it's, you know, it's less than a tweet, 280 we account for a tweet, so that's, that's good. That will fit. And we could kind of edit this down a little bit further now that we have a nugget of information.
But hopefully that gives you an illustration of how you think about this type of thing. And obviously it helps if you have experienced or if you can talk to someone. I who has experience you know, you could actually kind of turn this into a question that you ask an expert if you don't have that expertise yourself.
But you can see what we did here. We went from having a blank page you know, just five minutes ago to now having a pretty compelling social media. Post. And you know, if we know that this is probably gonna succeed because this is a very famous show, like Holmes quote you know, it's something that he said all the time.
It's a mistake to theorize before we have data. It's something that, that data analysts say quite often they include that in presentations and we've captured the spirit of. That, you know, in fact, we've, maybe we'll even have someone quote this back to us. We'll see. But but yeah, we, we were building this tweet on, on the solid foundation and we know that this is a meme or this is something that analysts deal with and data scientists deal with.
So we, we, we, we were pretty confident that this is gonna, you know, do good numbers but it's completely original, right? Like we didn't rip this off or, you know, we didn't just do a basic. We actually kind of related it to ourselves and I think that's the key. Hey, hopefully this was.

What would be a good example of meme-jacking for the following quote?
"Predictions have an expiry date. Action is needed before predictions expire."

Meme Jack this quote:
"The government are very keen on amassing statistics. They collect them, add them, raise them to the nth power, take the cube root and prepare wonderful diagrams. But you must never forget that every one of these figures comes in the first instance from the village watchman, who just puts down what he damn pleases."

Thanks for these, they're good to go!
Can you do 20 more?

Starting with a blank page

Your boss comes to you with a favor: can you start posting something to their twitter account? This isn’t part of your job, so you need to do more with less: what’s the quickest way to get good content ideas?

What can we post on social media?

You're planning to list your rental property on AirBnB, but first need to categorize the existing listings to see what 'meme's are common or rare.

I just heard back from the client and she has one condition before she'll sign off on the project
She wants someone from our team to actually go out to Europe for 6 months to make sure we understand how different the market is there
Travel will be paid, but you'd have to cover rent unfortunately the budget doesn't stretch that far.
What do you say? Do you want to go for it? If I didn't have kids I'd be jumping at the opportunity!

You're excited to go to Europe for 6 months, but you can't afford to pay double rent. So you decide to list your apartment on AirBnB. You ask a friend for advice on how to promote your listing to make sure you get enough bookings.

Oh I've got a good trick for this
It's a technique we use at Whipple for exploring the landscape for a brand (brandscape?)
We use it to figure out what attributes to talk about
Ironically the post I read on it is about AirBnB listings, which is why I thought of it!
It's called 'meme mapping' as in the original meaning, not internet memes
Memes as in genes, but for cultural evolution not biological evolution
Really fascinating topic...
Any way let me know how you get on

To stay consistent with consumer expectations, you first have to understand what memes are associated with your chosen product category. Here we're using the original definition of the word meme, coined by evolutionary biologist Richard Dawkins in 1976. "An element of a culture or system of behaviour passed from one individual to another by imitation or other non-genetic means." Internet memes are examples of memes, but then so are the different words, phases and design elements we use in our marketing.
Meme mapping is a method to systematically identify recurring patterns in competitive products. Once you have built your meme map, you can strategically decide what memes to incorporate, and where to differentiate your brand. The insights you gain from meme mapping are a great source of new hypotheses for conversion rate testing, or optimizing your ad campaigns with creative testing.
To start you must build a swipefile of competitive products, for example screenshots of their websites, marketplace listings or ad campaigns. Then you tag the listings with common themes until you feel like you've captured the important concepts. Finally you can do analysis of the memes you identified by seeing which ones occur most or least often, and incorporating performance data to spot opportunities or memes to avoid.

Meme Mapping

Hey, let's learn meme mapping  so we have an apartment in New York that we want to around and we want to know what listings tend to include so we can either copy it or decide to differentiate from it. So you can see, I've just done a search here on Airbnb for different listings. You actually get different results if you zoom in.
So I'll let you kind of decide what. View as most relevant to the apartment that you're renting. But you can see here that we have the listings in the side and straight away we can start to see some trends. So all the listings have beds in the picture. You know, some have different views of Manhattan.
It'd be interesting to see. You know, these get more or less bookings because you know, in some respects you can't see the apartment straightaway. You know, in other respects it kind of makes you interested in the skyline. So, you know, maybe there's some intentional kind of choices. You could also see, you know, segment these into higher alert price listings, or listings that have a set number of reviews.
Okay. So how do you do meme mapping? So I'm just going to bring up notion. This is the tool that I use, but you can really use any of these modern. Yeah, database kind of backed platform. So there's coder and air table. Some of the one I would be considered. Perfect. So first you want to make a table this would be a database view.
So here, I'm just going to make you in line, which is clinical. This is the listings. And then you basically just want to come in and copy the name. So click into the listing, copy the name.
You want to take a picture of the main image and just going to add this as a file a media. Okay. And then just let me select this and just save it to my computer. Okay. And then
add that picture there.
And then you just go onto the next slide. And keep going with it. So you know, this whole, we have the text and the image again and you just kind of keep doing that. You can, you can actually record multiple things about the listing. Maybe you want to go in and record these things here or record the description as well.
Because you can look at patterns in any of these you know, it's probably important to include the price and the number of reviews. So you can kind of add. As new fields to reviews and this case, it's a a number
Okay. So this one has 138 reviews, and those can be really useful for us to see, you know as a, kind of a proxy to bookings if, if something has a lot of reviews and it's probably pretty popular and we might want to copy some of the memes that they're using. Okay. So once you've got a few tagged and it's a pretty arduous process, you could either use web scraping to do this or do it manually.
Like I just did. Or you could pay an intern or virtual assistant to do it. But I actually, especially with something that's really important, I like to look at the listings myself just because it gives you a real sense. You kind of pick up through osmosis, what trends are popular and that really helps you do the analysis afterwards.
So even if you do pay someone or, you know, kind of. This process is probably worth just doing a few yourself just to pick up on the trends. Okay. So I'm just going to copy that in here. And this one has
138 reviews.
Okay. So once you've got the different listings, and I would say you probably need maybe about 20 you know, 10 to 20 to start noticing patterns. Then you want to start adding the tax. So with this one you know, for the image, that's a living room living room tag and then this one is a bed bedroom.
And you want to just keep going through like that. You could also tag the text as well. So this one says beautiful. So we can also tag that with beatable.
And then you've got tags for the text as well as as well as for the images. This one is sun drenched. So if you go through and you notice that there are a lot of. A lot of these with the mentioned sun drain. So I mentioned the sun or you know, others that mentioned beautiful and they have higher reviews then that could be a really good sign.
That that's a word you want to mention in your listing as well. Okay. Hopefully this is helpful and good luck out there. Me mapping.

What would make a good source of competitor assets for meme mapping?

What memes stand out from the title of this listing?
"East Village, private room with free breakfast"

Why might it make sense to use a meme in your listing that rarely appears?

Meme mapping airbnb listings

You've been given an assignment abroad and plan to rent out your apartment over the summer. What should you include in your listing?

What attributes should we talk about?

EARLY IN THE MORNING AT THE LEFTMEDIA OFFICE

You're in the office early and the CEO comes over, excited about how to automate content for the Wordpress website

Good morning everyone! I'm so excited to see everyone here so early. 
We've got some great ideas for how to automate content for our Wordpress website. I think it's going to make a huge difference for our business.
Firstly, can we get GPT-3 and Wordpress to play nicely then automate our FAQ generation/upload at scale?

