[evaluation] style: Re-enable black (Azure#37532)

* ci: Re-enable black

* style: Run black

Author: kdestin

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_common/utils.py

@@ -60,6 +60,7 @@ def nltk_tokenize(text: str) -> List[str]:
     if not text.isascii():
         # Use NISTTokenizer for international tokenization
         from nltk.tokenize.nist import NISTTokenizer
+
         tokens = NISTTokenizer().international_tokenize(text)
     else:
         # By default, use NLTK word tokenizer
@@ -72,9 +73,7 @@ def check_and_add_api_version_for_aoai_model_config(
     model_config: Union[AzureOpenAIModelConfiguration, OpenAIModelConfiguration],
     default_api_version: str,
 ) -> None:
-    if (
-        "azure_endpoint" in model_config or "azure_deployment" in model_config
-    ):
+    if "azure_endpoint" in model_config or "azure_deployment" in model_config:
         model_config["api_version"] = model_config.get("api_version", default_api_version)
 
 
@@ -84,4 +83,4 @@ def check_and_add_user_agent_for_aoai_model_config(
     user_agent: Optional[str] = None,
 ) -> None:
     if user_agent and ("azure_endpoint" in model_config or "azure_deployment" in model_config):
-        prompty_model_config["parameters"]["extra_headers"].update({"x-ms-useragent": user_agent})
+        prompty_model_config["parameters"]["extra_headers"].update({"x-ms-useragent": user_agent})

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_batch_run_client/code_client.py

@@ -121,7 +121,7 @@ def run(self, flow, data, evaluator_name=None, column_mapping=None, **kwargs):
                 json_data = load_jsonl(data)
             except json.JSONDecodeError as exc:
                 raise EvaluationException(
-                    message = f"Failed to parse data as JSON: {data}. Provide valid json lines data.",
+                    message=f"Failed to parse data as JSON: {data}. Provide valid json lines data.",
                     internal_message="Failed to parse data as JSON",
                     target=ErrorTarget.CODE_CLIENT,
                     category=ErrorCategory.INVALID_VALUE,

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_eval_run.py

@@ -216,7 +216,7 @@ def _end_run(self, reason: str) -> None:
                 internal_message="Incorrect terminal status. Valid statuses are 'FINISHED', 'FAILED' and 'KILLED'",
                 target=ErrorTarget.EVAL_RUN,
                 category=ErrorCategory.FAILED_EXECUTION,
-                blame=ErrorBlame.UNKNOWN
+                blame=ErrorBlame.UNKNOWN,
             )
         url = f"https://{self._url_base}/mlflow/v2.0" f"{self._get_scope()}/api/2.0/mlflow/runs/update"
         body = {
@@ -354,7 +354,7 @@ def _check_state_and_log(self, action: str, bad_states: Set[RunStatus], should_r
                     internal_message=msg,
                     target=ErrorTarget.EVAL_RUN,
                     category=ErrorCategory.FAILED_EXECUTION,
-                    blame=ErrorBlame.UNKNOWN
+                    blame=ErrorBlame.UNKNOWN,
                 )
             LOGGER.warning(msg)
             return False

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_evaluate.py

@@ -260,12 +260,12 @@ def _validate_and_load_data(target, data, evaluators, output_path, azure_ai_proj
         initial_data_df = pd.read_json(data, lines=True)
     except Exception as e:
         raise EvaluationException(
-                message=f"Failed to load data from {data}. Confirm that it is valid jsonl data. Error: {str(e)}.",
-                internal_message="Failed to load data. Confirm that it is valid jsonl data.",
-                target=ErrorTarget.EVALUATE,
-                category=ErrorCategory.INVALID_VALUE,
-                blame=ErrorBlame.USER_ERROR,
-            ) from e
+            message=f"Failed to load data from {data}. Confirm that it is valid jsonl data. Error: {str(e)}.",
+            internal_message="Failed to load data. Confirm that it is valid jsonl data.",
+            target=ErrorTarget.EVALUATE,
+            category=ErrorCategory.INVALID_VALUE,
+            blame=ErrorBlame.USER_ERROR,
+        ) from e
 
