OpenAI file attachment

[edwardzev]

Your Task History ID

IjU3NjUwNTZmMDYzNjA0MzM1MjZmNTUzMTUxMzE1MTZiNTQzOTBmMzAi_pc

I am trying to build workflow that is triggered by an email parser, receive attachment url (invoice - which is pdf file with open text). Fetch details from invoice using openai, and stores it in airtable or any other spreadsheet.

I built an assistant. tested it in playground and the assistant analyze quite efficiently the uploaded file and returns needed details (invoice num, sum, etc)

Step1 - trigger=>attachment url
Step2 - upload file to assistant=>file id
Step3 - create thread=> thread id
Step4 - create message with attachment - here i have a problem. i can't get message created with file id, that contains pdf file, although it is obviously uploaded since I received file id.
Step5 - create run => status queued. Wait a bit
Step6 - list messages=>I get response that indicate that the assistant didn't really checked the uploaded file.

I am aware that the easier option is to retrieve text with the help of third party pdf parser like pdf.co, but since openai assistant easily retrieve data from the open base pdf, i want to make it available through the direct uploading of the file, and not by feeding the extracted text.

 

[ArshilAhmad]

Hi @edwardzev,

In the 'Create Message' action step, please enable mapping, then map the File ID enclosed within double quotes and square brackets, and see if that fixes your issue.

 

[edwardzev]

thank you for a prompt reply.
but it didn't really help.

 

[ArshilAhmad]

Please allow us some time to look into this concern. We will get back to you with an update soon.

 

[Preeti Paryani]

Hello @edwardzev,

Please try using the Create Message V2 (Beta) action instead of Create Meaasage and let us know if it works for you.

 

[edwardzev]

Thank you.
I tried. It returns "Invalid type for 'attachments[0].file_id': expected a string, but got an array instead."
My guess is that in TYPE field I chose TEXT (not image, not image url obviously) but seems TEXT also wrong. My guess.
Pls check screenshot.

 

[ArshilAhmad]

Could you please click on 'Re-Capture Email Parser Response' and capture a new file in the Email Parser trigger step? Once done, please let us know.

 

[edwardzev]

done

 

[ArshilAhmad]

Thank you for uploading a new file. Please allow us some time to review this concern. We will get back to you with an update shortly.

 

[Preeti Paryani]

Hello @edwardzev ,

It seems there have been changes made to your workflow, and as a result, we are unable to locate the OpenAI steps. We kindly request you to add these steps back so we can proceed with testing the issue.

Thank you for your cooperation!

 

[quantum.je]

Hi @edwardzev & @Preeti Paryani !

I follow exactly the same workflow and have tested it with both PNG and PDF files. However, I encounter an error message at the last step:

"Files were not found."

Could you let me know how I can help in return? I’m happy to conduct additional tests if needed.

Also, has this type of workflow (e.g., document analysis via OpenAI) already been implemented on Pabbly's side?

Thank you in advance for your support!

Access to my workflow : here

 

[Luv]

Hey @quantum.je

It appears the the API for OpenAI is not accepting the file URL from Pabbly or Google Drive. We would suggest hosting the file on any other application such as OneDrive or Dropbox and try uploading with the URL you get from the response.

Just use "Upload File" for Dropbox or OneDrive before the OpenAI step.

You can refer to the tutorials below -

Let us know if it works for you.

 

[quantum.je]

Hello @Luv !

Thank you for your suggestion!

I tested both Dropbox and OneDrive. I was able to upload the files, but I am unsure how to retrieve the correct link for OneDrive.

With Dropbox, I successfully tested the "Upload file to Assistant OpenAI" module, and it seems to work.

However, I still encounter the same error at the next step:

"Files [file-YL8QHZBbu1BveAFG9gjEff] were not found."

Could you provide further guidance on this issue?

Thank you in advance for your help!

 

[Luv]

Hey @quantum.je

Kindly allow us some time to look into this issue. Also, please capture a new email with attachment so that we can check the issue effectively.

 

[quantum.je]

new capture done !

 

[Preeti Paryani]

Hello @quantum.je,

We have escalated your concern to our technical team, and they are currently investigating the issue. We will keep you updated as soon as we have more information.

 

[quantum.je]

Thank you @Preeti Paryani for taking this issue into consideration. However, I must say I'm quite surprised that, with so many people using the platform and all the exceptional expertise around the project, no one has yet attempted to use ChatGPT with files.

I noticed in your signature that there are over 7,400 tutorials. Are there any tutorials specifically dedicated to advanced usage of OpenAI?

 

[Preeti Paryani]

Hello @quantum.je,

You can refer to the tutorial playlist below to learn how to use OpenAI:
OpenAI Tutorial Playlist

Could you please clarify what you mean by the "usage of OpenAI"? This will help us provide more specific guidance.

 

[quantum.je]

Hi @Preeti Paryani !
The ability to upload a file for analysis by ChatGPT is an extremely powerful feature, offering incredible and unlimited possibilities. It opens up new perspectives for advanced use cases, making tasks like data processing, document analysis, and creative workflows much more efficient and accessible.

If I were in the position of the Pabbly team, I would invest significant resources into this feature, as it enables so much and could truly revolutionize how users interact with and benefit from the platform.

 

[Preeti Paryani]

Hello @quantum.je,

We understand the importance and potential of the Upload a File action in OpenAI. Please note that the issue related to this action has already been escalated to our technical team.

As soon as we receive any updates regarding this issue, we will inform you promptly.

Thank you for your patience and understanding!