I'm trying to create a flow which will extract information from a pdf file which has been uploaded to a sharepoint library. My flow is triggered 'when a file is created (properties only)' and also uses a 'get file content' step. When I use an AI model to 'extract information from documents', i get the following error. I have a feeling there is something wrong with the input in my AI step, even though it should just be referencing the pdf file in the sharepoint library. Is it referencing some metadata? I've tried using get file content using path and still get the same error. Any advice?
Action 'Extract_information_from_documents_1' failed: {"operationStatus":"Error","error":{"type":"Error","code":"InvalidPredictionInput","message":"Encountered an issue when
reaching Form Recognizer: InvalidRequest","properties":{"BackendErrorCode":"InvalidInferenceInput","DependencyHttpStatusCode":"400"},"innerErrors":
I'm using Power Automate for Desktop to read standard format PDF's pretty successfully, such as invoices and work orders. From there, your data is easy to access and put into specific variables to use downstream.
Check out Power Automate for Desktop. Pretty easy to get started.
------------------------------------------------
⭐ If this was helpful, please like and mark as a verified answer to help others find this too!
Thank you for your reply! To ensure a great experience for everyone, your content is awaiting approval by our Community Managers. Please check back later.