Automating FAQ generation and automatically uploading it to WordPress offers several benefits, including time savings, improved customer service, and enhanced SEO visibility.

Time Savings: Automating FAQ generation can save businesses a significant amount of time in generating content for their website. Instead of manually creating or editing existing FAQs, businesses can use automated software to quickly generate new content. This saves businesses the time and effort of having to manually create and update their FAQs.

Improved Customer Service: Automated FAQs can help improve customer service by providing customers with timely and accurate answers to their questions. By automating the process of creating and updating FAQs, businesses can ensure that their customers always have access to up-to-date information about their products or services. Automated FAQs also enable businesses to respond quickly and accurately to customer inquiries, which helps reduce customer frustration and improve customer satisfaction.

Enhanced SEO Visibility: Automatically uploading FAQs to WordPress can also help boost a business’s SEO visibility. By optimizing the content for search engine algorithms, businesses can make sure that their FAQs are more likely to appear in search engine results pages (SERPs).

Automating FAQ Generation + Uploading

0:00 Alright, so it looks like we need to scale some of our content generation specifically looking at scaling those FAQ questions that we might want to include on pages and posts.
0:13 So what we've got here is a couple of install statements. We're gonna run you through the script line by line.
0:19 If you've got any questions, obviously let us know. We're doing all these imports, so basics 64 js o pandas, you know, RegX requests.
0:29 And then you'll need to put in your open API key. And then moving on, we've got, once you've got open AI connected, we'll also then need to get access to the WordPress backend.
0:43 And when you have WordPress, the best thing I would recommend is having a look at this tutorial. All following along here.
0:50 What you're gonna need to do is essentially create a new ye user. So it could be like test app and then the domain.
0:58 And then what you want to do is then put in a password as well and then you'll use the username with the password.
1:08 And then essentially your base U URL is gonna be whatever your U URL is. So whatever your u URL will be, that's what it'll be, right?
1:16 That'll be your base U URL for example. And then you've got the username and password. And once you've got those credentials, the rest of that code basically gets the credentials.
1:28 Bay 64 encodes it and then yeah, decodes it to UTA eight. And then we pass that in in the headers and you'll see that we are doing w p Jasons and the posts.
1:39 So first thing to know about the WordPress REST API is by default you can specify PERS to get per page.
1:47 It will only default give you 10 posts per page per request. But we can scale that up to do a hundred per page and then we can loop through the pages and get multiple posts.
2:02 But, so that's an example of pation, but we can take it in a step further and also add on the status, the status of the posts.
2:10 And so what you'll see is we are getting the publish and draft posts by default. But in my case I wanted the draft, so maybe I'll get my draft posts.
2:19 And if we have a look inside of my site, you'll see that we do indeed have 28 draft posts. However, you can easily change this.
2:28 So if you wanna do published posts, you would do that and you'll now see that if I do that, notice how I get 36 published posts, which is correct.
2:40 And you could also add on multiple ones, right? So we can do both publish and draft and you'll see the length of that has also now increased to 64, which includes everything cool.
2:52 So I'm just gonna set mine to draft post, but feel free to keep yours in either draft published or published.
2:56 So change that according to your preference that function pages through the WordPress API and is gonna allow us to get those results.
3:04 The next thing that we've got going on is some funky reg rejects as a way to extract FAQ questions from GPT three s o open ai.
3:13 And we also have a prompt that says, given the following article title, provide a list of FAQ questions that we can include at the bottom of the article and make sure the questions cover the topic in a comprehensive way.
3:24 And then we've got an example and then we also have a separate function, which is write a detailed and factually correct answer to the following question.
3:34 And then what we can do is we can use this generate FAQs as a way to generate some FAQs given an article title.
3:44 So we'll just give that a second and let's have a look. So if we have a look at FAQs, You'll see that the FAQs come out like this.
3:54 And then we've got this extract function that allows us to pass that data back into a Python data type list.
4:01 So with that being said, we then loop over and I just, before we go on, it's also worth bearing in mind that you will need to have titles in the top of your in the top of your post to run those GT three scripts.
4:14 So you will need these titles at the top. So we then create dictionary and we gather the post ID title slug and the FAQ object.
4:24 We loop through all of that and we generate all these FAQs. And what we end up with is this data frame where we've got the original post id, the PostIt, the post slug, the post faq and does it have FAQs or not.
4:39 And then that's coming from this line here. So you can see that's what's running when you've got that. Then what we do is, in our case we are interested in, for all the ones that do have FAQs, we want to add a bit of a sleep and then answer those FAQs and store those in the original FAQ dictionary.
4:59 And then we've got this final function which is doing a patch request. And so what happens here is we get the original postal with a get request and then when we get the post data, we take the content that's rendered and then we add on our F f F faq, H CML data to that res, save the data as the content and then patch the original request.
5:23 So that's kind of what's happening there. Notice how we are using the post id which is in the url, which means that we're only editing that specific post.
5:35 And then as well as that we've got a couple of different ways you could ingest and use the FAQ accordion content.
5:42 So you can either, either use the accordion blocks that's a plugin you can install on your, on your WebPress website.
5:48 So you can use Ivo accordion blocks and if you are using accordion blocks, make sure to only run this specific pipe and function function and not this second one.
5:58 However, if you want to use otter blocks, that's also possible. So I've coded up both and I personally think the Otter blocks one looks quite good.
6:07 This is what it looks like after it comes out. So very, very nice. Pretty easy to implement and you just need to have that plug-in installed.
6:14 So choose either of those two plugins, activate the plugin, and then obviously run the function. So I'm gonna use this one cuz that's what I've done.
6:24 And just to show you it works in progress, let's go and delete these this bit of content. So I'm just gonna go and delete this and I will also do the same on the other draft cuz we've got two drafts in our data frame.
6:38 So I'll just edit both these. So we'll just wait for that to load. Let's see. All Right, so that one doesn't have any FAQs.
6:57 And then we will also get rid of the FAQs on this one here. Click save draft. Cool. So I've now got two posts that don't have FAQs.
7:10 And then essentially all we're gonna do is just loop over that data frame and if the row has FAQs, we've answered them inside here and we're gonna generate that faq, accordion html, gonna add a sleep, and then we're gonna add the FAQs to post.
7:28 And then once you run that, it should take a couple of seconds. And then now if I go back into my original posts, so let's reload these.
7:36 So these are the two that I've edited. I'm gonna click this classic converter blocks. You don't need to do that if you don't want to, but there you go.
7:47 Cool. So now I've got all these FAQs that have randomly appeared on the page which is great. So I'm just gonna convert to blocks.
7:54 And then you'll see at the bottom here you've got all these FAQs. So I think this is really powerful thing you can do is sort of use GT three to essentially generate some ideas of questions that would be useful given a specific article title.
8:11 After we've done that, we've then generated the answers for all the ones in the data frame that did actually have that.
8:18 You'll once remove this line here. This if is index is equal to one. So I'm gonna comment that out. But that was just to show you that you know, I only wanted to show you two examples.
8:29 So I'm gonna leave that commented out. But yeah, so that gives you that data frame and then obviously we go through and we answer all the FAQ questions for each individual row of the data frame, putting in a sleep here just for a bit of rate limiting and then adding the FAQs to the post.
8:45 So hopefully that was useful and helps you to scale out some of your FAQ content generation.

What is the main purpose of the script discussed in the context?

