How to use ChatGPT to generate product descriptions at scale

We wish extra high quality content material for our web sites, but it surely’s troublesome to supply sufficient. So how can we scale the content material creation course of, particularly for ecommerce websites with loads of merchandise?

If you happen to have been to pay for a copywriter to supply 1000’s of product snippets from scratch, you’d possible be out of pocket fairly rapidly.

What in the event you pay for 1,000 new product descriptions, however solely half of these merchandise reside one month later? Clearly, you want a sooner, cheaper strategy. That is the place ChatGPT will help.

ChatGPT’s native internet interface is absolutely useful and an awesome time-saver. 

But when we’ve got a whole lot or 1000’s of product descriptions to create, there’s a extra environment friendly method of utilizing ChatGPT with out copying and pasting prompts. Right here’s how.

Mass manufacturing of content material snippets: Scaling the output

When you’ve got an ecommerce web site, you would possibly want to produce product snippets utilizing information from a product info administration (PIM) system. 

Let’s say you’ve gotten the info on a spreadsheet.

We will use Excel formulation to concatenate (or be a part of, utilizing the “&” operator) information into wealthy prompts, prepared for ChatGPT. For instance:

Be aware that your method could require one or a number of “IF” statements. That’s as a result of your information could have holes in some areas. 

For instance, some merchandise could not have sure parameters (information inside sure columns) specified. You want your method to be versatile, and you’ll at all times ask ChatGPT that can assist you write the method.

As soon as your method is returning a immediate for every row (on this case, for every product), you possibly can copy and paste just a few of the generated prompts right into a phrase processor, even notepad. 

It’s good to spot-check just a few to make sure the textual content is sensible, even when some information objects have been lacking.

Upon getting verified that your Excel (or Google Sheets) method is producing the kinds of prompts that you really want, you possibly can ship just a few of them to ChatGPT (manually, utilizing the online interface) to see in the event you just like the outcomes.

The generated snippet(s) will possible require human editorial oversight, although you wish to get the AI to do as a lot of the work as doable. That’s why we engaged in such a deep “prompt-crafting” course of.

Blissful together with your preliminary prompts and responses? Good, then it’s time to maneuver on.

Fetching your new product content material snippets from OpenAI

So, you now have an inventory of merchandise (or different kinds of webpages) which you’d wish to generate content material for. 

On this instance, we’re going with a fictitious pattern of 100 merchandise. You now have an inventory of all of your merchandise (both separated by URL, SKU or another distinctive identifier). 

These merchandise even have assigned wealthy prompts which you’ve gotten generated. However ChatGPT’s internet UI is proscribed. So how will you ship these throughout ?

For this, you’re going to must get comfy with primary scripting and with dealing with API requests. You possibly can create an OpenAI API account to entry the ChatGPT internet interface. 

I put collectively a primary Python script for my company. Whereas I can’t share the script, I can assessment a few of the processes and documentation wanted.

Ought to I want to syndicate this script later, constructing it on marketing-accessible endpoints and applied sciences could be greatest. As such, I first produced an Excel sheet:

The sheet merely gives an space to dump objects for processing (recognized by some distinctive identifier within the “Merchandise Identify” column, on this case, product identify). As well as, the prompts to be processed will also be positioned right here. 

One other tab comprises parameter settings for the request. (You possibly can find out about all these via OpenAI’s documentation.) 

A few of these settings fine-tune content material creativity allowance, uncommon wording deployment, max token spend per request and even content material redundancy. That is additionally the place the OpenAI API secret is saved.

As soon as a sure button inside the spreadsheet is clicked, the Python script launches mechanically and handles the remaining:

First, the script defines the request / endpoint URL. After this, the script sends the request headers and the request information. 

Most parameters for the request header / information, will be tweaked inside the spreadsheet pictured beforehand. 

Lastly, the response textual content is obtained from OpenAI and logged inside the “information dump,” one other separate spreadsheet. 

I’ve three scripts for this deployment, although just one must run. I even have two separate spreadsheets, each of that are wanted.

As soon as the script resolves the entire queries, the entire snippets of textual content are saved right here:

Wanting on the above output, you could have some content material uniqueness considerations. 

Whereas the entire snippets start with the precise phrase (“Introducing the [product name]”), the produced content material will get extra numerous throughout the generated paragraphs. So, it’s not as dangerous because it seems. 

Additionally, there are issues you are able to do to try to make every generated snippet much more distinctive, corresponding to categorically asking the AI to generate distinctive content material (although you must be fairly agency and repetitive on this regard to get wherever). 

You may as well tweak the temperature and frequency parameters to regulate content material creativity and keep away from redundant language.

Weaving these applied sciences collectively (OpenAI’s API, Excel, Python), we will rapidly verify generated textual content snippets for all enter prompts. 

From right here, it’s as much as you what you wish to do with that newly processed information. 

I extremely advocate shifting it right into a format your editorial workforce can perceive. 

We’ve got considerably mitigated a lot of this by crafting very wealthy prompts. Nonetheless, you possibly can by no means make certain till you test the output.

ChatGPT output notes

Assuming that you just’re comfortable to work with ChatGPT, there are a few issues to bear in mind:

• Let’s speak about the fee. It is robust to present a value breakdown for utilizing OpenAI’s GPT-4 mannequin of ChatGPT through their API. It isn’t simply the enter phrase rely of the immediate or the output phrase rely. Pricing revolves across the AI’s “pondering time.” Extra complicated requests will use extra tokens and price extra (even when the enter / output phrase rely is diminished).
• Our check batch of 100 prompts from pattern information price us solely $1.74 to run and return. We generated 22,482 phrases of content material total. 22,482 phrases of content material for $1.74 appears good, however there’s rather more to contemplate.
• As a consequence of AI’s propensity to deduce, a human editorial course of remains to be essentially required (in our opinion).
• Nonetheless, utilizing this expertise does remodel a pricey from-scratch content material creation activity into a way more cost-effective content material enhancing activity.
• The info / AI specialist’s time for immediate crafting and operating scripts should even be factored in.
• On prime of inferring the place information is missing, AI may “creatively infer” issues. In our pattern information set, the AI determined to deduce the existence of a sizing information (clothes) inside the produced product content material. If no sizing information existed, that will look fairly foolish.
• All the time ship AI content material by means of a human editorial assessment course of for fact-checking, accuracy and (most significantly) further artistic aptitude.
• You possibly can additional automate ChatGPT by plugging in initiatives like Auto-GPT. These AI ‘brokers’ add extra lively processing and tasking energy to ChatGPT. Nonetheless, initiatives like this nonetheless want your OpenAI API key. And as a result of their infancy, they’ll chew up lots of credit earlier than they study to carry out duties to straightforward.

Scaling your content material creation course of with AI

AI can scalably produce numerous snippets of content material which might be match for objective with minimal intervention.

For long-form content material, it’s most likely nonetheless higher to make use of the interface and iterate the AI’s responses.