Skip to main content
253 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
0 votes
0 answers
143 views

I’m currently having an issue with my code — I’m using the REST API to train a Document AI model with the custom extraction type. I have already completed the following steps: Called the v1 process ...
Nor3soN's user avatar
  • 1
1 vote
1 answer
143 views

I am testing out Document AI's Expense processor using the provided Google Cloud client libraries in a few different languages (JavaScript, Python, and C++). I'm testing with a set of JPEG images ...
Jasen Chan's user avatar
  • 11
0 votes
2 answers
325 views

Following Google's documentation, I am trying to perform a Document AI OCR batch request (async), and I constantly receive an error. I tried both with gcs_input_uri and gcs_input_prefix. I can not ...
RanH's user avatar
  • 852
1 vote
1 answer
142 views

I get this error in my log-file each time I am trying to send a request to Google Document AI API: 403 Client Error: Forbidden for url: https://us-documentai.googleapis.com/v1/projects/230636727467/...
Stella Slad's user avatar
  • 11
-1 votes
1 answer
108 views

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 ...
jonah_w's user avatar
  • 1,030
4 votes
1 answer
152 views

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. ...
stu2's user avatar
  • 109
0 votes
0 answers
2k views

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 ...
AlexCT's user avatar
  • 35
0 votes
0 answers
130 views

As part of our workflow we invoke DocumentAI ProcessDocument API (v1) API from our back end and the code has been in place for over 6 months and running without any errors. In the past one week we ...
Charles's user avatar
  • 1
1 vote
0 answers
47 views

I am currently working on a project that utilizes the docai custom classifier. I have a question regarding the test dataset size limitations. As I understand, the current limit for the test dataset ...
Al Monteagudo's user avatar
  • 11
0 votes
1 answer
929 views

I was trying to analyze a contract using Microsoft's Document Intelligence Studio. All the pre-built models are working except for the contract pre-built model. I am getting error code: "...
Harsh Khewal's user avatar
  • 5
0 votes
1 answer
747 views

I’ve noticed that it’s possible to upload multi-page files to Document AI, such that all pages are connected to each other by being associated to the same file. My use case is invoice files that I ...
Yaniv Ben-Malka's user avatar
  • 57
0 votes
1 answer
595 views

I am using Document AI with a Custom Extractor. When I create a new Custom Extractor, it offers to manage my dataset. I expect that doing so will automatically create label names for the documents I ...
tmighty's user avatar
  • 11.6k
0 votes
1 answer
458 views

https://cloud.google.com/document-ai/docs/workbench/label-documents#labeling For google Document AI, what is a labeling instruction exactly? Is it a pdf where every label are annotated using a box? If ...
Max's user avatar
  • 1
0 votes
1 answer
195 views

I'm using Document AI to parse PDF files from one bucket and then save them as JSON in another bucket in GCS. However, Document AI creates a folder with a subfolder in my bucket. I've read a lot and I ...
c0nfusion's user avatar
  • 1
0 votes
1 answer
107 views

I've been using the document AI tool for a while and have quite a few documents labeled and just thought of a question: does the Number field type allow for decimals (ex: 0.3456) or does it only allow ...
pl8nt's user avatar
  • 49
0 votes
1 answer
126 views

I'm having issues with the API, there is no response whatsoever. I have created  the service account with the corresponding API key with its JSON file, however, I cannot seem to get any response when ...
Keagan Gilmore's user avatar
  • 1
0 votes
0 answers
161 views

How can I tell Google Document AI Enterprise OCR to always assume one column? My text (scans of old books) are always one column. However, due to layout, (lots of) whitespace, and inline figures, ...
SRobertJames's user avatar
  • 9,457
1 vote
1 answer
653 views

How can I use Google Document AI OCR to find the non-text images in a text document? I'm using Google Document AI Enterprise OCR to OCR images (scans of old books_, and it works well. The books have ...
SRobertJames's user avatar
  • 9,457
0 votes
0 answers
146 views

This may be a silly question but I've been annotating quite a few documents with the Google Document AI tool and have had this worry in the back of my mind. My task is to use Doc AI to extract ...
pl8nt's user avatar
  • 49
0 votes
0 answers
107 views

I have an app that uses Document AI to process PDFs and extract text from it. When I use the stable version but still is not accurate. The processed text seems to have its lines mixed up, not ...
Khaled Saleh's user avatar
  • 168
1 vote
1 answer
294 views

I am using a GCP workflow and eventarc trigger connected to cloud storage to have a document evaluated by Document AI when the cloud storage bucket receives it. The issue I'm encountering is, whenever ...
Lofton Gentry's user avatar
  • 333
1 vote
1 answer
268 views

GCP's Document AI is pre-processing images to remove things like skew. The bounding boxes it produces correspond to the pre-processed image, not the image sent to the API. I need to reskew them so ...
user19213041's user avatar
  • 11
0 votes
1 answer
513 views

I am trying to batch process a set of documents using Document AI and its Java SDK. My code is derived from the batch processing example for Java (seen here), but I have modified it to add more than ...
Filip Östermark's user avatar
  • 445
0 votes
0 answers
82 views

I'm currently working on a document AI project (with Custom Extractor) and have encountered a scenario that I'm unsure how to navigate. My training dataset of Shipping instruction documents consists ...
lht_18018's user avatar
  • 64
1 vote
1 answer
680 views

I’ve been experiencing an issue with the Google Cloud Document AI API in my Firebase Cloud Function that handles documents uploaded to Google Cloud Storage. The function triggers correctly upon PDF ...
HaZeust's user avatar
  • 13
1 vote
0 answers
370 views

I read this blogpost about the recently published Document AI - BigQuery Integration. I want to configure this setup completly using terraform. An important step in the blog post is the configuration ...
Brian's user avatar
  • 117
1 vote
0 answers
185 views