What is the default number of posts retrieved per page when using the WordPress REST API?

Learn how automatically create FAQ content at scale using GPT-3, the Wordpress REST API in Python.

Can we improve our FAQ generation process?

In light of copyright concerns, the publisher you work for has banned the use of artist’s names when making AI art for your articles. Perhaps there’s another way to get something more original?

I understand everyone else is doing it
But that’s no excuse not to hold ourselves to a higher standard
We don’t want to be the ones with legal issues in six months when all these artists start getting litigious.
There is a better more creative way to do this
Have you heard of unbundling? It’ll ultimately get you to better work anyways so I highly recommend you learn it

Have you ever wanted to create something new and unique but were limited by the existing works of art and designs available? If you’re looking for a way to break free of those restrictions, then meme unbundling could be the perfect solution.
Meme unbundling is a technique that uses artificial intelligence to deconstruct an existing image or painting and create something new from its components. It was first developed by Bakz T Future, who used it to create new images from the iconic Starry Night painting by Vincent van Gogh. They asked a GPT-3 algorithm to describe the painting in detail and then used the results to generate something new.
The same technique can be used to create something unique from Salvador Dali’s Persistence of Memory. By asking a ChatGPT algorithm to describe the painting’s artistic style without mentioning Dali’s name, you can create something that looks similar to the original but with its own unique twist.
The advantages of meme unbundling are numerous. For one, it allows you to create something that looks like the original artwork but is not a replica. You can also customize the results by removing elements you don’t like and adding in those you do. This way, you can create something that’s truly unique and special.
It’s also a great way to show your appreciation for an artist’s work without infringing on their copyright. By deconstructing their artwork and using the components to create something new, you can pay homage to the original without running the risk of getting into any legal trouble.
Finally, meme unbundling can be used to create art with a surrealist twist. By using AI to generate a description of the painting, you can get a more abstract, dream-like interpretation of the original. This can be used to create something truly unique and eye-catching.
Overall, meme unbundling is an incredibly versatile technique that can be used to create something truly unique and special. Whether you’re looking to create something similar to an existing work of art or something completely unique, meme unbundling can help you get the job done. So if you’re looking for a way to break free of existing restrictions and create something truly unique, give meme unbundling a shot. You won’t be disappointed!

Meme Unbundling

0:01 <affirmative>. Okay. Lemme teach you about unbundling, which is one of my favorite techniques to get more advanced, interesting images. So here I have a picture of or a painting of Times squared by Salvador Dali.
0:13 You can see it's in his kind of unique style, surrealist style which is really cool. But, you know, I don't know how long this is gonna be possible, right?
0:21 Like by Salvador Dali, he's in the public domain. But what if you like an artist's style and you can't really you know, use their term anymore like you or you, you know, don't want it to be exactly like Salvador Dali.
0:33 You kind of want to use some of the elements, but not others. So unbundling is something I found from Baxt Future.
0:40 You know, on the ck they use the example of Van Gogh Starry Night.  And they basically asked g PT three to describe in detail you know, what, what makes Starry night, starry night.
0:55 And then they put that into the prompter. Got some really creative pictures. So I'm doing the same thing. I've asked Chachi b t to describe the characteristics and art artistic style of the persistence of memory by Salvador Dali.
1:09 That's his famous one with the clocks melting. But I've added this extra piece here, which, which is, without mentioning his name, otherwise it keeps talking out Dali which, you know, kind of is against the point of what we're trying to do.
1:21 So what we're gonna do is gonna copy this. And you can see here it says like, the painting features a surreal landscape.
1:29 It talks about, you know, the pocket watches draped over objects they're distorted is a dream light quality to the scene.
1:38 Muted and subdued paintings. So they've kind of picked out all of the different attributes or elements of this which is really cool.
1:46 And I'm just gonna post this in here, painting off Times Square. Then I'm just gonna generate and see what we get back.
1:56 And the, the other benefit of doing this, by the way, while we're waiting for this, is now that we have all of these attributes, we can just go in and kind of get rid of the things we don't want.
2:06 So if we don't want there to be clocks in it, for example, we can get rid of time pieces and change some of this text.
2:13 We're kind of unbundled the different features of what makes a dolly photo interesting, right. You know, we could even change this.
2:21 So instead of muted and subdued, we could say we could say bright and vibrant, right? And see what we get from that.
2:28 Cool. Let's see if we finished generating and let's see, it's coming up. Oh, wow. Look at that. Okay, cool. <laugh>.
2:39 Nice. So this basically just recreated the original dolly. This is basically the same thing, but with some skyscrapers in the background.
2:47 But I think like these two are really what we're looking for. You know, like we've got Manhattan kind of skyline, but it's a little bit different.
2:55 And then this one I think is probably the winner, right? Like it's got the clock here but It's kind of like a cool surrealist style.
3:02 And we can kind of edit from there and kind of add in different features that we want. I think this is gonna be increasingly important.
3:09 You know, you can use one AI to talk to another, essentially as what we're doing here. We can unbundle the specific features, like what makes an image interesting or what makes the style interesting, and then that can lead us to more creative results.

What artist's painting is used as an example in the tutorial?

What can we do with the unbundled elements to make the painting more unique?

Including “in the style of X” in your prompt is lazy and maybe even unethical. It might even go away in the future. You need to unbundle an artist’s memes instead.

Copying an artist without ripping them off

UPSERT HEADQUARTERS – WATERCOOLER CONVERSATION

You've just been assigned to the Data Science team at Yearbook, and your new boss has asked you to learn how to use Dream Booth for AI profile picture generation. You'll need access to a GPU and 10-30 images of the user for training. You're excited to learn this new skill, and you can't wait to show off the results you'll be able to achieve with Dream Booth.

I can't believe I'm finally getting to use Dream Booth!
It's supposed to be really powerful for creating AI profile pictures.
I can't wait to see what I can do with it!
I just need to get access to a GPU and 10-30 images of the user for training.
I'm sure I can do it!

AI profile pictures are becoming increasingly popular on social media platforms like Twitter and Instagram. With the help of tools like Dream Booth, users are now able to generate AI profile pictures in just a few steps. Dream Booth is a way to fine-tune the Stable Diffusion Library to train models on user-uploaded images. This can be used to create personalized profile pictures with a unique style or to make a picture look like a scene from a movie.

The first step to using Dream Booth is to view your resources and change the runtime type. It's important to make sure you're running with a GPU as Stable Diffusion and model training are resource-intensive. Once you've set up the environment, you can edit the part in the code with different concepts. It's best to only focus on one concept at a time, as combining multiple concepts can take a long time and not always produce the best results.

Once you have a concept in mind, you can start uploading images to train the model. You will need a minimum of 10 images, with 20-30 being ideal. It's important to make sure the images are diverse, having some full body shots, close-ups, different clothing and locations. This will help the model understand the common threads of what makes you, you.

Once you have the images uploaded, you can run the training code. You can also set a seed to get the same image every time and adjust the guidance scale. The higher the guidance scale, the closer the image is to the prompt. However, the lower it is, the more creative it can be. You can also adjust the number of inference steps and samples to achieve the desired results.

Once the training is complete, the model should have generated an AI profile picture. It can take anywhere from 10 minutes to 10 hours, so be sure to have a GPU ready to speed up the process. The results vary, but with the right guidance scale, inference steps, and samples, you should be able to get a good quality image.

AI profile pictures are a great way to stand out on social media and express your creativity. With the help of tools like Dream Booth, you can generate AI profile pictures in just a few steps. All it takes is a bit of creativity and some patience, and you'll be on your way to creating a unique and eye-catching profile picture.

