Change theme
Help
Press space for more information.
Show links for this issue (Shortcut: i, l)
Copy issue ID
Previous Issue (Shortcut: k)
Next Issue (Shortcut: j)
Sign in to use full features.
Vote: I am impacted
Notification menu
Refresh (Shortcut: Shift+r)
Go home (Shortcut: u)
Pending code changes (auto-populated)
View issue level access limits(Press Alt + Right arrow for more information)
Request for new functionality
View staffing
Description
This will create a public issue which anybody can view and comment on.
Issue raised for the Stack Overflow thread:https://stackoverflow.com/questions/70940619/send-pdf-instead-of-textsnippet-in-goole-automl-enrity-extraction
What you would like to accomplish: The customer is using Cloud Natural Language AutoML to extract entities from a PDF file. They have a trained AutoML model to which predictions are being sent. The requirement is to send PDF files for prediction from their local machine as a document but not a TextSnippet (constructed from raw text) nor send a document from GCS. The customer is using the Java client library.
How this might work: The customer will be able to send documents for prediction from their local storage instead of uploading them to GCS.
If applicable, reasons why alternative solutions are not sufficient: Currently, the REST API does not have the provision to send documents from local storage. Only GCS source is supported.