[DI] Add tests and samples for new API (Azure#37197)

Author: Yalin Li

sdk/documentintelligence/azure-ai-documentintelligence/CHANGELOG.md

@@ -1,6 +1,6 @@
 # Release History
 
-## 1.0.0b4 (Unreleased)
+## 1.0.0b4 (2024-09-05)
 
 ### Features Added
 - Added support for the Analyze Batch Documents API:
@@ -22,6 +22,7 @@
 - Added property `allow_overwrite` to model `BuildDocumentClassifierRequest`.
 - Added properties `allow_overwrite` and `max_training_hours` to model `BuildDocumentModelRequest`.
 - Added properties `classifier_id`, `split` and `doc_types` to model `ComposeDocumentModelRequest`.
+- Added support for getting `operation_id` via `details` property in the new return types `AnalyzeDocumentLROPoller` and `AsyncAnalyzeDocumentLROPoller` in operation `begin_analyze_document()`.
 
 ### Breaking Changes
 - Removed support for extracting lists from analyzed documents:

sdk/documentintelligence/azure-ai-documentintelligence/README.md

@@ -18,7 +18,7 @@ Azure AI Document Intelligence ([previously known as Form Recognizer][service-re
 
 ## _Disclaimer_
 
-_The API version 2024-02-29-preview is currently only available in some Azure regions, the available regions can be found from [here][python-di-available-regions]._
+_The latest service API is currently only available in some Azure regions, the available regions can be found from [here][python-di-available-regions]._
 
 ## Getting started
 
@@ -195,6 +195,8 @@ Sample code snippets are provided to illustrate using long-running operations [b
 The following section provides several code snippets covering some of the most common Document Intelligence tasks, including:
 
 * [Extract Layout](#extract-layout "Extract Layout")
+* [Extract Figures from Documents](#extract-figures-from-documents "Extract Figures from Documents")
+* [Analyze Documents Result in PDF](#analyze-documents-result-in-pdf "Analyze Documents Result in PDF")
 * [Using the General Document Model](#using-the-general-document-model "Using the General Document Model")
 * [Using Prebuilt Models](#using-prebuilt-models "Using Prebuilt Models")
 * [Build a Custom Model](#build-a-custom-model "Build a custom model")
@@ -303,6 +305,81 @@ print("----------------------------------------")
 
 <!-- END SNIPPET -->
 
+### Extract Figures from Documents
+
+Extract figures from the document as cropped images.
+
+<!-- SNIPPET:sample_analyze_result_figures.analyze_result_figures -->
+
+```python
+from azure.core.credentials import AzureKeyCredential
+from azure.ai.documentintelligence import DocumentIntelligenceClient
+from azure.ai.documentintelligence.models import AnalyzeOutputOption, AnalyzeResult
+
+endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
+key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
+
+document_intelligence_client = DocumentIntelligenceClient(endpoint=endpoint, credential=AzureKeyCredential(key))
+
+with open(path_to_sample_documents, "rb") as f:
+    poller = document_intelligence_client.begin_analyze_document(
+        "prebuilt-layout",
+        analyze_request=f,
+        output=[AnalyzeOutputOption.FIGURES],
+        content_type="application/octet-stream",
+    )
+result: AnalyzeResult = poller.result()
+operation_id = poller.details["operation_id"]
+
+if result.figures:
+    for figure in result.figures:
+        if figure.id:
+            response = document_intelligence_client.get_analyze_result_figure(
+                model_id=result.model_id, result_id=operation_id, figure_id=figure.id
+            )
+            with open(f"{figure.id}.png", "wb") as writer:
+                writer.writelines(response)
+else:
+    print("No figures found.")
+```
+
+<!-- END SNIPPET -->
+
+### Analyze Documents Result in PDF
+
+Convert an analog PDF into a PDF with embedded text. Such text can enable text search within the PDF or allow the PDF to be used in LLM chat scenarios.
+
+_Note: For now, this feature is only supported by `prebuilt-read`. All other models will return error._
+
+<!-- SNIPPET:sample_analyze_result_pdf.analyze_result_pdf -->
+
+```python
+from azure.core.credentials import AzureKeyCredential
+from azure.ai.documentintelligence import DocumentIntelligenceClient
+from azure.ai.documentintelligence.models import AnalyzeOutputOption, AnalyzeResult
+
+endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
+key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
+
+document_intelligence_client = DocumentIntelligenceClient(endpoint=endpoint, credential=AzureKeyCredential(key))
+
+with open(path_to_sample_documents, "rb") as f:
+    poller = document_intelligence_client.begin_analyze_document(
+        "prebuilt-read",
+        analyze_request=f,
+        output=[AnalyzeOutputOption.PDF],
+        content_type="application/octet-stream",
+    )
+result: AnalyzeResult = poller.result()
+operation_id = poller.details["operation_id"]
+
+response = document_intelligence_client.get_analyze_result_pdf(model_id=result.model_id, result_id=operation_id)
+with open("analyze_result.pdf", "wb") as writer:
+    writer.writelines(response)
+```
+
+<!-- END SNIPPET -->
+
 ### Using the General Document Model
 