AI Profile Picture Generation with Dream Booth

 Hey, I'm gonna show you how to make AI profile pitches. Like you might have seen on Twitter. So, There are a few of these tools out there that do this. And to be honest it's probably better and easier just to use those tools. Especially if you don't have access to a GPU, but you know, I, I think there's a lot you can do in terms of flexibility. Once you understand this format. 

And like how it works. We're using dream booth. Dream booth is a way to fine tune this Stable Diffusion library. To train it on your own images so you could train it on a specific style or you could train it on. Pictures of yourself. Like, like I have. The main thing to note here, I'm just gonna connect. 

Is when you connect you wanna view your resources. And change, your runtime type. And you need to make sure that you're running. with a GPU. So the reason why you need this is you're running stable diffusion and also training the models. And that is resource intensive. So I'm not actually gonna run this. I've run it previously, just cause it takes quite a long time. 

But you'll have access to this code to be able to run it in a, in a couple hours yourself. So we're just. You know, the first thing, just downloading. The install Requirements so that's pretty quick. And then you need a hugging face token. So this one is mine. I am. You know, I'm gonna delete this afterwards just so you guys can't access. 

But in order to get it, you could just go. Into hugging face. This is the the original stable diffusion. the 1.5 version. And then I'm just gonna go to settings, I think. First you have to accept this model card. Which I've already done, so it's not showing up for me, but. 

If you go to access tokens and then You know, you can create a new access token here. So that's where you would run this. And then if you want to invalidate and refresh, you can do that here as well. 

And then this token will stop working. So that's fine. Cause I'm not running this. The the model name that you're using. Is stable diffusion one five. And then you have like an output directory, which is gonna kinda store this. Locally. There's just enough Ram and and storage in the computer that Google CoLab gives you to store all this but it's kind of getting to the limits. 

Okay. So the main thing you need to do is.  you need to edit this part here. So you know, you can put in different concepts. I would say only do one concept at a time. And then, and then like generate the image and then cut out that part. Because when you try and combine multiple concepts, it tends not to work very well. 

And takes a really long time for training. So here we go. What we're doing is we're the instance prompters photo of a UK J person. And this is the type of class. So if you're doing a style, like a certain type of art style, you could change that here. And then the reason why we use KJ or. 

You know, Z W X is because that's like pretty far away from an actual word, right? It's not a real word. So, it won't get Confused. And you know, there's different types of classes. So like this product person, or you could have style. right. So that's just going to run when you run that to the 

It will do the json dump here to kind of use this concept list when it's training. Now what you can do is upload the actual images and what I've done. I just went on my Facebook account, and downloaded 30. I think it was 30 years. Actually only 20 images of myself, just screenshotted them. And then I, and then I uploaded them. I would say, typically you need at least 10, otherwise it doesn't work very well. 

About 20 is fine. 30 is great. The more you upload the longer It takes obviously. But about 20. was fine. Main thing to make sure is that the images are all like. Very similar. or not, not very similar. So you wanna make sure that the images like, have some diversity, you know, some full body, some close up. 

You know, some of you laughing, some of you wearing a hat. Different wearing different clothes in different locations. I think that tends to improve the diversity because then it can kind of see the common threads of like, what makes you, you. When it kind of you know, trains the this is the actual training code here, so nothing to change. 

Other than the sample prompt. So what I wanted to do is I wanted to. make an illustration of myself and the style of Spiderman into the Bi biodiverse. I generated this prompt. I, I would say like, this it's really good to combine fine tuning. With prompting. So this is an actual prompt that I used to use in order to make into the biodiverse type images. And then this is kind of like doubling up. Right. So you know, we have the prompt and then we have the image of me and then you know, that way. 

You know, I don't have to like, kind of describe myself in this prompt. It can actually get me from from the training data. Cool. So you can also save the weights and reuse them if you want. I haven't saved them in this case. It takes up quite a lot of space. in your Google drive. 

or locally. And then. When you run this then it's generating the example images. After the training. So just. to see here. This took about 10. I guess this is 10 minutes. It's not, oh no, sorry, it's 10 hours. Yeah. it's quite a while. I was running. it, Yeah. I think, I think it's. 

I think it's 10 minutes. But it's you know, sometimes takes a long time to run. The you know, I've run it before and it took half a day. So I think that's probably the longest. Just make sure you have the GPU and that that's what makes it faster. Cool. So it did a pretty good job, right? Like this is decent. 

Image of me. Obviously this is kind of cheating showing me in a mask. But, you know, this is kind of. You know, taking my beard and my eyebrows and my hair and stuff. And. yeah, I think it's done a good job of matching the style. And and putting me in, into the spider verse. You can also save the weights and kind of use use that for. 

Some of the U web. UIs, Like automatic. If if you want but you can also just keep running it in this Google collab. So. This part here is to actually kind of run the pipeline and then you can set a seed. Here. That's just so you get the same image every time, if you use the same prompt and then I've used the specific prompt. here. So illustration. U K J person, the style of Spider-Man. Blah, blah, blah. right. So that's what it's come back with. And you can edit this. You can say, you know, I want guidance scale, like. you you know, The the higher, the guidance scale. The closer it is to the prompt. the lower. The more kind of creative it can be. There's also a number of inference steps. so, You know, if these steps are higher, it tends to be. Higher quality images, but not always. I I think it's good to experiment with this. And then number of samples as well. So generated four images here. And yeah, you can see it's done. Pretty cool job. here. Cool. So that's, that's how this works. 

What type of data is used to train the model?

How can the guidance scale and number of inference steps be used to generate better images?

What is the model name that is used for training?

What type of runtime is needed to run the model?

What is the minimum number of pictures needed in order to train the model?

Ever wondered how those stunning AI-generated profile pictures on social media are made? Struggling to make your online avatar stand out? Join us as we unravel the secrets of Dream Booth, teaching you to harness the power of AI for unparalleled image generation. Say goodbye to generic profile photos and hello to a new era of personalized digital identity.

Mastering AI Profile Picture Generation: A Deep Dive into Dream Booth

LOCAL COFFEE SHOP – WEDNESDAY AFTERNOON

You and your boss Gustav Gieger, CEO of GoolyBib, are sitting in a local coffee shop on a Wednesday afternoon. You've been tasked with writing a whole story with AI, and you're discussing the best way to use recursive reprompting and revision, based on the hero's journey template and least to most technique. You also need to ensure accuracy and consistency in the story.

We need to make sure that our AI story generator has enough context to make a coherent story. It needs to know the beginning, middle and end of the story.
We should also look into the hero’s journey framework and the least-to-most technique to ensure accuracy and consistency.
Let me do a little research, and then we can come up with a plan for how to approach the task.\n
We can use recursive reprompting and revision to make sure that the story is as good as it can be.

Recursive reprompting and revision is an AI technique which seeks to generate longer stories beyond the limitations of the context window. By using a plan-and-draft-and-rewrite module, AI can be given a premise and then use that to generate a setting, characters, plot points, and ultimately a coherent story.

This technique starts with the premise, which is used to generate a setting. Characters are then generated based on the premise and setting. From there, the plot points are outlined, and the draft text is generated for each plot point. Finally, the draft text is rewritten in case it doesn't make sense with the facts that have been established.

The plan-and-draft-and-rewrite module can also be used to address the issue of hallucination, which is when AI makes up facts that don't actually exist. To do this, it checks for consistency between the new facts and the old facts. For example, if an AI writes that two characters have been friends for a long time, but it was established earlier that they just met, the AI will rewrite the text to match the facts.

