1dp sdk followup (Azure#40813)

* initial changes

* fix

* fix

* fix

* fix

* rearranged

* fix

* Fix tests

* Fix tests

* Fix tests

* Fix tests

* Copilot fix

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

* Fix tests

* Fix tests

* Fix tests - assets

* Fix tests - assets

* Fix tests - assets

* assets

* assets

* fix-assets

* adding service check

* revert one test to avoid large size recording

* unit test fix

* unit test fix

* last asset

* red-team

* Enabling Red Teaming for 1dp

* assset change

* fix for one test

* typo fix

* fix

* dep

* asset

* CI Fix

* CI Fix

* CI Fix

* revert again

* revert

* updated asset for one test

* rollback changes

* rollback changes

* initial commit

* adding assets

* fix

* fix

* asset for evaluate_conversation test

* fix for validate

---------

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

Author: w-javed

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

@@ -2,5 +2,5 @@
   "AssetsRepo": "Azure/azure-sdk-assets",
   "AssetsRepoPrefixPath": "python",
   "TagPrefix": "python/evaluation/azure-ai-evaluation",
-  "Tag": "python/evaluation/azure-ai-evaluation_7d56415461"
+  "Tag": "python/evaluation/azure-ai-evaluation_a93be1e527"
 }

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

@@ -14,7 +14,7 @@
 import pandas as pd
 
 from azure.ai.evaluation._common.math import list_mean_nan_safe, apply_transform_nan_safe
-from azure.ai.evaluation._common.utils import validate_azure_ai_project
+from azure.ai.evaluation._common.utils import validate_azure_ai_project, is_onedp_project
 from azure.ai.evaluation._exceptions import ErrorBlame, ErrorCategory, ErrorTarget, EvaluationException
 
 from azure.ai.evaluation._aoai.aoai_grader import AzureOpenAIGrader
@@ -816,7 +816,7 @@ def _evaluate(  # pylint: disable=too-many-locals,too-many-statements
     target: Optional[Callable] = None,
     data: Union[str, os.PathLike],
     evaluator_config: Optional[Dict[str, EvaluatorConfig]] = None,
-    azure_ai_project: Optional[AzureAIProject] = None,
+    azure_ai_project: Optional[Union[str, AzureAIProject]] = None,
     output_path: Optional[Union[str, os.PathLike]] = None,
     fail_on_evaluator_errors: bool = False,
     **kwargs,
@@ -915,7 +915,7 @@ def _evaluate(  # pylint: disable=too-many-locals,too-many-statements
 
     # Done with all evaluations, message outputs into final forms, and log results if needed.
     name_map = _map_names_to_builtins(evaluators, graders)
-    if isinstance(azure_ai_project, str):
+    if is_onedp_project(azure_ai_project):
         studio_url = _log_metrics_and_instance_results_onedp(
             metrics, results_df, azure_ai_project, evaluation_name, name_map, **kwargs
         )
@@ -943,7 +943,7 @@ def _preprocess_data(
     evaluator_config: Optional[Dict[str, EvaluatorConfig]] = None,
     target: Optional[Callable] = None,
     output_path: Optional[Union[str, os.PathLike]] = None,
-    azure_ai_project: Optional[AzureAIProject] = None,
+    azure_ai_project: Optional[Union[str, AzureAIProject]] = None,
     evaluation_name: Optional[str] = None,
     **kwargs,
     ) -> __ValidatedData:

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_common/_base_rai_svc_eval.py

@@ -59,7 +59,7 @@ def __init__(
     ):
         super().__init__(eval_last_turn=eval_last_turn, conversation_aggregation_type=conversation_aggregation_type, threshold=threshold, _higher_is_better=_higher_is_better)
         self._eval_metric = eval_metric
-        self._azure_ai_project = azure_ai_project if is_onedp_project(azure_ai_project) else validate_azure_ai_project(azure_ai_project)
+        self._azure_ai_project = validate_azure_ai_project(azure_ai_project)
         self._credential = credential
         self._threshold = threshold
         self._higher_is_better = _higher_is_better

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

@@ -111,7 +111,7 @@ def __init__(
             self.model_config = model_config
         else:
             self.model_config = None
-        self.azure_ai_project = azure_ai_project if isinstance(azure_ai_project, str) else validate_azure_ai_project(azure_ai_project)
+        self.azure_ai_project = validate_azure_ai_project(azure_ai_project)
         self.credential = credential
         self.logger = _setup_logger()
 

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_red_team.py

@@ -212,7 +212,7 @@ def __init__(
         :type output_dir: str
         """
 
-        self.azure_ai_project = azure_ai_project if is_onedp_project(azure_ai_project) else validate_azure_ai_project(azure_ai_project)
+        self.azure_ai_project = validate_azure_ai_project(azure_ai_project)
         self.credential = credential
         self.output_dir = output_dir
 

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

@@ -49,9 +49,9 @@ class AdversarialSimulator:
     """
     Initializes the adversarial simulator with a project scope.
 
-    :param azure_ai_project: The scope of the Azure AI project. It contains subscription id, resource group, and project
-        name.
-    :type azure_ai_project: ~azure.ai.evaluation.AzureAIProject
+    :param azure_ai_project: The Azure AI project, which can either be a string representing the project endpoint 
+        or an instance of AzureAIProject. It contains subscription id, resource group, and project name. 
+    :type azure_ai_project: Union[str, AzureAIProject]
     :param credential: The credential for connecting to Azure AI project.
     :type credential: ~azure.core.credentials.TokenCredential
 

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

@@ -8,7 +8,7 @@
 import time
 from dataclasses import dataclass
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union, cast
-
+import base64
 import re
 import jinja2
 
@@ -422,7 +422,10 @@ async def _to_multi_modal_content(self, text: str) -> list:
                 if(isinstance(self.rai_client, RAIClient)):
                     encoded_image = await self.rai_client.get_image_data(msg)
                 else:
-                    encoded_image = self.rai_client.red_teams.get_template_parameters_image(path=msg)
+                    response = self.rai_client.red_teams.get_template_parameters_image(path=msg, stream="true")
+                    image_data = b"".join(response)
+                    encoded_image = base64.b64encode(image_data).decode("utf-8")
+                    
                 contents.append(
                     {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{encoded_image}"}},
                 )

sdk/evaluation/azure-ai-evaluation/tests/e2etests/test_sim_and_eval.py

@@ -138,7 +138,7 @@ async def callback(
         ("proj_scope", "cred"),
         (
             ("project_scope", "azure_cred"),
-            # ("project_scope_onedp", "azure_cred_onedp"),
+            ("project_scope_onedp", "azure_cred_onedp"),
         )
     )
     def test_protected_material_sim_image_understanding(self, request, proj_scope, cred):
@@ -192,7 +192,6 @@ async def callback(
         eval_output = evaluate(
             data=file_name,
             evaluation_name="sim_image_understanding_protected_material_eval",
-            # azure_ai_project=project_scope,
             evaluators={"protected_material": protected_material_eval},
         )