[documentintelligence] Code fixes (Azure#38920)

* fix samples

* fix content type

* remove models patch

* fix content type logic + update tests

* update docs

* pylint

* support bufferedreader input

---------

Co-authored-by: catalinaperalta <[email protected]>

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

@@ -34,6 +34,7 @@
 
 ### Other Changes
 
+- Changed the default service API version to `2024-11-30`.
 - No need to pass `content-type` when analyze_request is a stream in `begin_analyze_document()` and `begin_classify_document()`.
 
 ## 1.0.0b4 (2024-09-05)

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

@@ -951,7 +951,7 @@ client = DocumentIntelligenceAdministrationClient(endpoint=endpoint, credential=
 # The `send_request` method can send custom HTTP requests that share the client's existing pipeline,
 # Now let's use the `send_request` method to make a resource details fetching request.
 # The URL of the request should be absolute, and append the API version used for the request.
-request = HttpRequest(method="GET", url=f"{endpoint}/documentintelligence/info?api-version=2024-07-31-preview")
+request = HttpRequest(method="GET", url=f"{endpoint}/documentintelligence/info?api-version=2024-11-30")
 response = client.send_request(request)
 response.raise_for_status()
 response_body = response.json()

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_faf458f6e7"
+  "Tag": "python/documentintelligence/azure-ai-documentintelligence_bfcdb2d242"
 }

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

@@ -449,7 +449,7 @@ def begin_analyze_document(
 
         :param model_id: Unique document model name. Required.
         :type model_id: str
-        :param body: Analyze request parameters. Default value is None.
+        :param body: Analyze request parameters. Required.
         :type body: JSON
         :keyword pages: 1-based page numbers to analyze.  Ex. "1-3,5,7-9". Default value is None.
         :paramtype pages: str
@@ -501,7 +501,7 @@ def begin_analyze_document(
 
         :param model_id: Unique document model name. Required.
         :type model_id: str
-        :param body: Analyze request parameters. Default value is None.
+        :param body: Analyze request parameters. Required.
         :type body: IO[bytes]
         :keyword pages: 1-based page numbers to analyze.  Ex. "1-3,5,7-9". Default value is None.
         :paramtype pages: str
@@ -553,7 +553,7 @@ def begin_analyze_document(
         :param model_id: Unique document model name. Required.
         :type model_id: str
         :param body: Analyze request parameters. Is one of the following types:
-         AnalyzeDocumentRequest, JSON, IO[bytes] Default value is None.
+         AnalyzeDocumentRequest, JSON, IO[bytes] Required.
         :type body: ~azure.ai.documentintelligence.models.AnalyzeDocumentRequest or JSON or
          IO[bytes]
         :keyword pages: 1-based page numbers to analyze.  Ex. "1-3,5,7-9". Default value is None.
@@ -585,15 +585,13 @@ def begin_analyze_document(
         _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {})
         _params = kwargs.pop("params", {}) or {}
 
-        content_type: Optional[str] = kwargs.pop(
-            "content_type", _headers.pop("content-type", "application/octet-stream")
-        )
+        content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("content-type", None))
         cls: ClsType[_models.AnalyzeResult] = kwargs.pop("cls", None)
         polling: Union[bool, PollingMethod] = kwargs.pop("polling", True)
         lro_delay = kwargs.pop("polling_interval", self._config.polling_interval)
         cont_token: Optional[str] = kwargs.pop("continuation_token", None)
         if cont_token is None:
-            if isinstance(body, io.BytesIO):
+            if isinstance(body, (bytes, io.BytesIO, io.BufferedReader)):
                 content_type = "application/octet-stream"
             raw_result = self._analyze_document_initial(
                 model_id=model_id,
@@ -683,10 +681,8 @@ def begin_classify_document(
         :raises ~azure.core.exceptions.HttpResponseError:
         """
         _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {})
-        content_type: Optional[str] = kwargs.pop(
-            "content_type", _headers.pop("content-type", "application/octet-stream")
-        )
-        if isinstance(body, io.BytesIO):
+        content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("content-type", None))
+        if isinstance(body, (bytes, io.BytesIO, io.BufferedReader)):
             content_type = "application/octet-stream"
         return super().begin_classify_document(  # type: ignore[arg-type, misc]
             classifier_id=classifier_id,