This technique is based on the hero's journey, which is a template used in many successful movies such as Harry Potter, The Matrix, and the Lion King. It is also a form of progressive extraction, where the AI progressively extracts facts from each text and builds up a list of facts.

In conclusion, recursive reprompting and revision is a powerful technique which allows AI to generate longer, coherent stories. By using plan-and-draft-and-rewrite modules, hallucination can be addressed, and the AI can generate stories based on the hero's journey template. Through progressive extraction, AI can build up a list of facts as it goes through each text.

Recursive Reprompting and Revision

00:01 Okay, so this is recursive, reprompting and revision. So this is a technique for writing coherent stories way beyond the context length.
00:11 This comes from a paper that you told me to hear generating longer stories with, with a recursive, reprompting revision. And the general idea here is that you can't just say, like, write me a story.
00:24 I mean, novel to the AI because the context window is relatively small. So you can get like a few thousand words in and then you know, then you have to kind of generate the next section, but it's not aware of what it wrote in the previous section, right?
00:40 So you know, chat GPT makes this a little bit easier in that it can kind of see past messages, but again, you know, you can kind of run your tissues with hallucinations.
00:49 So what these guys came up with is if you kind of recursively build the story using these kind of plan and then draft and rewriting modules.
01:01 So the way this works is first you generate a plan. So what's the premise of this? You know, what are the characters you know, where's the location.
01:10 And then you use the plan to generate each draft the plot points. And then for each plot point kind of generate the draft text.
01:19 And then. And then rewrite the draft text in case it doesn't make sense with any of the facts that are coming in so far.
01:26 So let me just dive in here and show you how this works. And so this is a you know, Google Colab notebook.
01:35 Just, you know, you can run this and you're gonna share this as long as you have your own API key.
01:40 If you click here and go the API keys, I've also linked to the paper here. But you know, if you run the cell, if you just click play, if you press like shift and enter, command and enter then it's gonna prompt you for your key.
01:52 You put that in there, install open AI. So run that. And then this is just some code to run the completion.
02:00 So like to actually message open AI and get the text back. Cool. And if, if all this is working, you say, you know, you'll get a response from open AI.
02:10 All right. So here's the plan module. This is the first part you put in the premise and you can type it in here.
02:16 Actually. This is just like a feature you can do with Google notebook. A new grad law a new law grad returns him.
02:26 Start a career, but start also with a broken justice system. And you know, we we feed the premise in to open AI and then we get the story.
02:39 Setting back, right? So that's the first thing we get back. And this is why it's called recursive re-prompting. Cause it's kind of, you know, you put in the premise and you get the, the st- setting.
02:49 And then we're going to put in the premise and the setting and get the characters. So you can see here, we put in the premise to the prompt and the setting.
02:58 And then we give it like a character format. So we've asked it you know, give it like name and then context, given some examples.
03:07 And then told it not to reuse the same character names because it has a habit of doing that. Cool. So you run that and then you're going to stop when it gets to the full stop.
03:19 So make sure that it's only one complete sentence, otherwise you get really long descriptions sometimes. And and then it's going to kind of generate the characters.
03:28 So here I've just given it just asked if it's just going to get two characters here. It came up with Lela Smith.
03:40 So now we're just asking to outline the main plot points of the story. So again, it's recursive re-prompting. But now we're in.
03:48 We use the premise to get the setting, but now we use the premise and the setting to get the characters.
03:52 And we're using all three to get the outline of the plot points. So the plot is basically Lillyn Muftham. She discovers a broken g- the justice system, she meets Toby.
04:04 Together they fight against injustices. And despite facing obstacles, they find success. And in the end they become respected advocates. If you're paying attention here, this is basically the hero's journey.
04:15 So, it's really interesting that you know, we didn't tell her to use the hero's journey template, but it's obviously, you know, derived that from the data.
04:23 So, this is the same story behind Harry Potter, The Matrix and. Lion King you know, any Marvel movie really, like every, every successful movie uses this template.
04:35 So, pretty interesting. It comes up with that. Cool. So, now, this is what we have so far. We have the premise, the setting, characters, and then.
04:43 And this is the planning module altogether, right? So, this is kind of planning what the story's going to be. And this is also using another technique that you might be familiar with, which is, is in general.
04:57 Purpose technique with AI which is the least to most technique. Right? We started with the least, like the smallest thing, which is just the premise.
05:05 And then we're kind of expanding out to the most, right? Like, we've, now we have a whole plan. We can kind of feed that.
05:11 And to, you know, generating more stuff. Cool. So now we're asking for the plot points. So I'm just going to split.
05:17 So we have like a list of these without the numbers. So that's useful. And then we're going to iterate through.
05:25 And with every plot point, we're going to give it the previous summary story. We're going to say immediately before this passage.
05:32 This is what you wrote. And then in the upcoming passage, this is the new plot point. Here's some relevant. Context as well.
05:41 And you can kind of see that coming together here. So if you have if you start with say plot point two you know, it's given the context of the characters.
05:53 Previous summary story is that Lula moves back to her hometown as this is the text that it generated just before.
05:59 And then in the upcoming passage, she's dismayed to discover So what we're doing here is, you know, really based off this draft module in this paper.
06:10 And, you know, it's giving the relevant context to, you know, upcoming passage, etc. So. We've just kind of translated that into our prompt template here.
06:20 Cool. So that actually generates the whole story and you can, you can join it all together here, so like, the Smith graduated from college, you know, you should move back.
06:30 She knows the area well, you know, so this is like the whole story. And then introduces Toby Johnson. Also returned to his hometown.
06:39 Cool. Let's leave that in. Toby were excellent lawyers, right? Yeah. So this is like the whole story. It's put the whole story together and it's much more coherent than if you just kind of prompted these things in isolation because it has the continuity.
06:55 Of each draft module feeding off the previous one. But there's sometimes issues with this. One thing I found when I run it with this prompt in particular, like the premise is that sometimes like Leela is, you know the same, you know, graduated at the same time as Toby, which doesn't necessarily make
07:17 sense, right? Sometimes it says that they move, move back and meet each other, but then it. The next bit it says that they had been friends for a long time or that they've been practicing a lot together for a long time, which doesn't make any sense.
07:30 Right. So they still have some issues with you know, hallucination and. And this is like a pretty useful module, even on its own, this revision module to, to start hallucination.
07:44 You can basically just ask it, you know, are you making things up, right? Like, like what's wrong? With this text, you can get it to correct itself.
07:52 So the way that we've done this I've departed a little bit from this paper. They have this whole coherence and relevance thing where they generate multiple drafts and then.
08:06 You know, different algorithm. I didn't do that. I think it's overkill potentially for this. And that's not necessarily prompt engineering, right?
08:16 But you can kind of think about. This is like a multi-vote. So you know, it generates multiple drafts and then it ranks them based on coherence and then chooses the top one.
08:25 That's one way to do it. You know, there's also the edit model, but they kind of keep this two different steps of these inferred tax, inferred facts.
08:35 They keep like an attribute dictionary. So like Lisa Turner is the younger sister, you know, gender is female. You know, workplaces, the restaurant, right.
08:45 So they, they gone a little bit deeper with this. I just want to demonstrate the whole revision kind of prompt concept.
08:52 So what I've done is just focus on the Vax. So what facts can be inferred from this text? And you can see here, I start actually on index one meaning you know, we, we skipped the first text.
09:08 So we're going iteratively through the te- the drafts, and we're taking the first draft as a gospel. So anything that's in the first draft is gonna be inferred as, as facts, right?
09:20 Because there's nothing previous to disagree with. But we're going through like the reader would and then we're checking whether the next paragraph you know, agrees with the old facts.
09:31 So we have this faxed fax array, and we have this edits array. And what we're doing is we're checking the facts for the old text.
09:42 We're getting the response. And then and then we're adding that to the facts to this array. And then we're getting.
09:50 Checking in new facts. So what could be a friend from this text? And then we're joining this is kind of getting the old facts like as, as we go through this, we're going to have the old facts from the first text and then we'll get to the second text.
10:04 We're going to have old facts from two texts, right? The two previous texts. So we're going to have like a longer list.
10:09 This kind of joins all that together with spaces and then, or with the new line. And then we're asking it for consistency.
10:18 So saying, are any of the new facts inconsistent with the old facts? And if you remember the old facts will continue to grow, right?
10:26 Like every time we add a new edit it's going to be checking the old texts that came before. And adding those facts.
10:33 So by the time we get to the sixth paragraph, we're going to have, say, five sets of old facts. So keep up with it.
10:41 This is a concept I call progressive extraction because we're kind of. Progressive summaries, the summarization is where you go through and you summarize each text and then you maybe like summarize the summaries.
10:54 Progressive extraction is where you go through each text progressively. But you extract the facts out or you extract quotes out or whatever it is you're extracting information.
11:05 So we're going through kind of building this list of facts and then over time we've got, you know, more facts to agree with essentially.
11:13 So we're checking the consistency and then here we're just simply asking it like edit so any consistencies are addressed. And we've got the rewrite and rewritten text, which is what actually goes into the edits and the edits.
11:26 The final kind of version of the text. So I'm just putting it out as you go through so you can see you know, Lula Smith have been pressing the law, the old facts.
11:39 You know, we're here. They, they moved back from their hometowns. So they've made a formidable legal team, blah, blah, blah.
11:49 Here it says in terms of consistency it's saying that they've been practicing the law in their hometown for a few years while Tony jumps and only just moved back to his hometown.
12:00 So they both graduated from the law school, both moved back to their hometowns. Was it but then they're saying. That they had worked basically like he had only just come back and she had been back for a while.
12:15 So so basically it rewrote the text based on this issue. Right. Here we found no consistency. So in this module, I've kind of kept it relatively simple.

