Closed tonyranieri closed 6 months ago
@tonyranieri Thanks for your feedback! We will investigate and update as appropriate.
Hi @tonyranieri
Thank you for your feedback! I'd recommend working closer with our support team via an [Azure support request] (https://docs.microsoft.com/en-us/azure/azure-portal/supportability/how-to-create-azure-support-request). Or you can leverage our Q&A forum by posting your issue there so our community, and MVPs can further assist you in troubleshooting this issue or finding potential workarounds. [Teams Q&A forum] (https://docs.microsoft.com/en-us/answers/topics/46488/office-teams-windows-itpro.html) for technical questions about the configuration and administration of Microsoft Teams on Windows. [Microsoft Teams Community forum] (https://answers.microsoft.com/en-us/msteams/forum?sort=LastReplyDate&dir=Desc&tab=All&status=all&mod=&modAge=&advFil=&postedAfter=&postedBefore=&threadType=All&isFilterExpanded=false&page=1) Thank you for your time and patience throughout this issue.
I have a use case where I'm attempting to use Document Intelligence to extract contents of an HTML via the
AnalyzeDocumentContent.Base64Source
property.According to this page "prebuild-read" supports HTML. I have gotten it to work for extraction of the contents of the HTML file.
However, I have noticed that under the header of "Analysis features" the "prebuilt-read" model optionally supports Key-Value Pairs.
The page also says under the header "Model data extraction" that prebuild-read does not support Key-Value Pairs.
Can you please elaborate on the difference between the analysis and extraction?
I'm assuming since Key-Value Pairs are not included for extraction that I should never expect any content populated when using the prebuilt-read model, correct? In this case what would optionally enabling Key-Value Pairs do with this model?
Also, I'm left wondering if this documentation is correct. I've tried setting the
DocumentAnalysisFeature.KeyValuePairs
for a request with the "prebuilt-read" model, but have gotten the following responses:With an HTML file: "The parameter keyValuePairs for file type Html is invalid: The feature is invalid or not supported."
With a PDF file: "The parameter keyValuePairs is invalid: The feature is invalid or not supported."
The errors combined with the documentation have left me a bit confused.
This is .NET 8 utilizing the Azure.AI.DocumentIntelligence version 1.0.0-beta.2. I can provide sample code if needed, but I'm mostly looking for clarification on the analysis vs. extraction and how the Key-Value Pairs plays into this.
Thanks!
Document Details
⚠ Do not edit this section. It is required for learn.microsoft.com ➟ GitHub issue linking.