Hey guys, I’m building a financial newsletter automation in Make.com. After a subscriber signs up (test subscriber data from Airtable), I run their info through a GPT module that generates a ticker-based news query. The GPT output correctly includes a “Clean Tickers: …” line at the end (with the ticker symbols). I then use a Text Parser to extract just the ticker symbols. However, even though the correct line exists in the output, the Text Parser fails with “BundleValidationError: Missing value of required parameter ‘text’.” I’ve double-checked that the GPT output has the Clean Tickers line. Has anyone experienced the Text Parser missing text that is clearly present? Could it be related to formatting issues like line breaks, hidden characters, or parser settings? Any advice is appreciated.
Welcome to the Make community!
You have not yet provided sufficient information to demonstrate the problem that would allow us to reproduce the scenario and any error(s).
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. Scenario Blueprint
Please export the scenario blueprint. Providing your scenario blueprint file will allow others to quickly recreate and see how you have set up the mappings in each module, and also allows us take screenshots or provide module exports of any solutions we have for you in return - this would greatly benefit you in implementing our suggestions as you can simply paste module exports back into your scenario editor!
To export your scenario blueprint, click the three dots at the bottom of the editor then choose ‘Export Blueprint’.
You can upload the file here by clicking on this button:
3. Output Bundles of Modules
Please provide the output bundles of each of the relevant modules by running the scenario (you can also get this without re-running your scenario from the History tab).
Click on the white speech bubbles on the top-right of each module and select “Download input/output bundles”.
A. Upload as a Text File
Save each bundle contents in a plain text editor (without formatting) as a bundle.txt
file.
You can upload the file here by clicking on this button:
B. Insert as Formatted Code Block
If you are unable to upload files on this forum, alternatively you can paste the formatted bundles.
These are the two ways to format text so that it won’t be modified by the forum:
-
Method 1: Type code block manually
Add three backticks
```
before and after the content/bundle, like this:```
content goes here
``` -
Method 2. Highlight and click the format button in the editor
Providing the input/output bundles will allow others to replicate what is going on in the scenario, especially if there are complex data structures (nested arrays and collections) or if external services are involved, and help you with mapping the raw property names from collections.
Sharing these details will make it easier for others to assist you.
I’m working on a scenario where GPT (via OpenAI module) generates a structured output, and I need to extract a specific line from it to update a text field in Airtable.
Specifically, the GPT module ends its response with a line like this: Clean Tickers: TSLA, AAPL, QQQ
I’m using a Text Parser module to extract that line using:
- Text to parse: {{14.choices[0].text}}
- Regex pattern: Clean Tickers:\s*(.+)
The scenario runs successfully — no errors — but the expected field in Airtable remains empty. I’ve confirmed the GPT output contains the expected line, and the regex pattern seems valid.
Any idea why the text isn’t being parsed and passed forward to Airtable? I’ve tried moving the parser to different points in the scenario and confirmed module 14 is returning a valid response.
Thanks in advance!
Looks like the Text Parser module isn’t outputting any bundles.
If you need further assistance, 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. Scenario Blueprint
Please export the scenario blueprint. Providing your scenario blueprint file will allow others to quickly recreate and see how you have set up the mappings in each module, and also allows us take screenshots or provide module exports of any solutions we have for you in return - this would greatly benefit you in implementing our suggestions as you can simply paste module exports back into your scenario editor!
To export your scenario blueprint, click the three dots at the bottom of the editor then choose ‘Export Blueprint’.
You can upload the file here by clicking on this button:
3. Output Bundles of Modules
Please provide the output bundles of each of the relevant modules by running the scenario (you can also get this without re-running your scenario from the History tab).
Click on the white speech bubbles on the top-right of each module and select “Download input/output bundles”.
A. Upload as a Text File
Save each bundle contents in a plain text editor (without formatting) as a bundle.txt
file.
You can upload the file here by clicking on this button:
B. Insert as Formatted Code Block
If you are unable to upload files on this forum, alternatively you can paste the formatted bundles.
These are the two ways to format text so that it won’t be modified by the forum:
-
Method 1: Type code block manually
Add three backticks
```
before and after the content/bundle, like this:```
content goes here
``` -
Method 2. Highlight and click the format button in the editor
Providing the input/output bundles will allow others to replicate what is going on in the scenario, especially if there are complex data structures (nested arrays and collections) or if external services are involved, and help you with mapping the raw property names from collections.
Sharing these details will make it easier for others to assist you.
Hi again — thank you for helping me out so far.
I’m following up with two specific screenshots to clarify the issue.
The GPT module (14) successfully outputs a line like: Clean Tickers: TSLA, ETH
I then pass that to a Text Parser (Advanced) module (18), using this regex pattern:
Clean Tickers:\s*(.+)
The module logs show that the input and pattern match are both successful. However, the extracted value is not passed into my Airtable Update module (17). The Clean Tickers field remains blank in Airtable, even though the run reports as successful.
Screenshots:
- Pipeline layout showing parser directly before Airtable update.
- Module inspector showing all Text Parser settings and mapping from 14.Choices[0].Text.
Any idea what’s breaking the value handoff, or if this is a nuance with test data not being processed the same way?
Quick refresher the text parser is supposed to pull the (Clean Tickers: TSLA, ETH) from the gpt module then send it to airtable which is supposed to update a field in airtable with those tickers now I also do have the gpt module outputting some other thing as well but this part (Clean Tickers: TSLA, ETH) is the last instruction and it does it I just don’t know why the text parser is not picking it up by saying it does.
Appreciate any help!
Welcome to the Make community!
You have not yet provided sufficient information to demonstrate the problem that would allow us to reproduce the scenario and any error(s).
This includes a screenshot of the module fields, and sample text that is being matched.
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. Scenario Blueprint
Please export the scenario blueprint. Providing your scenario blueprint file will allow others to quickly recreate and see how you have set up the mappings in each module, and also allows us take screenshots or provide module exports of any solutions we have for you in return - this would greatly benefit you in implementing our suggestions as you can simply paste module exports back into your scenario editor!
To export your scenario blueprint, click the three dots at the bottom of the editor then choose ‘Export Blueprint’.
You can upload the file here by clicking on this button:
3. Output Bundles of Modules
Please provide the output bundles of each of the relevant modules by running the scenario (you can also get this without re-running your scenario from the History tab).
Click on the white speech bubbles on the top-right of each module and select “Download input/output bundles”.
A. Upload as a Text File
Save each bundle contents in a plain text editor (without formatting) as a bundle.txt
file.
You can upload the file here by clicking on this button:
B. Insert as Formatted Code Block
If you are unable to upload files on this forum, alternatively you can paste the formatted bundles.
These are the two ways to format text so that it won’t be modified by the forum:
-
Method 1: Type code block manually
Add three backticks
```
before and after the content/bundle, like this:```
content goes here
``` -
Method 2. Highlight and click the format button in the editor
Providing the input/output bundles will allow others to replicate what is going on in the scenario, especially if there are complex data structures (nested arrays and collections) or if external services are involved, and help you with mapping the raw property names from collections.
Sharing these details will make it easier for others to assist you.