 Analyze key-value pairs, tables, styles, and selection marks from documents using the general document model provided by the Document Intelligence service.

sdk/documentintelligence/azure-ai-documentintelligence/assets.json

@@ -2,5 +2,5 @@
   "AssetsRepo": "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath": "python",
   "TagPrefix": "python/documentintelligence/azure-ai-documentintelligence",
-  "Tag": "python/documentintelligence/azure-ai-documentintelligence_d5576d9de8"
+  "Tag": "python/documentintelligence/azure-ai-documentintelligence_c952134951"
 }

sdk/documentintelligence/azure-ai-documentintelligence/azure/ai/documentintelligence/__init__.py

@@ -6,23 +6,21 @@
 # Changes may cause incorrect behavior and will be lost if the code is regenerated.
 # --------------------------------------------------------------------------
 
-from ._client import DocumentIntelligenceClient
-from ._client import DocumentIntelligenceAdministrationClient
+from ._patch import DocumentIntelligenceClient
+from ._patch import DocumentIntelligenceAdministrationClient
 from ._version import VERSION
 
 __version__ = VERSION
 
-try:
-    from ._patch import __all__ as _patch_all
-    from ._patch import *  # pylint: disable=unused-wildcard-import
-except ImportError:
-    _patch_all = []
+
+from ._patch import AnalyzeDocumentLROPoller
 from ._patch import patch_sdk as _patch_sdk
 
 __all__ = [
+    "AnalyzeDocumentLROPoller",
     "DocumentIntelligenceClient",
     "DocumentIntelligenceAdministrationClient",
 ]
-__all__.extend([p for p in _patch_all if p not in __all__])
+
 
 _patch_sdk()

sdk/documentintelligence/azure-ai-documentintelligence/azure/ai/documentintelligence/_operations/__init__.py

@@ -6,16 +6,15 @@
 # Changes may cause incorrect behavior and will be lost if the code is regenerated.
 # --------------------------------------------------------------------------
 
-from ._operations import DocumentIntelligenceClientOperationsMixin
-from ._operations import DocumentIntelligenceAdministrationClientOperationsMixin
+from ._patch import DocumentIntelligenceClientOperationsMixin
+from ._patch import DocumentIntelligenceAdministrationClientOperationsMixin
+
 
-from ._patch import __all__ as _patch_all
-from ._patch import *  # pylint: disable=unused-wildcard-import
 from ._patch import patch_sdk as _patch_sdk
 
 __all__ = [
     "DocumentIntelligenceClientOperationsMixin",
     "DocumentIntelligenceAdministrationClientOperationsMixin",
 ]
-__all__.extend([p for p in _patch_all if p not in __all__])
+
 _patch_sdk()