Merge pull request #118697 from luzhang06/patch-11

Update overview.md

Author: Court72

articles/ai-services/document-intelligence/concept-read.md

@@ -107,15 +107,7 @@ Try extracting text from forms and documents using the Document Intelligence Stu
 
 ### Microsoft Office and HTML text extraction
 
-Use the parameter `api-version=2023-07-31` when using the REST API or the corresponding SDKs of that API version to extract text from Microsoft Word, Excel, PowerPoint, and HTML files. The following illustration shows extraction of the digital text and text in the Word document by running OCR on the images. Text from embedded images isn't included in the extraction.
-
-> [!NOTE]
->
-> * [Add-on capabilities](concept-add-on-capabilities.md) are not supported for Microsoft Word, Excel, PowerPoint, and HTML file formats.
-
-:::image type="content" source="media/office-to-ocr.png" alt-text="Screenshot of a Microsoft Word document extracted by Document Intelligence Read OCR.":::
-
-The page units in the model output are computed as shown:
+When analyzing Microsft Office and HTML files, the page units in the model output are computed as shown:
 
  **File format**   | **Computed page unit**   | **Total pages**  |
 | --- | --- | --- |

articles/ai-services/document-intelligence/concept-retrieval-augumented-generation.md

@@ -45,7 +45,7 @@ Markdown is a structured and formatted markup language and a popular input for e
 
 * **Scalability and AI quality**. The Layout model is highly scalable in Optical Character Recognition (OCR), table extraction, and [document structure analysis](concept-layout.md#document-layout-analysis). It supports [309 printed and 12 handwritten languages](language-support-ocr.md#model-id-prebuilt-layout), further ensuring high-quality results driven by AI capabilities.
 
-* **Large learning model (LLM) compatibility**. The Layout model Markdown formatted output is LLM friendly and facilitates seamless integration into your workflows. You can turn any table in a document into Markdown format and avoid extensive effort parsing the documents for greater LLM understanding.
+* **Large language model (LLM) compatibility**. The Layout model Markdown formatted output is LLM friendly and facilitates seamless integration into your workflows. You can turn any table in a document into Markdown format and avoid extensive effort parsing the documents for greater LLM understanding.
 
 **Text image processed with Document Intelligence Studio and output to MarkDown using Layout model**
 

articles/ai-services/document-intelligence/overview.md

@@ -63,7 +63,7 @@ Document analysis models enable text extraction from forms and documents and ret
    :::column-end:::
    :::column span="":::
       :::image type="icon" source="media/overview/icon-layout.png" link="#layout":::</br>
-    [**Layout**](#layout) | Extract text </br>and document structure.
+    [**Layout**](#layout) | Extract text, tables, </br>and document structure.
    :::column-end:::
   :::row-end:::
 :::moniker-end
@@ -281,7 +281,7 @@ You can use Document Intelligence to automate document processing in application
 
 |Model ID| Description |Automation use cases | Development options |
 |----------|--------------|-------------------------|-----------|
-|[**prebuilt-read**](concept-read.md)|&#9679; Extract **text** from documents.</br>&#9679; [Data and field extraction](concept-read.md#read-model-data-extraction)| &#9679; Contract processing. </br>&#9679; Financial or medical report processing.|&#9679; [**Document Intelligence Studio**](https://formrecognizer.appliedai.azure.com/studio/read)</br>&#9679; [**REST API**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-3.0.0&preserve-view=true&pivots=programming-language-rest-api)</br>&#9679; [**C# SDK**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-3.0.0&preserve-view=true&pivots=programming-language-csharp)</br>&#9679; [**Python SDK**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-3.0.0&preserve-view=true&pivots=programming-language-python)</br>&#9679; [**Java SDK**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-3.0.0&preserve-view=true&pivots=programming-language-java)</br>&#9679; [**JavaScript**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-3.0.0&preserve-view=true&pivots=programming-language-javascript) |
+|[**prebuilt-read**](concept-read.md)|&#9679; Extract **text** from documents.</br>&#9679; [Data extraction](concept-read.md#read-model-data-extraction)| &#9679; Digitizing any document. </br>&#9679; Compliance and auditing. &#9679; Processing handwritten notes before translation.|&#9679; [**Document Intelligence Studio**](https://formrecognizer.appliedai.azure.com/studio/read)</br>&#9679; [**REST API**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-4.0.0&preserve-view=true&pivots=programming-language-rest-api)</br>&#9679; [**C# SDK**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-4.0.0&preserve-view=true&pivots=programming-language-csharp)</br>&#9679; [**Python SDK**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-4.0.0&preserve-view=true&pivots=programming-language-python)</br>&#9679; [**Java SDK**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-4.0.0&preserve-view=true&pivots=programming-language-java)</br>&#9679; [**JavaScript**](how-to-guides/use-sdk-rest-api.md?view=doc-intel-4.0.0&preserve-view=true&pivots=programming-language-javascript) |
 
 > [!div class="nextstepaction"]
 > [Return to model types](#document-analysis-models)
@@ -292,7 +292,7 @@ You can use Document Intelligence to automate document processing in application
 
 | Model ID | Description |Automation use cases | Development options |
 |----------|--------------|-------------------------|-----------|
-|[**prebuilt-layout**](concept-layout.md) |&#9679; Extract **text and layout** information from documents.</br>&#9679; [Data and field extraction](concept-layout.md#data-extraction)</br>&#9679; Layout API is updated to a prebuilt model. |&#9679; Document indexing and retrieval by structure.</br>&#9679; Preprocessing prior to OCR analysis. |&#9679; [**Document Intelligence Studio**](https://formrecognizer.appliedai.azure.com/studio/layout)</br>&#9679; [**REST API**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.0.0&preserve-view=true)</br>&#9679; [**C# SDK**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.0.0&preserve-view=true#layout-model)</br>&#9679; [**Python SDK**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.0.0&preserve-view=true#layout-model)</br>&#9679; [**Java SDK**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.0.0&preserve-view=true#layout-model)</br>&#9679; [**JavaScript**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.0.0&preserve-view=true#layout-model)|
+|[**prebuilt-layout**](concept-layout.md) |&#9679; Extract **text and layout** information from documents.</br>&#9679; [Data extraction](concept-layout.md#data-extraction) |&#9679; Document indexing and retrieval by structure.</br>&#9679; Financial and medical report analysis. |&#9679; [**Document Intelligence Studio**](https://formrecognizer.appliedai.azure.com/studio/layout)</br>&#9679; [**REST API**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-4.0.0&preserve-view=true)</br>&#9679; [**C# SDK**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-4.0.0&preserve-view=true#layout-model)</br>&#9679; [**Python SDK**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-4.0.0&preserve-view=true#layout-model)</br>&#9679; [**Java SDK**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-4.0.0&preserve-view=true#layout-model)</br>&#9679; [**JavaScript**](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-4.0.0&preserve-view=true#layout-model)|
 
 > [!div class="nextstepaction"]
 > [Return to model types](#document-analysis-models)