I'm trying to make a nodejs project to extract data from invoices using Cloud Document AI API. I have copied the code provided on google doc as follows: /** * TODO(developer): Uncomment these ...
Maurizio Liguori's user avatar
  • 11
0 votes
1 answer
126 views

I am following Google's official tutorial on setting up Document AI: https://cloud.google.com/document-ai/docs/libraries#client-libraries-install-java My POM file: <project> <...
SolidCloudinc's user avatar
  • 321
1 vote
1 answer
287 views

I have a scenario where I am uploading a local file to a Cloud Storage bucket, triggering a Cloud Function (xyz). Within this Cloud Function, I am performing a batch processing task using Google Cloud ...
Manish gupta's user avatar
  • 11
0 votes
1 answer
172 views

I'm currently working on a project that involves using the Google Cloud Document AI Client Library in my PHP application. However, I've encountered an issue with the library's namespace that's been ...
shoop79's user avatar
  • 1
0 votes
1 answer
405 views

I'm trying to use the document ai forms processor to get the rows of a table. When I upload a document, the forms processor does not get each line separately. It combines multiple lines into a single &...
mijaro's user avatar
  • 1
2 votes
0 answers
123 views

I am currently building a custom OCR extractor with Google's Document AI, my documents are usually around 8-14 pages long and I have created a schema across all possible pages. Using the defined ...
Cookie Monster's user avatar
  • 21
0 votes
2 answers
721 views

I have a Google Document AI Custom Extractor model trained and it works great when I test it in the cloud console but I'm struggling to get a sample python program to work. I've taken this sample code ...
Matt Reidy's user avatar
  • 37
0 votes
1 answer
804 views

I'm looking to find ways to remove header, footer text in a pdf with document ai, I couldn't find in any API documentation here I'm using OCR_PROCESSOR and tried to enable_native_pdf_parsing but there ...
Prany's user avatar
  • 2,131
0 votes
1 answer
187 views

I'm using Google Document AI OCR to extract the text from and image following this guide. I'm using this image: Test image This is what I'm doing: from google.cloud import documentai_v1 as documentai ...
galex's user avatar
  • 671
0 votes
1 answer
441 views

I am trying to use the Google DocAI Warehouse sample Python code and it looks like that the location parameter is always ignored and just assumes the 'us' location. My prototype project has 'eu' as ...
caoimhinmacg's user avatar
  • 11
0 votes
1 answer
222 views

I have dumped JSON files from DOCAI to GCP but each file is stored in individual folder, although they are in the same bucket on Cloud Storage. I am not able to iterate through the JSON files stored ...
Vedant Patil's user avatar
  • 1
0 votes
1 answer
947 views

I am trying the Google Document AI with a standard Form Parser. I processed a 60 pages PDF file and the OCR result returned entities for a first few pages and the rest of the pages do not include the ...
Emma's user avatar
  • 9,633
0 votes
0 answers
210 views

I want to understand how to train via code a document classifier using the Document AI API, but I haven't found relevant information in the documentation or code samples. I have defined an Invoice OCR ...
Kronchik X's user avatar
  • 23
0 votes
0 answers
505 views

I am currently working on a project involving Google Document AI, and I need assistance with removing documents from a Processor dataset using Python. I have tried various approaches but haven't been ...
Mikkel's user avatar
  • 318
0 votes
1 answer
198 views

I just train a custom extractor at Document AI and test it there and get the values for the tags that I created, but I was following the Sample Request for Python (here's the code sample) but I get no ...
Alberto Martinez's user avatar
  • 1
1 vote
0 answers
36 views

I am running some example custom processors to read values of governmental documents. Some of the values we are after have a single letter as value, for example on a passport "Gender" has a ...
Stefan Walther's user avatar
  • 71
0 votes
1 answer
588 views

We are integrating Google's Document AI into our document management system and require an automated solution to import and label PDF documents for a custom classifier processor's dataset. Is there an ...
Michael Maramzin's user avatar
  • 1
0 votes
1 answer
27k views

I am trying to process documents using Google's document AI. But there are some issues, which I am facing. I have created a service account, given all the necessary access, but I am still not able to ...
Akshay Malik's user avatar
  • 1
0 votes
1 answer
189 views

we are using gcloud document ai to parse invoices and we recently enabled the invoice type feature and relabeled all documents with the labeling feature. so that all invoices will have an invocie_type,...
Christian Schmitt's user avatar
  • 922
0 votes
1 answer
2k views

I'm trying to use the Python console to use the Document OCR processor to locally process a large amount of pdf documents (native and scanned) to extract the text and some metadata. The documents are ...
Vojta Partík's user avatar
  • 1
0 votes
1 answer
674 views

I am trying to upload a file directly to Google Cloud Document AI for processing. I am receiving the error 400 Request contains an invalid argument. [field_violations { field: "raw_document....
SeaSky's user avatar
  • 1,312
-1 votes
1 answer
982 views

I had a discussion with a female representative from Google Cloud sales. She claimed that ‘Document AI’ is now available as an on-premise solution. I have doubts about this claim. Can anyone confirm ...
Seyed Hossein Mirheydari's user avatar
  • 105
2 votes
1 answer
446 views

I created a training set for custom document splitter with a total 3803 docs and 158 labels. I checked with documents quota and limits and all my docs and pages are within the limits. When I run the ...
Services GitHub's user avatar
  • 23
2 votes
3 answers
724 views

I am creating a Custom Document Classification Processor in GCP's DocumentAI platform, and am trying to understand whether it is possible to assign a Document Type label to documents when importing ...
J L's user avatar
  • 440

1
2 3 4 5 6