Strange Diffeence ... Claude vrs Claude in Gumloop

Get Help General Question
1

@Wasay-Gumloop have a look …
I upload a pdf to Claude via there website and get a reply.
I create a Gumloop with the File Reader to Ask AI with the same prompt … and then I do nt get a reply.
What is the difference?
D

image
image1920×1170 121 KB

2

Hey @Donna! If you’re reporting an issue with a flow or an error in a run, please include the run link and make sure it’s shareable so we can take a look.

  1. Find your run link on the history page. Format: https://www.gumloop.com/pipeline?run_id={your_run_id}&workbook_id={workbook_id}

  2. Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
    GIF guide

  3. Provide details about the issue—more context helps us troubleshoot faster.

You can find your run history here: https://www.gumloop.com/history

3

Hey @Donna – Can you share the run link please? You can find the run link on the https://www.gumloop.com/history page or through the Previous Runs tab on the canvas

4

https://www.gumloop.com/pipeline?run_id=be4oY2F6zE2Ji6Le9SaCdC&workbook_id=j8fXcvdppi9sNMXHgwB6Aw
Let me know if this works (strange case for me)

5

Thank you @Donna – The issue is that the File Reader can’t read drive links directly since it doesn’t have access to the drive credentials. if you view outputs of the file reader node you’ll see a bunch of static information.

Instead you can use the Drive File Reader node that can output the file object itself which you can connect to an Analyze Image node. Here’s the updated workflow: https://www.gumloop.com/pipeline?workbook_id=44s7Ntte7tdiQsg7CyHTtk&tab=1

Let me know if this makes sense and works for you. Additionally, I’d recommend giving this a quick read—it’s helpful for debugging flows and checking outputs from the run log: Run Log Documentation.

6

Thanks for answer and both links!

7

But @Wasay-Gumloop how do I then configure a flow where I can read all pdf’s from one folder? Normaly I would create a (sub) flow with Input’s and Output’s, and then a new flow where I connect e.g. a google sheet which links to the subflow (hope you understand … (you will ;))

8

And what is the difference between this case and mine … Google Drive Folder Reader isn't recognizing any PDFs - #2 by Gumloop_Bot
I thought we had the same problem …

9

@Donna – If you’re using a Drive Folder Reader node and want to send multiple PDF contents to the Ask AI node then you can use the Join List Items node to merge the PDF contents together. Eg: https://www.gumloop.com/pipeline?workbook_id=44s7Ntte7tdiQsg7CyHTtk&tab=2

10

This was a small issue with the node configuration which has been fixed.

11

I do not follow what you try to explain.

I have a folder with 150 pdf’s (with images). Every page needs to be pushed trough the Anale Image node (one by one) and then trough the Extract Data node.
If I look at your proposed solution you will put all pdf’s into one and then push it into the Extract Data node … that is what I do not understand …

12

Ah I see, so in that in case you don’t need the Join List Items node, you loop each file through the Analyze Image node → Extract Data node. Let me know if this makes sense and works for you :slight_smile:

13

This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.