What is the purpose of the recursive reprompting and revision technique?

What is the hero's journey template mentioned in the tutorial?

What is the difference between the paper's approach and the approach taken in the tutorial?

It's easy to create short form content that's consistent, but AI tends to hallucinate and introduce inconsistencies when you go outside the amount of text that fits in a single prompt.

I want to write a whole story with AI

VEXNOMICS OFFICE – CONTENT SPRINT PLANNING MEETING

You've been tasked with scaling out the social media content. The social team are looking for innovative ways to improve their content velocity.

Hey, I'm looking for a way to re-write my Twitter content at scale. 
I heard GPT-3 is a great option. 
Can you tell me more about it?

Sometimes the process of re-writing competitor content is called 'Meme Jacking' - https://marketingmemetics.com/essays/meme-jacking

So what are the benefits of re-writing content using code?

1. Increased SEO visibility: Rewriting competitor content using GPT3 allows you to generate unique versions of the same content, meaning your website will be more likely to show up in search engine results for certain keywords and phrases.

2. Better customer engagement: By re-writing competitor content, you can update the content to better suit the needs of your customers. This can help keep them engaged and on your website for longer.

3. More cost-effective content production: Rewriting competitor content with GPT3 is far more cost-effective than creating new content from scratch. Therefore, it’s often a great way to increase the amount of content on your website without spending too much money.

4. Increased automation: GPT3 makes it easier to automate the process of rewriting competitor content at scale, meaning you can save time and resources that would otherwise be spent manually re-writing the same content over and over again.

