Custom document extractor Batch Processing Request

Question

How to send batch processing request using Custom document extractor?

I tried using Jupyter Notebook by creating a cluster but the Python code didn't work. It's not showing any output whenever I run the code.

Answer 1

Refer to this documentation for how to send a batch processing request for any processor type and get the response.

Batch (asynchronous) requests let you send multiple documents in a single request. The input files must be stored in Google Cloud Storage. Document AI responds with an operation that you can poll for the status of the request. When this operation finishes, it contains a BatchProcessMetadata that points to the Google Cloud Storage bucket where the processed results are stored.

If the input files you want to access are in a bucket in another project, you must provide access to that bucket before you can access the files. See Cross-Project file access setup.

You can also refer to this codelab for more instructions.

https://goo.gle/3OVnmnO