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

@@ -25,7 +25,7 @@ class DocumentIntelligenceClient(DIClientGenerated):
     :type credential: ~azure.core.credentials.AzureKeyCredential or
      ~azure.core.credentials.TokenCredential
     :keyword api_version: The API version to use for this operation. Default value is
-     "2024-07-31-preview". Note that overriding this default value may result in unsupported
+     "2024-11-30". Note that overriding this default value may result in unsupported
      behavior.
     :paramtype api_version: str
     :keyword int polling_interval: Default waiting time between two polls for LRO operations if no
@@ -58,7 +58,7 @@ class DocumentIntelligenceAdministrationClient(DIAClientGenerated):
     :type credential: ~azure.core.credentials.AzureKeyCredential or
      ~azure.core.credentials.TokenCredential
     :keyword api_version: The API version to use for this operation. Default value is
-     "2024-07-31-preview". Note that overriding this default value may result in unsupported
+     "2024-11-30". Note that overriding this default value may result in unsupported
      behavior.
     :paramtype api_version: str
     :keyword int polling_interval: Default waiting time between two polls for LRO operations if no

sdk/documentintelligence/azure-ai-documentintelligence/azure/ai/documentintelligence/aio/_operations/_patch.py

@@ -566,15 +566,13 @@ async def begin_analyze_document(  # type: ignore[override]
         _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {})
         _params = kwargs.pop("params", {}) or {}
 
-        content_type: Optional[str] = kwargs.pop(
-            "content_type", _headers.pop("content-type", "application/octet-stream")
-        )
+        content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("content-type", None))
         cls: ClsType[_models.AnalyzeResult] = kwargs.pop("cls", None)
         polling: Union[bool, AsyncPollingMethod] = kwargs.pop("polling", True)
         lro_delay = kwargs.pop("polling_interval", self._config.polling_interval)
         cont_token: Optional[str] = kwargs.pop("continuation_token", None)
         if cont_token is None:
-            if isinstance(body, io.BytesIO):
+            if isinstance(body, (bytes, io.BytesIO, io.BufferedReader)):
                 content_type = "application/octet-stream"
             raw_result = await self._analyze_document_initial(
                 model_id=model_id,
@@ -665,10 +663,8 @@ async def begin_classify_document(  # type: ignore[override]
         :raises ~azure.core.exceptions.HttpResponseError:
         """
         _headers = case_insensitive_dict(kwargs.pop("headers", {}) or {})
-        content_type: Optional[str] = kwargs.pop(
-            "content_type", _headers.pop("content-type", "application/octet-stream")
-        )
-        if isinstance(body, io.BytesIO):
+        content_type: Optional[str] = kwargs.pop("content_type", _headers.pop("content-type", None))
+        if isinstance(body, (bytes, io.BytesIO, io.BufferedReader)):
             content_type = "application/octet-stream"
         return await super().begin_classify_document(  # type: ignore[arg-type, misc]
             classifier_id=classifier_id,

sdk/documentintelligence/azure-ai-documentintelligence/azure/ai/documentintelligence/aio/_patch.py

