280 questions
0
votes
0
answers
24
views
Custom Trained Versions in Google Document AI Suddenly Failing to Deploy
I have been successfully using custom-trained versions in Google Document AI for some time. However, recently, all my previously functional trained versions have stopped working and cannot be deployed....
- 727
0
votes
1
answer
34
views
How to pass a raw document to a processor instance in Google Document AI?
I'm just starting to experiment with Google Document AI using the PHP client library, but see the sample code documentation for this is for version 1, which does not work in the current version of the ...
- 21
0
votes
1
answer
31
views
Google Document AI value types Money vs Currency
I noticed this when I was working on a Schema for a custom processor it seems that there are two different options for money I'm not sure what the difference is. or to put it another way when should I ...
- 1,911
0
votes
1
answer
61
views
DocumentAI detect if image contains non-text visual elements in it
Most of my target images contain only text elements, which is expected, since my main purpose is to extract text from them. But some of the target images contain non-text visual elements (actual ...
- 1,032
0
votes
0
answers
40
views
Document AI not returning tax_rate
I am trying to use the Invoice Parser Processor of Document AI. The problem is that I am not getting the tax_rate field in the response when I use the API in my code. However, when I upload the same ...
0
votes
0
answers
34
views
Doesn't contain any ground-truth entity defined in the Schema
while training a Google Document Classifyer, the training failed with the below errors.
On inspection of the error, I noticed that all failed documents belong to classification lables which have been ...
3
votes
1
answer
72
views
With Custom Extractor, Python API view of schema does not provide access to EntityTypes; it should according to docs
The API documentation shows that the DocumentSchema has EntityType children which should contain details of all fields in a Custom Extractor. I am able to obtain the DocumentSchema as expected. ...
- 99
0
votes
0
answers
38
views
Error code 13 training with document processor
Processor type: Custom extractor
I'm having the following error when trying to train a document ai processor:
{
"code": 3,
"message": "Invalid document.",
"...
0
votes
1
answer
81
views
How to use DocumentAI to extract data and bring the results to BQ using BQML?
I built a custom extractor in Document AI.
Deployed version : pretrained-foundation-model-v1.3-2024-08-31
# Create a remote model to register your Doc AI processor in BigQuery.
CREATE OR REPLACE ...
0
votes
0
answers
25
views
Custom Classifier Failed to refresh dataset stats
I'm training a Custom Classifier in Document AI. Worked fine and I had a Dataset with about 4000 documents. I trained multiple versions and they are running well.
But now I'm not able to see these ...
0
votes
1
answer
29
views
ValueError: Protocol message OcrConfig has no "premium_features" field when use DocumentAI
I'm using Font-style detection in Google's DocumentAI using Python:
"premium_features": {
"compute_style_info": True
},
But it gives the following ...
- 1,032
0
votes
0
answers
2k
views
Document AI - Processor location issue [duplicate]
I'm using a Mac and I have created a simple Document AI processor on the Google Cloud Platform (PDF splitter). This processor was trained, tested and deployed.
I'm now desperately trying to make use ...
- 35
0
votes
0
answers
212
views
Google Document AI Fine Tuning is taking forever
I am using a foundational model "pretrained-foundation-model-v1.1-2024-03-12" to train a custom extractor on Google Document AI. I've set the epochs to 300 and Learning Rate to 1 (range is ...
- 13
0
votes
0
answers
104
views
DocumentAI OCR Error: Invalid Document Content
I am calling DocumentAI OCR batch processing from Workflows generally quite successfully, however, I occasionally get the following error:
{
"caughtError": {
"message": "...
- 101
0
votes
0
answers
201
views
How to improve the checkbox detection on gcp documents ai?
We're using google OCR to read PDF or Images that are Loan Estimates.
We're defining multiple fields such as loanTerm, loanPurpose
loanPurpose
but we're also labeling multiple checkboxes that can be ...
- 1