I have this flow where i search my rows in sheets to get urls & navigate to get the webpage and scrape the data using Open AI. I had asked it to give it to me in JSON Format using prompts.
After Parse JSON Module , the output bundle looks like this mixed with array & collection.
Sometimes all the property are in array format in the output bundle.
I thought Open AI output JSON was wrong, but JSON Validator said it’s correct.
I tried Data Structure in Parse JSON Module by mentioning property names , nothing occured.
I used Aggregator ,Set Multiple Variables , Get Multiple Variables to get the data from ParseJSON but ,I get the error “Collection cannot be converted or Invalid Parameter”
I’m new to Make.com , please guide me where I’m going wrong? If I figure out this only, I can move onto updating my row data.
Welcome to the Make community!
Combining Bundles Using Aggregators
Every result (item/record) from trigger/iterator/list/search/match modules will output a bundle. This can result in multiple bundles, which then trigger multiple operations in future modules (one operation per bundle). To “combine” multiple bundles into a single variable, 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 can apply to many use-cases like building of JSON, CSV, HTML.
Mapping a Specific Structure Into a Complex Field
The Array Aggregator module is very powerful because it allows you to build a complex array of collections for a later module’s field to map multiple items (collections) to it.
This is done using the “Target structure type” field in an Array Aggregator module.
Here is an example:
As you can see, the “Map” toggle on complex fields are used when you have an array. You can easily build an array variable to map to a future module’s field, by using an Array Aggregator module and select the “Target Structure Type” as the future module’s field you have mapped the array into.
Example
You’ll need a minimum of four modules:
This is just an example. Your final solution may or may not look like this depending on your requirements and actual input data.
The Dumpling AI module replaces all the in-between modules in your current scenario above.
To do this, you can try using the Dumpling AI “Extract data from URL with AI” module —
Scrapes and extracts structured data from a webpage with multimodal AI
For more information, see:
Examples of How to use Dumpling AI
For more information, see these Dumpling AI tutorials below, grouped by category:
YouTube & Videos
Image Generation
AI Agents & RAGs
Searching & Scraping
Other Data Extraction
Business & Social
Dumpling AI Tutorials
In short, Dumpling AI is able to replace several other paid services combined that cost more than itself, making it a noteworthy choice as the “multi-tool” of AI services.
How to Use
For more information on how to set this up, refer to these forum threads:
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
Thanks for your Advice , Your Alternate solution was not applicable to my scenario. Appreciate the solution.
I had Directly changed my prompts in my Open AI Module and given a strict formatting to confirm it applicable for make.com’s parseJSON to process it the way I want it.
Later I used Set Multiple Variables followed by Array Aggregator & was able to update my rows successfully.
3 Likes
