I’m encountering a frustrating issue with the GPT Vision module: it seems to only process a single image correctly, even though I need to send multiples. I’m using a HTTP module to fetch images and then im trying to map their data outputs.
The Problem:
The GPT Vision module appears to only work when provided a single image data/file.
I need to send multiple image data files in a single request.
I’ve tried all mapping approaches I can think of, but none seem to work.
What I’ve Tried (and failed):
Direct Mapping of HTTP Data: Mapping multiple HTTP “data” outputs directly to the Vision module doesn’t work.
Aggregating multiple files into a single data field: I attempted this, and this also does not work.
I’ve been working on this for days now and just can’t get it to work. I found this YouTube video from another support thread here, but I’m none the wiser: https://www.youtube.com/watch?v=pDH3Y_k4wRU
This really shouldn’t be that difficult since it’s just simply forwarding three images to a specific module. Still, at least 10-12 working hours have gone into this so far with no results, so now this thread is my last hope that someone can help me.
I will also attach a screen recording since it might help. Thanks so much to everyone who helps me in advance!
To allow others to assist you with your scenario, please provide the following:
Relevant Screenshots
Please share screenshots of your scenario, any error messages, relevant module fields, and relevant filter settings. It would really help other community members to see what you’re looking at.
You can upload images here using the Upload icon in the text editor:
Scenario Blueprint
Please export the scenario blueprint file to allow others to view the mapped variables in the module fields. At the bottom of the scenario editor, you can click on the three dots to find the Export Blueprint menu item.
Please provide the output bundles of the modules by running the scenario (or get from the scenario History tab), then click the white speech bubble on the top-right of each module and select “Download input/output bundles”.
Save each bundle contents in your text editor as a bundle.txt file, and upload it here into this discussion thread.
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 even if they do not use the external service.
By providing these details, it will allow others to assist you better.
