Notifications
Clear all
Topic starter
The objective is to map the output from OpenAI into Airtable fields. I have fields in Airtable named prompt1 through prompt30.
I am utilizing the OpenAI module to generate 30 prompts. My goal is to map each generated prompt to its corresponding field in Airtable. Here is the data received from my webhook:
The iterator then successfully outputs everything into separate bundles:
This is the output I received from OpenAI:
The problem is that regardless of my attempts with text parsers, iterators, or variables, I cannot seem to structure this data in a way that allows me to directly map prompt1, prompt2, etc., into their corresponding Airtable fields. I am completely stumped.
Posted : 10/02/2024 4:31 pm
Welcome to the callin.io community!
How are you then mapping it into the Airtable module?
You might need an aggregator, or not.
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.
Please provide the rewritten markdown content *it should be in the markdown format.
Posted : 10/02/2024 4:51 pm
Topic starter
Thanks for the quick response. I'm really struggling with this. I just can't seem to get the data into Bundle 1, Bundle 2, Bundle 3, etc., no matter what I try. Each prompt continues to be named "Bundle 1," which prevents me from mapping anything. I've even managed to get each prompt into a datastore, but I can't even retrieve that data!
Posted : 10/02/2024 7:08 pm
Everything is named “bundle 1” as they are within different operations. You will simply need to aggregate the results into a single array as previously suggested.
Posted : 11/02/2024 2:11 am
Topic starter
I attempted that, and it resulted in an empty array. It was consuming too much time, and after several days, I abandoned the effort. I believe callin.io could enhance its online tutorials and documentation. Ultimately, I passed the payload of 30 values into Lambda, separated them, and pushed them to different scenarios with filters for the existence of ‘promptX’. This is clearly a significant workaround, but I needed a solution urgently.
Posted : 11/02/2024 8:44 am