Documentexctractionskill issue in azure AI search
I have a blob storage with pdf files, where i want to implement knowledge mining solution. I created the data source, the index, the skillset, and the indexer. However, when I run everything i get a warning that the "Could not execute skill because…
Fine-Tuning the GPT-4o Model
Hello there, How can I fine-tune the GPT-4o model (or other versions like GPT-3.5) using .pdf input samples (including text and images)?
![](https://techprofile.blob.core.windows.net/images/3b270b575c094eeca63e9bc66c861c5a.png)
Issues with Azure Assistant API File Search and Response Times
I am currently working with the Azure Assistant API and facing some challenges. Specifically, when I attempt to add files and utilize function calls, the file search functionality does not work as expected. Despite providing proper instructions, the API…
![](https://techprofile.blob.core.windows.net/images/3b270b575c094eeca63e9bc66c861c5a.png)
Azure AI Document Intelligence - can't call Custom Classification model via API
Hi there, I've trained a model with Model ID of "my-custom-classification-model" as a Custom Classification model within Azure AI Document Intelligence. However, I'm unable to call this model via API endpoint, receiving a "The requested…
![](https://techprofile.blob.core.windows.net/images/3b270b575c094eeca63e9bc66c861c5a.png)
How should we label the table that spans multiple pages?
when we try to label the table that spans multiple pages we got the error. is there any workaround for this?
![](https://techprofile.blob.core.windows.net/images/3b270b575c094eeca63e9bc66c861c5a.png)
one column table is not getting recognized by document intelligence even after custom model training.
when i train my custom model on one column tables still it doesn't recognizing table.
![](https://techprofile.blob.core.windows.net/images/3b270b575c094eeca63e9bc66c861c5a.png)
how to convert the output of custom model in case of tables ?
when i train the custom model to fetch the tables how can i extract tables from my trained fields from output json?
![](https://techprofile.blob.core.windows.net/images/3b270b575c094eeca63e9bc66c861c5a.png)
Document intelligence has a problem to read the xlsx files.
When I uploaded the xlsx file inside the document intelligence , the error shows like this. InternalServerError An unexpected error occurred. Please submit support request with apim-request-id shown below to get further assistance. apim-request-id:…
![](https://techprofile.blob.core.windows.net/images/3b270b575c094eeca63e9bc66c861c5a.png)
Auto Labeling Not Working - Azure Gov DI Studio IP?
I'm working on the azure gov DI studio: https://formrecognizer.appliedai.azure.us/studio/ The auto labeling function is not working. We are only allowing specific IPs to connect to the subscription. I saw instruction to whitelist 20.3.165.95 in this MS…
How to automate Azure Document Intelligence model
Hi MS Team, I have a custom invoice extraction model on Azure Document Intelligence Studio with the invoices being held in azure blob storage. Goal: To extract information from invoices using the model and automatically upload results to an Excel table…
I am new - How to build the same UI as shown in the studio in React
I have just started learning about this document intelligence my question is i want to build the same UI in my react application so does Azure provides some renderer or package or i need to build my own ?
I don't want to use the check box detection feature in the layout function of Azure Document Intelligence, is it possible?
Is it possible to not use the check box feature? because there is a problem in recognizing the part of the table that is not the check box as a check box. i don't want to see ':selected:' word.
Translate a foreign language scanned document to English
Hey all, I have a pdf scanned document in a foreign language like korean and want to use document intelligence to extract the text and translate that into English. I don't know how to achieve this. If you have worked on something like this, please let…
Getting "Connection to ...azure.com timed out. (connect timeout=300)" when doing many calls to begin_analyze_document
We are trying out azure document intelligence from python. In particular we are using client.begin_analyze_document() with model id prebuilt-read. When we are doing a load test, a large amount of requests continuously for several minutes, we are getting…
does SDK c# support add-on query field ( Document intelligence)
Hi everyone, I'm trying to use the Azure Document intelligence prebuilt model (invoice) to read and extract specific fields , I read the document of Microsoft to see some examples how to add-onn field query to the request using c# sdk , but I only found…
Need help on table extraction from a document
Hi All, We are having tables in a document, we need to extract it. We are invoking form recognizer using REST API, and in the OCR response, we are getting an element named tables, with all cell details. Can you please let me know if the only way to…
Why the speed that upload the documents is so slow? and another issue
I just upload a txt document which is 2.3 MB to do a RAG in GPT4 model, but the uploading speed is too slow!! And finally I even can't chat with bot! I don't know why?
![](https://techprofile.blob.core.windows.net/images/UVyLn-Xlr0apNce5TRX1RA.png?8DBA3B)
Convert DocumentTable to normal table for Azure Intelligent Documents
Hi, Is there other way to export TABLE result in a normal form, extracted from Azure AI Document Intelligence (DI) (previously called Form Recognizer)? I could not convert documenttable to a normal table form to read each row and column. Method I called…
The OCR engine just doesn't recognize some digits
Tried the online version of your OCR engine (Vision Studio) with a scanned database printout. Occasionally some digits (usually the last one of a number) simply gets lost. The source image is clearly readable. Why can this be the case? One would…
![](https://techprofile.blob.core.windows.net/images/d2tvFBHkuECHIdJFwoOShw.png?8DB3F8)
How get azure 'layout' document intelligence api version "2024-02-29-preview" with python sdk
Hello, I'm using python SDK (azure-ai-documentintelligence==1.0.0b3) to extract layout from files. According to the documentation´s information, this SDK should use the API version '2024-02-29-preview', but the version actually used is…