GPT Stops Processing After 5 Rows in Excel Data Flow – Need Help to Process All Rows

Hi guys!

I’m encountering an issue with a GPT I’ve created. Here’s in a nutshell what it does:

  • Receive data in an Google Sheets/Excel file (let’s say the file has 50 lines)
  • Clean data
  • Send data to an API and get back new data
  • Write a json body for me to copy paste into Postman

The issue is that it will only process 5 lines and then think the job’s done. Or even sometimes, it says that it will process the rest in the background and stops its answer. Obviously it won’t do such thing haha.

How can I make it work using instructions?

1 Like

I am having the same problem. To add on to what Julien has said, I ask it to re-run and it acknowledges it made a mistake and tells me “I’ve incorrectly only ran on the top 5 records, i’ll go back and fix it”

Also it seems to not always attach the export excel file correctly. It will tell me “File cannot be found”

Are you using Responses API or Chat Completions API?

When you say “clean data” what do you mean?

GPT’s have trouble counting. What model are you using? You say “a GPT I’ve created” what does that mean? You mean you saved a prompt in custom GPT, but are you accessing on Webchat app or using the API?

Usually you just say,

I’m going to send you an entire file, perform this process, and return the entire file to me. Ensure that you include 100% of all existing file data, performing only the necessary modifications, and otherwise not removing/deleting any data."

Also, sometimes GPT is better at doing file modifications (especially with large data set) as a providing only-the-set-of-changes. It’s pretty bad even with code files (which look more like natural language than excel files/database sets) at sometimes saying things like "and here, do that other huge thing we talked about doing, I didn’t do it!

The best success I’ve had is either with custom formatting or standardized script interfaces (“patch” utility scripts (i.e. diff files), “ed scripts”), or using other kinds of structured output to essentially say “change cell X to content Y, overwrite cell Z with content X,”, etc. And then you use your middleware to process the response and actually perform the operation.

Rarely will you succeed with getting GPT to provide you back full datasets/large docs with all content intact and only modifications performed. But it will do well if you have a format by which it can provide only the necessary modifications.

Also if you are doing “data cleanup” on an excel file, you most likely should just use native excel scripts/etc. to perform data migrations/formatting changes/“clean up”.

GPT could help you generate those scripts if that’s the kind of cleanup you are doing (i.e. like removing stray whitespace characters, reformatting, doing regular expression extraction, etc.). These are normal coding tasks - NOT gpt tasks (but GPT can give you the code!).