Text aggregator doesn't aggregate

How To
1

Hello everyone,

I’m having trouble setting up the Text Aggregator module in my Make scenario, and I’m hoping someone can help me figure out what’s going wrong.

:wrench: Goal:

I’m extracting **text content from several URLs using the HTML Extractor, and I want to aggregate all the extracted text into one single block of text. The idea is to send this aggregated content to OpenAI (ChatGPT) as part of the prompt.

:warning: Problem:

Instead of aggregating all the extracted text into one combined block, the Text Aggregator module outputs the texts separately (like an array of individual items or multiple strings), rather than one big concatenated string.

:paperclip: What I’m doing:

  • I extract HTML content from multiple URLs.
  • Then I use the Text Aggregator module, expecting it to combine everything into a single text string.
  • But it just outputs each piece of text independently, instead of merging them into one.

:pushpin: What I need:

A single string, something like:

Text from Page 1. Text from Page 2. Text from Page 3.

…so I can insert it into my OpenAI prompt for analysis/summarization.

:camera: Blueprint:

Here’s the blueprint of my scenario:
blueprint.json (44.3 KB)

:brain: Questions:

  • Am I missing a configuration step in the Text Aggregator ?
  • Do I need to use a Set Variable or a Text Parser to clean and join the results?
  • Is there a better way to merge all the extracted texts into one string?

Thanks in advance for your help!

1 Like
2

Welcome to the Make community!

To allow others to assist you with your scenario, please provide the following:

1. Relevant Screenshots

Could you please share screenshots of your full scenario? Also include screenshots of any error messages, module settings (fields), relevant filter settings (conditions), and module output bundles. We need to see what you’re working with to give you the best advice.

You can upload images here using the Upload icon in the text editor:

We would appreciate it if you could upload screenshots here instead of linking to them outside of the forum. This allows us to zoom in on the image when clicked, and prevent tracking cookies from third-party websites.

2. Regex101 example

Could you go to regex101.com, paste in your Pattern at the top and paste a complete/full example text you are trying to match from below it?

Then, save the regex example and share the link with us here.

This will allow others to assist you here with your pattern. Thanks!

3

Hey Mohamed,

1st - immediately iterating an aggregator is a pointless action that only wastes operations, delete the two modules and map the URL coming from Apify directly in the Get a File module.

2nd - you always aggregate the module that is producing the extra bundles, in your case that is NOT the text parser, but the iterator. After you remove the iterator, that would be the Apify module.

4

Hi @Mohamed_Necib

To get the Text Aggregator module to work as expected, make sure you’ve correctly set the source module in its configuration.

Since you’re extracting HTML content from multiple URLs, the HTML Extractor is producing multiple bundles—one per URL. The Text Aggregator needs to know which module it’s supposed to aggregate the data from, and it will then combine all the text into a single string.

If you’re using an Iterator to process a list of URLs, and each URL leads to a separate HTML extraction, then the Iterator is generating multiple bundles. In this case, you should set the Iterator as the source module in the Text Aggregator settings.

Once that’s correctly set, the module will merge the content into one block, like: Text from Page 1. Text from Page 2. Text from Page 3.

Best regards,
Msquare Automation
Platinum Partner of Make
@Msquare_Automation

5

Hi @Mohamed_Necib
Attaching a sample workflow.

image
image1782×413 83.2 KB

Best regards,
Msquare Automation
Platinum Partner of Make
@Msquare_Automation