Re-writing Content with GPT-3

0:00 All right. So we've been tasked with scaling out our social media content. A couple of ways that we could do this one in particular is we could automate some of our social media content by looking at what competitors have been doing and figuring out is this a personal story or is it not a personal story?
0:17 And if it isn't a personal story, then we could potentially rewrite that LinkedIn post or that Twitter post. So we've written a script to do this for you.
0:27 But what I'd like to do is run through it with you, but line by line. So hopefully it makes sense.
0:31 So at the top, we have a couple of Pippin installs with a package we'll be using called twk that allows us to interface with Twitter.
0:40 We've also got open AI that will be used for the GPT three and also a datetime package and Panders.  And then you'll see we've got some imports as well as some bits that you'll need to fill in.
0:52 So the open ai dot API key, you'll find in your open AI account. And these keys here, all the way from consumer key down to access token secret.
1:02 Those those you'll be able to get through setting up a Twitter app at the Twitter development. And you'll need to get these keys here, these API key and secret and the bar token and the access token secret and just click regenerate and get those.
1:16 And once you've got all of those, what you can then do is have a look at this code. So we're authenticating with Twitter.
1:24 We're also waiting on rate limits, which means if you do run into weight limits, then the API is gonna go to sleep for a couple of minutes.
1:32 And then you'll be able to then re-query inside the same function, which means you won't get errors if you do a large amount of querying.
1:40 So let's have a look at what it looks like if we're just querying for Python and getting a maximum count of 500 and the length of that.
1:49 And then you can see here we are able to essentially get a range of different tweets out you know, from the Python community.
1:58 So this is kind of like one thing that you could do. But what's quite interesting from our point of view is we've written some automatic Python functions to help you automate this.
2:08 So this one here, scrape tweets takes in a couple of different parameters. So like it takes in the Tweety object, takes in a keyword, which is a string and also it takes in the number of days which is an integer and also the number of pages, which is a integer.
2:24 And then what we're doing here is basically just finding how many number of days do you wanna look back, and how many pages do you want to see?
2:32 And notice here there's a count. So we're cursing through a hundred tweets at a time with a one second sleep.
2:38 And then we can go through any number of those pages and any number of those days. And then if we hit a time where we have gone back to the previous time then we break out of the for loop and then return the list.
2:50 So at some point we will break out of this loop if we go far back enough. So, and then the other thing that we've got is the ability to scrape user tweets.
3:01 So if we know a user's timeline then we can essentially go and get a bunch of their tweets based on chunks of a hundred and the number of pages that we want.
3:12 And however many pages you want going backwards in time. Cool. The other functions that I've written for us at the moment, you can see we've got this generate related keywords and we do a bit of text string manipulation to kind of clean up the data and return a Python list.
3:29 And so the prompt there is kind of like creating an order list sort of around up to 50 similar key keywords for seo given a a primary keyword.
3:39 And then basically what this does is it allows us to generate more keywords so that we could gather more different types of tweets to find more users, which you could, which we could then feed into this.
3:51 So the aim is we're kind of expanding out with a keyword research. So maybe start with, you know, one or two keywords and then you get a load of related keywords, and then you could then start branching out and finding all of the tweets and all of the users in a kind of semantically like relevant way.
4:08 This other prompt for GPT three is is it a personal story? So act as a social media strategic responsible for re reviewing competitor tweets with the sole aim to determine whether the capacity suite includes a personal story.
4:23 And then we do some simple classification and look inside that to see whether or not it is or not. And we've also got a separate prompt for rewriting the social media text.
4:34 So the first thing we're gonna do is we've had a look at like getting some tweets using just the, the native api with just Python.
4:42 So let's generate some recommended keywords first. So I'm gonna, I'm gonna comment out this code and we can just have a look at what this returns when I've when the, when the function gets back from GPT three.
4:58 And let's have a look at that. And you'll see that we've got a range of different types of words similar to Python, so like Python web framework, python data science.
5:07 So all of those could act as keywords that we may or may want to use. And then I'm not gonna run this piece of code cause it can take about a certain number of time, depending upon the number of days and the number of pages, parameters that you decide to choose.
5:21 But essentially what you're looking to get back is a bunch of tweets. And that should be a bunch of tweets for all of the different types of keywords that you've got in your recommendations.
5:30 At this time, I've only limited to five just for the sake of the tutorial. And then what we can then do is create a data frame based off that.
5:38 And then we've got a data frame of users and tweets. And you've got like the follow account frame count, listed count, et cetera.
5:44 And then what we want to do is we want to drop duplicates by the screen name. And then maybe, I don't know, maybe we wanna look at the ones who are actually quite popular and then maybe the look, look at the top 10 of those.
5:54 And now we've got a data frame of the top 10 of those with their screen names based on like their, you know, their follow account.
6:03 And, and so there we are. So cool. And then what we're gonna also do is then for all of these users, we're gonna scrape their tweets.
6:13 And I just wanna get 10 pages up to 10 pages of a hundred tweets for each user. And then what you'll end up with is we take that and save it into the user's tweet list.
6:22 And then we get all of those metrics out there. And then you'll see we get something called a user's tweets data frame.
6:29 And then inside of that we've then got a bunch of tweets against user IDs against text. And we've also got how popular it was in terms of was it retweeted, what's the favorite count and what's the retweet count as well.
6:42 And which is quite useful. So now we're gonna sort by the favorite count and you'll see if I now look at that data frame again, it completely changes and we start to see maybe some stuff of emojis, maybe some stuff that's a bit more interesting.
6:54 And so this is sort of by favorite count. And then what we can then do is, I've just limited it to the top 10 rows, but you could obviously do this for your entire data frame.
7:04 Is we then basically set a column called, is personal story called a false. And what we're doing here is we're looping over every row in the data frame, and we are then just updating that row ID with the T function to, to see whether it is a personal story or not.
7:21 And so if you have a look here, you'll see and I'll just show you this, that you can see that all of mine u users tweets, df.
7:30 So let's actually go and run this quickly. Cuz I, I actually just overwrite my data frame. So we actually do need to run this now.
7:38 So now it's going through and checking whether or not these are personal stories. And so if we now look at that, you'll see it doesn't believe that any of these tweets are personal stories, which means we could potentially rewrite all of these tweets and they probably still require some visual inspection from a human.
7:59 But the idea being is that we're just trying to, you know, throw out the ones that are like, you know, I went for a coffee last week with my friend and it was great kind of tweets.
8:09 But obviously you probably still have to look at them after they've been made. And then what we're doing is filtering out any of the ones that are a personal story.
8:18 So we want to say if the personal story is equal to false, then keep those ones. And if there aren't any of those, then we need to just bail on this point because we don't have any nonpersonal stories.
8:31 And then what we then do is we create a new column called Rewritten tweet. And then essentially we go through that data frame over again and essentially just write the text.
8:42 And so this one in action is then going through and rewriting each of these tweets to be unique and you know, completely unique.
8:51 And so this is something you could potentially do where, you know, a load of keywords or you know, a load of competitors.
8:58 And what you want to do is just put in, you know, a load of a load of their tweets and go, okay, are these personal stories?
9:05 Are these personal stories? Are these personal stories? And then the ones that aren't personal stories, we are then basically you know, creating new tweets from that.
9:15 And then after that you could give that to a low skilled worker potentially in, you know, in, you know, or, or maybe like a mid, mid-level worker who could then review those tweets and really clean out the junk and maybe even edit some of the tweets to make them make them viable.
9:31 And so this is something you would do as well. So I think the, the process doesn't stop here. We still need to check the, like, the validity of these tweets, but this definitely does give us the ability to scale and get to the point where we've, we've got a lot more of the tweets coming through.
9:45 So hopefully this was useful. And if you let need any help or, or anything, just let us know.

What are the benefits of re-writing existing content?

Why should you setup competitor tracking scripts on social media?

Scaling social media content can be a challenge, but it is a necessary part of any successful digital marketing strategy. Content scaling involves creating a consistent flow of social media posts across multiple platforms in order to reach a larger audience.

How can we scale our social media content?

GOOLYBIB OFFICES – WEEKLY MARKETING MEETING

The content team is keen to review several months of reporting. However the data is spread across into multiple .csv files and it would take a very long time to manually merge them.

We have tons of content marketing data but it's all in separate csv files.
Please would you be able to automatically merge them so that we can review the data?

The benefit of automatically merging CSV files with pandas is that it can save time and effort. By using pandas, you can quickly and easily combine data from multiple CSV files into a single data frame. This makes it easier to analyze and visualize the data, as well as allowing you to quickly make changes to the data set. Additionally, many pandas functions are optimized to work with CSV files, making them a great choice for working with this type of data.

Automatically Merging .csv Files In Python

0:00 Alright, so the boss has just sent us a bunch of CSVs and we've got over a thousand CSVs inside of this data folder.
0:08 And so what we're gonna look to do is to automate reading this in and then outputting it and as a concatenate results.
0:16 So we've got this script here, which does the work for us. You can technically upload your CSVs in a data folder in here, but it might take a while.
0:27 So another approach that I'd recommend is basically going and doing file download, downloading this as a Python script, putting it on side of your desktop, and then on your desktop, just have the data folder there, right?
0:42 And so I can now go into how to combine a files a thousand csvs.py and you can see that we've got this automatically generated python file.
0:54 And so we can have a look at what's, what's happening here. So we're first importing panders and the operating system, and we're getting the current working directory and then a touching data to that.
1:04 And so what we are now doing here is looping over the data folder, and if the end of the file contains csv, then we are returning that.
1:13 So we've got a list of CSV files and we can even make this more explicit by calling it CSV files instead.
1:19 As well as that also notice how we're creating a list to store all the individual data frames. If you did have an error with one of your CSV files, you could for example, wrap that of a try and accept and then work out why these things are happening.
1:33 But that might be something you decide to include inside of the script.  But in this case, we're just gonna assume that all of the csv reads using pandas into that data folder with the file name.
1:45 It's gonna actually work. And then we use this PD dot con command, which concatenates all of the data frames together.
1:53 We can then do things like print the shake for the data frame, print the first five rows, print the first five last five rows.
1:58 And then as well as that we also want to output as a csv, right? And we can do that just by doing two csv.
2:07 And then we've got this combined file, right? And so what you can do is you can go to a terminal, you'll obviously need Python installed for this, and you can just run Python three.
2:16 And then how to combine this csv. And then you can see now we're sort of running the script and notice how we added on.
2:26 And then we've got a file that contains this number of rows. And you can see here if we look at this combined file, we have indeed got a large CSV file with all of the data in it.
2:38 It would also be possible to just do this in the current working directory. So we could, for example, run our script in the desktop directory.
2:47 And then instead of including the data folder, imagine you had all your CSVs not in a folder, but they were inside of just the, the current working directory where you're running the script.
2:57 Then you could just do this, for example.  And you could probably even get away with just doing this OS dot get current working directory, right?
3:07 But in our case, we're assuming that all of the CSV files are inside of a data folder. So if you do have lots of CSV files, you could just place 'em in there, run this script, and then you'll get this combined file that would appear on your desktop.
3:20 So yeah, super quick and easy task to do, but it's definitely a good value add. I've seen it a lot where teams are spending a lot of time manually and copying and pacing multiple CSV files together.
3:32 And so you can kind of see the magic is happening here where we're like reading in all of these CSVs iteratively creating a list of pandas data frames, and then we are almost ho vertically stacking those data frames by using this pd.com command.
3:47 So it's a really powerful pattern and hopefully helps with your data analysis.

