The way to use ChatGPT to generate product descriptions at scale


We would like extra high quality content material for our web sites, however it’s tough to provide sufficient. So how can we scale the content material creation course of, particularly for ecommerce websites with loads of merchandise?

In case you had been to pay for a copywriter to provide hundreds of product snippets from scratch, you’d doubtless be out of pocket fairly shortly.

What in case you pay for 1,000 new product descriptions, however solely half of these merchandise dwell one month later? Clearly, you want a quicker, cheaper method. That is the place ChatGPT may help.

ChatGPT’s native net interface is admittedly useful and an important time-saver. 

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

Mass manufacturing of content material snippets: Scaling the output

When you have an ecommerce web site, you may want to produce product snippets utilizing knowledge from a product info administration (PIM) system. 

Let’s say you’ve the information on a spreadsheet.

Product data spreadsheet

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

Data Concatenate 800x395

Observe that your formulation could require one or a number of “IF” statements. That’s as a result of your knowledge could have holes in some areas. 

For instance, some merchandise could not have sure parameters (knowledge inside sure columns) specified. You want your formulation to be versatile, and you may all the time ask ChatGPT that can assist you write the formulation.

Product description prompt
Product description prompt 1

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

It’s good to spot-check a couple of to make sure the textual content is sensible, even when some knowledge objects had been lacking.

Spot check prompts

After you have verified that your Excel (or Google Sheets) formulation is producing the varieties of prompts that you really want, you may ship a couple of of them to ChatGPT (manually, utilizing the online interface) to see in case you just like the outcomes.

The generated snippet(s) will doubtless require human editorial oversight, although you need 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.

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

Get the day by day publication search entrepreneurs depend on.

Fetching your new product content material snippets from OpenAI

So, you now have an inventory of merchandise (or different varieties of webpages) which you’d prefer 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 generated. However ChatGPT’s net UI is restricted. So how will you ship these throughout all of sudden?

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

I put collectively a primary Python script for my company. Whereas I can’t share the script, I can evaluation 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 finest. As such, I first produced an Excel sheet:

ChatGPT checker

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

One other tab incorporates parameter settings for the request. (You possibly can study all these by way of 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’s saved.

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

Python script

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

Most parameters for the request header / knowledge, might be tweaked inside the spreadsheet pictured beforehand. 

Lastly, the response textual content is acquired from OpenAI and logged inside the “knowledge 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 all the queries, all the snippets of textual content are saved right here:

Final output

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

Whereas all the 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 unhealthy because it seems to be. 

Additionally, there are issues you are able to do to aim 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 anyplace). 

It’s also possible to 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 are able to shortly verify generated textual content snippets for all enter prompts. 

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

I extremely suggest transferring it right into a format your editorial crew can perceive. 

Now we have considerably mitigated a lot of this by crafting very wealthy prompts. Nevertheless, you may by no means make sure till you verify the output.

ChatGPT output notes

Assuming that you just’re completely satisfied to work with ChatGPT, there are a few issues to remember:

  • Let’s speak about the price. It is robust to offer a price breakdown for utilizing OpenAI’s GPT-4 mannequin of ChatGPT by way of their API. It is not 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 take a look at batch of 100 prompts from pattern knowledge value 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 way more to contemplate.
  • As a consequence of AI’s propensity to deduce, a human editorial course of continues to be basically required (in our opinion).
  • Nevertheless, utilizing this expertise does remodel a pricey from-scratch content material creation activity into a way more cost-effective content material enhancing activity.
  • The information / AI specialist’s time for immediate crafting and working scripts should even be factored in.
  • On prime of inferring the place knowledge is missing, AI also can “creatively infer” issues. In our pattern knowledge 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.
  • At all times ship AI content material by means of a human editorial evaluation 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 energetic processing and tasking energy to ChatGPT. Nevertheless, initiatives like this nonetheless want your OpenAI API key. And because of their infancy, they’ll chew up plenty 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.

Opinions expressed on this article are these of the visitor writer and never essentially Search Engine Land. Workers authors are listed right here.


Please enter your comment!
Please enter your name here