     return initial_data_df
 

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_utils.py

@@ -33,16 +33,16 @@ def extract_workspace_triad_from_trace_provider(trace_provider: str):  # pylint:
     match = re.match(AZURE_WORKSPACE_REGEX_FORMAT, trace_provider)
     if not match or len(match.groups()) != 5:
         raise EvaluationException(
-                message="Malformed trace provider string, expected azureml://subscriptions/<subscription_id>/"
-                "resourceGroups/<resource_group>/providers/Microsoft.MachineLearningServices/"
-                f"workspaces/<workspace_name>, got {trace_provider}",
-                internal_message="Malformed trace provider string, expected azureml://subscriptions/<subscription_id>/"
-                "resourceGroups/<resource_group>/providers/Microsoft.MachineLearningServices/"
-                "workspaces/<workspace_name>,",
-                target=ErrorTarget.UNKNOWN,
-                category=ErrorCategory.INVALID_VALUE,
-                blame=ErrorBlame.UNKNOWN,
-            )
+            message="Malformed trace provider string, expected azureml://subscriptions/<subscription_id>/"
+            "resourceGroups/<resource_group>/providers/Microsoft.MachineLearningServices/"
+            f"workspaces/<workspace_name>, got {trace_provider}",
+            internal_message="Malformed trace provider string, expected azureml://subscriptions/<subscription_id>/"
+            "resourceGroups/<resource_group>/providers/Microsoft.MachineLearningServices/"
+            "workspaces/<workspace_name>,",
+            target=ErrorTarget.UNKNOWN,
+            category=ErrorCategory.INVALID_VALUE,
+            blame=ErrorBlame.UNKNOWN,
+        )
     subscription_id = match.group(1)
     resource_group_name = match.group(3)
     workspace_name = match.group(5)

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_chat/_chat.py

@@ -272,7 +272,7 @@ def _validate_conversation(self, conversation: List[Dict]):
                     category=ErrorCategory.INVALID_VALUE,
                     blame=ErrorBlame.USER_ERROR,
                 )
-            
+
             if turn["role"] != expected_role:
                 msg = f"Expected role {expected_role} but got {turn['role']}. Turn number: {one_based_turn_num}"
                 raise EvaluationException(
@@ -305,7 +305,9 @@ def _validate_conversation(self, conversation: List[Dict]):
                     )
 
                 if "citations" not in turn["context"]:
-                    msg = f"Context in each assistant's turn must have 'citations' key. Turn number: {one_based_turn_num}"
+                    msg = (
+                        f"Context in each assistant's turn must have 'citations' key. Turn number: {one_based_turn_num}"
+                    )
                     raise EvaluationException(
                         message=msg,
                         internal_message=msg,

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_content_safety/_content_safety_chat.py

@@ -9,7 +9,7 @@
 from promptflow.tracing import ThreadPoolExecutorWithContext as ThreadPoolExecutor
 from azure.ai.evaluation._exceptions import EvaluationException, ErrorBlame, ErrorCategory, ErrorTarget
 
-from azure.ai.evaluation._model_configurations import AzureAIProject 
+from azure.ai.evaluation._model_configurations import AzureAIProject
 
 try:
     from ._hate_unfairness import HateUnfairnessEvaluator

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_qa/_qa.py

@@ -52,9 +52,7 @@ class QAEvaluator:
         }
     """
 
-    def __init__(
-        self, model_config: dict, parallel: bool = True
-    ):
+    def __init__(self, model_config: dict, parallel: bool = True):
         self._parallel = parallel
 
         self._evaluators = [
@@ -88,12 +86,7 @@ def __call__(self, *, query: str, response: str, context: str, ground_truth: str
             with ThreadPoolExecutor() as executor:
                 futures = {
                     executor.submit(
-                        evaluator,
-                        query=query,
-                        response=response,
-                        context=context,
-                        ground_truth=ground_truth,
-                        **kwargs
+                        evaluator, query=query, response=response, context=context, ground_truth=ground_truth, **kwargs
                     ): evaluator
                     for evaluator in self._evaluators
                 }
@@ -103,9 +96,7 @@ def __call__(self, *, query: str, response: str, context: str, ground_truth: str
                     results.update(future.result())
         else:
             for evaluator in self._evaluators:
-                result = evaluator(
-                    query=query, response=response, context=context, ground_truth=ground_truth, **kwargs
-                )
+                result = evaluator(query=query, response=response, context=context, ground_truth=ground_truth, **kwargs)
                 results.update(result)
 