What's the benefit of automatically merging .csv files with the pandas package?

What types of errors/mistakes might you experience whilst using the pd.read_csv() command?

Are you ready to take your data wrangling skills to the next level? Learn how to easily combine 2000 CSV's in Python.

Combining 1000 csv files with Python

LeftMedia Headquarters - Pre-Meeting Banter

You're in the LeftMedia headquarters for the pre-meeting banter. You're a part of the team that will be using LangChain to summarize large documents. You've heard of the power of LangChain, PyPDF, and recursive text splitter, and you're excited to learn more.

Have you guys heard of LangChain?
It's a powerful tool for summarizing large documents quickly and efficiently.
With the recursive text splitter and PyPDF, we can get the job done in no time.
Let's get started and see what this software can do!

Delve deep into the world of LangChain, learning how to leverage its capabilities to condense large documents into easy-to-digest summaries.
One of the key skills you will acquire is the use of the "map_reduce" chain type for summarizing voluminous documents.
Also it's possible to customize the summarization chain to suit different languages and specific documents. We'll teach you how to create a custom "map_reduce" chain for generating summaries in different languages, and customize map and reduce patterns as per the needs of specific documents. 

Automatically Summarizing with LangChain!

 So in this video, we're gonna cover how you can summarize large documents using Lang chain. So let's start by installing Lang chain And PI P W F if you don't already have it. 

  After installing those packages, what we're then gonna do is import a range of different packages from Lang chain and requests. So we're gonna import the chat models, OpenAI. We're gonna also import a document loader called PI PDF loader. that's going to allow us to load PDF documents directly into Lang chain documents. 

We'll also use one of Lang chain's most common text splitters called the recursive text splitter, And we'll load in something called a load summarized chain function, as well as that we're going to import requests and we'll be going and getting a marketing book called principles of marketing. 

PDF. we're gonna just download that and store it on the local file system with the requests. As after we have downloaded the PDF, what you are then going to do is you're going to use a recursive character, tech splitter. Which will recursively split across a range of different separators. 

and it will try and keep within a specific size. So there are a couple of different parameters that you can choose with the recursive text splitter. One that's quite common is using something called the chunk size. And the chunk size is where you're defining how large your chunks are. And you can basically. determine what size, the chunks that you would like to have. and then, by default, all of the lo the documents that you create will have that size in terms of character length. 

You'll see here that we're loading in the PDF and we're then splitting it. so we're doing loader load and split. And then if we have just a brief look here at the pages, you will see. That we now have these pages, which are basically line chain documents, and it's got some metadata about what the source of it is. And the page of it is. 

also notice how we've got some of the page content here, so you can see the first page. is, doesn't have much content. And then if we start to look at some of the other ones, we can see that this book is produced by the university of Minnesota. what we want to do is we want to load in our chat model as an L L M. and this is important because we're going to use this in the various functions. So what you're gonna do is you're going to import that chat open AI. Remember that if you do. need to set an API key. you will have to set that here. so the way that you can do that and I'll leave this in the code would be to use the OS package and then you could do os Enron. and then we'll put the open AI. API key. And you will add your API key here. And then that would basically mean that this model is then authenticated, uh, so that you can easily call open AI. You'll see that the chat model by default uses GT 3.5 turbo, and this will be you know, upgraded as more, more and more models. Roll out. 

Um, we're gonna use a function today called load summarized chain. And essentially what this does is it takes in an L L M a chain type. So that could be stuff. Map map reduce. there's ones that are quite important. I personally find that map reduces very good for large documents. And essentially what happens in MapReduce is you can think of MapReduce being, you will do an operation on each individual document, and then once you've got all those documents, 

you will then use a reduce pattern on the, all of those documents. So you could have a hundred documents you would create a hundred summaries, and then you would have a reducing pattern that would then recursively reduce those a hundred documents into a final summary. the way that we can load this up is by using load summarize chain, the l lm And the chain type. and in this case, we're passing in map underscore reduce.  this one in particular to do the whole 400 pages of a book. that took about 30 minutes. 

so it does take a lot of time to run a large summarization chain. Um, however, this is kind of the summary that you can see, and it says this passage covers a range of topics related to marketing including defining marketing, strategic planning, consumer behavior. So we've got a really nice high level summary after running that summarization chain on the entire p d f of the book. 

Now I think it's worthwhile just seeing it in action. So if we just have a look at like, you know, the, the, 10 pages and running a summarization chain, You'll see it's taking a bit of time and what's going on underneath the hood is it's running that map, produced pattern across a range of different documents for you. 

And essentially getting summaries of each of the individual pieces. And then reducing that back into a single l l m response, which you'll then get back as a. summarized output. Uh, so we're just gonna see how long this takes here. We're currently at about half a minute. So let's actually just see what's come back now. So we've got, various marketing concepts as marketing segmentation, targeting planning, advertising. It's designed to help individuals effectively promote products and services. Cool. So it's very easy for you to, you know, do a summarization chain on any type of  document. and so essentially what we've got here is we've got this l l m, we have the chain type, and then we are also passing in, these pages, which is a list of documents. so now that you can sort of see that running in action, I think it's important for us to take a step back and say, well, maybe you want to do a summary in a different language, or, you know, maybe you've got something that you need to really specifically do at every stage of that map or reduce pattern. 

this is where you can create a map, reduce chain, which is a custom chain. And so what you'll see here is we've got this map pattern here that says, given the following pages of a marketing book, generate a summary in Spanish, and we've got the pages here. Uh, and then you say given the following summaries of pages of a marketing book, generate a high level description of the book in Spanish, we've set up a map prompt that will map over the pages. One at a time, we also set up a reduced prompt that will. 

go over the summaries, then we'll reduce those. We set up two L l m chains and then as well as that, we have a list of documents and combining that into a single string. we also have the map produce documents chain, which takes in the map and then associate all of the documents, the individual documents with pages. And we also have the combined document chain here. So just in case we need to. 

Combine these, uh, that's kind of how that's working underneath the hood. Uh, and then, so that's part of the reduced section when we're doing that combined. So that's a chain  to use to combine results of applying l l M chains to documents. We then set that up with a map, reduced chain and we feed it in the map. reduced documents, chain. 

And as well as that, you can also attach a text splitter. And then essentially you just passed in your input text. So in this scenario here, you can see, we call our map produce chain, which is called map produce. And then we pass in our input text. And what we've done is I've looked at the top. hundred documents to start with. And then what we've done is extracted the page content, joined those altogether and ran that through a map produced pattern. But notice now that the actual text that you're getting back is not necessarily an English summarization across all of these first hundred documents, actually a Spanish. translation. So, you know, being able to specifically. change what happens at the map section of your summarization chains or even just what's happening when all the documents are getting stuffed in to get reduced. can give you the flexibility to really optimize your summarization techniques.

Did you know it's possible to easily extract key insights from voluminous text, transforming an entire book into a digestible summary with LangChain?

50 Content Courses

Courses - It's time to grow👇

Learn the skills to be a Data-Driven Marketer