@@ -28,7 +28,7 @@ class DocumentIntelligenceClient(DIClientGenerated):
     :type credential: ~azure.core.credentials.AzureKeyCredential or
      ~azure.core.credentials_async.AsyncTokenCredential
     :keyword api_version: The API version to use for this operation. Default value is
-     "2024-07-31-preview". Note that overriding this default value may result in unsupported
+     "2024-11-30". Note that overriding this default value may result in unsupported
      behavior.
     :paramtype api_version: str
     """
@@ -59,7 +59,7 @@ class DocumentIntelligenceAdministrationClient(DIAClientGenerated):
     :type credential: ~azure.core.credentials.AzureKeyCredential or
      ~azure.core.credentials_async.AsyncTokenCredential
     :keyword api_version: The API version to use for this operation. Default value is
-     "2024-07-31-preview". Note that overriding this default value may result in unsupported
+     "2024-11-30". Note that overriding this default value may result in unsupported
      behavior.
     :paramtype api_version: str
     """

sdk/documentintelligence/azure-ai-documentintelligence/azure/ai/documentintelligence/models/_patch.py

@@ -6,45 +6,9 @@
 
 Follow our quickstart for examples: https://aka.ms/azsdk/python/dpcodegen/python/customize
 """
-from typing import List, Optional
-from ._models import (
-    AnalyzeDocumentRequest as GeneratedAnalyzeDocumentRequest,
-    ClassifyDocumentRequest as GeneratedClassifyDocumentRequest,
-)
-from .._model_base import rest_field
+from typing import List
 
-
-class AnalyzeDocumentRequest(GeneratedAnalyzeDocumentRequest):
-    """Document analysis parameters.
-
-    :ivar url_source: Document URL to analyze.  Either url_source or bytes_source must be specified.
-    :vartype url_source: str
-    :ivar bytes_source: Document bytes to analyze.  Either url_source or bytes_source must be specified.
-    :vartype bytes_source: bytes
-    """
-
-    bytes_source: Optional[bytes] = rest_field(name="base64Source", format="base64")
-    """Document bytes to analyze.  Either url_source or bytes_source must be specified."""
-
-
-class ClassifyDocumentRequest(GeneratedClassifyDocumentRequest):
-    """Document classification parameters.
-
-    :ivar url_source: Document URL to classify.  Either url_source or bytes_source must be
-     specified.
-    :vartype url_source: str
-    :ivar bytes_source: Document bytes to classify.  Either url_source or bytes_source must be specified.
-    :vartype bytes_source: bytes
-    """
-
-    bytes_source: Optional[bytes] = rest_field(name="base64Source", format="base64")
-    """Document bytes to classify.  Either url_source or bytes_source must be specified."""
-
-
-__all__: List[str] = [
-    "AnalyzeDocumentRequest",
-    "ClassifyDocumentRequest",
-]  # Add all objects you want publicly available to users at this package level
+__all__: List[str] = []  # Add all objects you want publicly available to users at this package level
 
 
 def patch_sdk():

sdk/documentintelligence/azure-ai-documentintelligence/samples/async_samples/sample_analyze_batch_documents_async.py

@@ -52,8 +52,8 @@ async def analyze_batch_docs():
 
     endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
     key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
-    result_container_sas_url = os.environ["RESULT_SAS_URL"]
-    batch_training_data_container_sas_url = os.environ["TRAINING_DATA_SAS_URL"]
+    result_container_sas_url = os.environ["RESULT_CONTAINER_SAS_URL"]
+    batch_training_data_container_sas_url = os.environ["TRAINING_DATA_CONTAINER_SAS_URL"]
 
     document_intelligence_client = DocumentIntelligenceClient(endpoint=endpoint, credential=AzureKeyCredential(key))
 

sdk/documentintelligence/azure-ai-documentintelligence/samples/async_samples/sample_analyze_receipts_async.py

@@ -29,6 +29,8 @@
 
 
 def format_price(price_dict):
+    if price_dict is None:
+        return "N/A"
     return "".join([f"{p}" for p in price_dict.values()])
 
 

sdk/documentintelligence/azure-ai-documentintelligence/samples/async_samples/sample_send_request_async.py

