How can I concatenate the output of all operations of a Text parser

Hello all!

I’ve been dealing with an issue all morning. I’m trying to concatenate strings from a text parser to provide them to GPT.

The text parser processes different links (sometimes 5, sometimes 15… it depends) and extracts information from these links. I want to provide all these different pieces of information to GPT so it can summarize them for me. However, currently, GPT is giving me a summary of each link one at a time, which is not what I intended. Is there a way to give it all the information at the same time from each bundle?

I tried using repeaters and text aggregators, but I cannot seem to find the solution.

Thank you in advance for your help! :raised_hands:

Every result (item/record) from a search/match module will output a bundle. To “combine” them into a single structure, you’ll need to use an aggregator of some sort.

Aggregators are modules that accumulate multiple bundles into one single bundle. An example of a commonly-used aggregator module is the Array aggregator module. The next popular aggregator is the Text Aggregator which is very flexible and has applies to many use-cases.

There are other types of aggregator modules, click the below links to find out more:

samliewrequest private consultation

Join the unofficial Make Discord server to chat with other makers!

2 Likes

Hello,

Thank you for your response.

I tried using the Array aggregator, which seems to fit what I was aiming to do. However, the messages sent to GPT keep going one at a time.

Here are some screenshots of the Array aggregator (I stopped it after one cycle because it kept sending messages one at a time)


This is because you have two Text Parsers. Each may need its own aggregator.

samliewrequest private consultation

Join the unofficial Make Discord server to chat with us!

1 Like

Hello,
The text parser just before this one extracts all the links from a website one at a time, so I shouldn’t aggregate them since I want the next text parser to select all of the information from each individual link. The goal of this process is to scrape a website, select each article from yesterday’s date, and send all of this to GPT so it can summarize it for me. Isn’t there a way to wait for the text parser to process all elements before sending them to GPT ?
Thanks in advance !

Yes, by using another aggregator. Try a Text Aggregator just before the OpenAI Create a Completion module.

samliewrequest private consultation

Join the unofficial Make Discord server to chat with other makers!

1 Like

Hey,
I tried a lot of different stuff but still nothing.

The “Create a completion” model keeps summarizing articles individually.


Thank you again for your time

You need a second aggregator for module [15].

samliewrequest private consultation

Join the unofficial Make Discord server to chat with other makers!

1 Like