         return results

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_helpers/_experimental.py

@@ -154,4 +154,4 @@ def _is_warning_cached(warning_msg):
     if warning_msg in _warning_cache:
         return True
     _warning_cache.add(warning_msg)
-    return False
+    return False

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/simulator.py

@@ -20,6 +20,7 @@
 from .._user_agent import USER_AGENT
 from ._conversation.constants import ConversationRole
 from ._helpers import ConversationHistory, Turn, experimental
+
 # from ._tracing import monitor_task_simulator
 from ._utils import JsonLineChatProtocol
 
@@ -198,7 +199,7 @@ async def _simulate_with_predefined_turns(
         """
         simulated_conversations = []
         progress_bar = tqdm(
-            total=int(len(conversation_turns) * (max_conversation_turns/2)),
+            total=int(len(conversation_turns) * (max_conversation_turns / 2)),
             desc="Simulating with predefined conversation turns: ",
             ncols=100,
             unit="messages",
@@ -290,8 +291,8 @@ def _load_user_simulation_flow(
         :return: The loaded flow for simulating user interactions.
         """
         if not user_simulator_prompty:
-            package = 'azure.ai.evaluation.simulator._prompty'
-            resource_name = 'task_simulate.prompty'
+            package = "azure.ai.evaluation.simulator._prompty"
+            resource_name = "task_simulate.prompty"
             try:
                 # Access the resource as a file path
                 with pkg_resources.path(package, resource_name) as prompty_path:
@@ -315,12 +316,12 @@ def _parse_prompty_response(self, *, response: str) -> Dict[str, Any]:
         """
         try:
             if type(response) == str:
-                response = response.replace('\u2019', "'").replace('\u2018', "'")
-                response = response.replace('\u201C', '"').replace('\u201D', '"')
-                
+                response = response.replace("\u2019", "'").replace("\u2018", "'")
+                response = response.replace("\u201C", '"').replace("\u201D", '"')
+
                 # Replace None with null
-                response = response.replace('None', 'null')
-                
+                response = response.replace("None", "null")
+
                 # Escape unescaped single quotes inside string values
                 def escape_single_quotes(match):
                     s = match.group(0)
@@ -391,8 +392,8 @@ def _load_query_generation_flow(
         :return: The loaded flow for generating query responses.
         """
         if not query_response_generating_prompty:
-            package = 'azure.ai.evaluation.simulator._prompty'
-            resource_name = 'task_query_response.prompty'
+            package = "azure.ai.evaluation.simulator._prompty"
+            resource_name = "task_query_response.prompty"
             try:
                 # Access the resource as a file path
                 with pkg_resources.path(package, resource_name) as prompty_path:
@@ -432,7 +433,7 @@ async def _create_conversations_from_query_responses(
         total_turns = len(query_responses) * max_conversation_turns
 
         progress_bar = tqdm(
-            total=int(total_turns/2),
+            total=int(total_turns / 2),
             desc="Generating: ",
             ncols=100,
             unit="message",
@@ -516,11 +517,14 @@ async def _complete_conversation(
                 user_simulator_prompty_kwargs=user_simulator_prompty_kwargs,
             )
             conversation_starter_from_simulated_user = user_flow(
-                task=task, conversation_history=[{
-                    "role": "assistant",
-                    "content": conversation_starter,
-                    "your_task": "Act as the user and translate the content into a user query."
-                }]
+                task=task,
+                conversation_history=[
+                    {
+                        "role": "assistant",
+                        "content": conversation_starter,
+                        "your_task": "Act as the user and translate the content into a user query.",
+                    }
+                ],
             )
             if type(conversation_starter_from_simulated_user) == dict:
                 conversation_starter_from_simulated_user = conversation_starter_from_simulated_user["content"]