@@ -37,7 +37,7 @@ async def sample_send_request():
         # The `send_request` method can send custom HTTP requests that share the client's existing pipeline,
         # Now let's use the `send_request` method to make a resource details fetching request.
         # The URL of the request should be absolute, and append the API version used for the request.
-        request = HttpRequest(method="GET", url=f"{endpoint}/documentintelligence/info?api-version=2024-07-31-preview")
+        request = HttpRequest(method="GET", url=f"{endpoint}/documentintelligence/info?api-version=2024-11-30")
         response = await client.send_request(request)
         response.raise_for_status()
         response_body = response.json()

sdk/documentintelligence/azure-ai-documentintelligence/samples/sample_analyze_batch_documents.py

@@ -51,8 +51,8 @@ def analyze_batch_docs():
 
     endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
     key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
-    result_container_sas_url = os.environ["RESULT_SAS_URL"]
-    batch_training_data_container_sas_url = os.environ["TRAINING_DATA_SAS_URL"]
+    result_container_sas_url = os.environ["RESULT_CONTAINER_SAS_URL"]
+    batch_training_data_container_sas_url = os.environ["TRAINING_DATA_CONTAINER_SAS_URL"]
 
     document_intelligence_client = DocumentIntelligenceClient(endpoint=endpoint, credential=AzureKeyCredential(key))
 

sdk/documentintelligence/azure-ai-documentintelligence/samples/sample_analyze_receipts.py

@@ -42,6 +42,8 @@ def analyze_receipts():
     from azure.ai.documentintelligence.models import AnalyzeResult
 
     def _format_price(price_dict):
+        if price_dict is None:
+            return "N/A"
         return "".join([f"{p}" for p in price_dict.values()])
 
     endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]

sdk/documentintelligence/azure-ai-documentintelligence/samples/sample_send_request.py

@@ -36,7 +36,7 @@ def sample_send_request():
     # The `send_request` method can send custom HTTP requests that share the client's existing pipeline,
     # Now let's use the `send_request` method to make a resource details fetching request.
     # The URL of the request should be absolute, and append the API version used for the request.
-    request = HttpRequest(method="GET", url=f"{endpoint}/documentintelligence/info?api-version=2024-07-31-preview")
+    request = HttpRequest(method="GET", url=f"{endpoint}/documentintelligence/info?api-version=2024-11-30")
     response = client.send_request(request)
     response.raise_for_status()
     response_body = response.json()

sdk/documentintelligence/test-resources.json

@@ -186,6 +186,14 @@
             "type": "string",
             "value": "[concat(reference(parameters('blobResourceId'), '2019-06-01').primaryEndpoints.blob, parameters('batchTrainingDataContainer'), '?', listServiceSas(parameters('blobResourceId'), '2019-06-01', parameters('batchTrainingResultSasProperties')).serviceSasToken)]"
         },
+        "TRAINING_DATA_CONTAINER_SAS_URL": {
+            "type": "string",
+            "value": "[concat(reference(parameters('blobResourceId'), '2019-06-01').primaryEndpoints.blob, parameters('batchTrainingDataContainer'), '?', listServiceSas(parameters('blobResourceId'), '2019-06-01', parameters('batchTrainingSasProperties')).serviceSasToken)]"
+        },
+        "RESULT_CONTAINER_SAS_URL": {
+            "type": "string",
+            "value": "[concat(reference(parameters('blobResourceId'), '2019-06-01').primaryEndpoints.blob, parameters('batchTrainingDataContainer'), '?', listServiceSas(parameters('blobResourceId'), '2019-06-01', parameters('batchTrainingResultSasProperties')).serviceSasToken)]"
+        },
         "DOCUMENTINTELLIGENCE_BATCH_TRAINING_ASYNC_RESULT_DATA_CONTAINER_SAS_URL": {
             "type": "string",
             "value": "[concat(reference(parameters('blobResourceId'), '2019-06-01').primaryEndpoints.blob, parameters('batchTrainingDataContainer'), '?', listServiceSas(parameters('blobResourceId'), '2019-06-01', parameters('batchTrainingAsyncResultSasProperties')).serviceSasToken)]"