False positives when extracting math formulas
In my python script detecting math formulas for an AI chat app, I am using Azure Document Intelligence function "begin_analyze_document" with the "formula" feature. Sometimes it is returning false positives - which are clearly not…
OCR issues extracting math formulas with Document Intelligence
I want to extract mathematic formulas from scientific/ engineering PDF documents. The extracted formula values are later injected as LaTex math code back into the extracted text which is then provided to a GPT model used by a Chatbot AI app. With Azure…
Document AI table confidence
Hi, I would like to know if we can extract or get the confidence value of the table. I can get the confidence value of the fields but I had a hard time figuring out if we can get the confidence of each table rows. I used this code but it will only get…


Does Azure Document Intelligence C# SDK support add-on query field?
Hi, I am trying to use the query fields feature using the Azure .NET C# SDK but I am getting below error on calling the method. Could you please help me. Error details - ErrorCode: InvalidArgument Content: …
How to batch create a searchable pdf using azure document intelligence python API
Hi All, I have stored some PDFs in Azure Blob storage and I am trying to batch OCR these documents while also creating a searchable PDF. Unfortunately at the moment I'm getting a file with the following extension "filename.pdf.ocr.json" which…
Document Text extraction model
I have created a model for "Document Text extraction" under Azure AI foundry. I would like to use the model that i have created in my python code. How do i use the model to extract the fields from the files?
Can build content for custom classifier be specified using generic urls?
I’m a bit confused by this APIdocumentation regarding how to train a custom document classifier in v4.0. The ClassifierDocumentTypeDetails specifies the build content files, and has 2 possible formats (azureBlobSource and azureBlobFileListSource) which…
Inquiry about Preprocessing Steps in Azure AI Document Intelligence (Prebuilt Receipt Model)
I am currently working with the Azure AI Document Intelligence service, specifically the Prebuilt Receipt model, and I have a question regarding the preprocessing steps performed automatically by the service. Could you please clarify the following: …
Support for Document Intelligence containers API Version v3.1 and higher
Hello MS Team, I would like to know if there is a timeline for container support to be available for Rest API Versions v3.1 and v4.0. As stated here…
How to publish the model created in Azure Document Intelligence? Model is created but not able to find option to publish it.
How to publish the model created in Azure Document Intelligence? Model is created but not able to find option to publish it.
Issue with Mandatory Query Parameters Being Added to Template Parameters in Azure API Management (APIM) When Importing OpenAPI Specification
Hi everyone, I’m facing an issue while adding an API to Azure API Management (APIM) using an OpenAPI specification. Specifically, all mandatory query parameters are being automatically added to the template parameters in the operation URL, which is…
Document AI get table values
Hello, I have a field table in my model. How can I get their values? I can get the values of the string fields just fine I have this code but it only gives the value of string fields. The Items field is blank. Am I missing something? This is the code I…


document ai read change fileURI to local file path
Hi, I'm new to this document AI, I want to know if we change the fileURI path to a local file path. fileURI requires an https link, is there a way or a code to use a local file path. string modelId = ""; Uri fileUri = new…


Is there a better OCR service than Azure Document Intelligence for text extraction?
I’m currently using Azure Document Intelligence (formerly Form Recognizer) for OCR tasks, but I’m wondering if there are any more accurate or efficient alternatives — either within Azure or outside it. My main goal is to extract clean and structured text…
Extracting Tables only
Is there a way of extracting tables only using Azure AI Document Intelligence
Extract line item fields with query fields
I've seen a few posts that says its possible to extract line item fields with query fields. I've tried this and at best it will only extract a single field value and not extract the value for every line. If there is a way to extract additional line…
Inconsistent analyze results for form recognizer studio and form regognizer service invoked via the sdk (28-02-23-preview api version)?
I've trained a custom neural model for some customer specific invoices using the 28-02-23-preview api version. The invoices comprise a number of typical line items with price etc. Specific to those invoices, however, is that a group of line items is…
Azure document Intelligence - Invoice Model stopped returning Date data we rely on
Until very recently, the invoice model returned two fields that are critical to our service's value: fields.ServiceStartDate fields.ServiceEndDate ^ These represent the start and end date of the service. This was being extracted perfectly, until today,…
Azure AI Document Intelligence - Unable to see project under "All projects"
I have a custom extraction model project set up that others need access to—they have access to the Document Intelligence resource and the Storage Account in question, but when they try to use the filter under "All Projects" it doesn't return…
Could not build the model: Total number of pages in the dataset is 1013. The maximum number of pages allowed in a dataset is 1000
Error: (Depicted Below) Could not build the model: Total number of pages in the dataset is 1013. The maximum number of pages allowed in a dataset is 1000 Question: why this happing ?