azure-ai-evaluation 1.9.0__py3-none-any.whl → 1.10.0__py3-none-any.whl

azure/ai/evaluation/red_team/_red_team_result.py

@@ -185,11 +185,14 @@ class RedTeamingParameters(TypedDict):
     :type attack_complexity: List[str]
     :param techniques_used: Dictionary mapping complexity levels to lists of converter techniques used
     :type techniques_used: Dict[str, List[str]]
+    :param attack_success_thresholds: Thresholds used for determining attack success per risk category
+    :type attack_success_thresholds: Dict[str, Any]
     """
 
     attack_objective_generated_from: AttackObjectiveSource
     attack_complexity: List[str]
     techniques_used: Dict[str, List[str]]
+    attack_success_thresholds: Dict[str, Dict[str, int]]
 
 
 @experimental
@@ -228,6 +231,8 @@ class AttackDetails(TypedDict):
     :type conversation: List[Dict[str, str]]
     :param risk_assessment: Dictionary containing content safety assessment for the conversation
     :type risk_assessment: Optional[RiskAssessment]
+    :param attack_success_threshold: The threshold value used to determine attack success
+    :type attack_success_threshold: Optional[int]
     """
 
     attack_success: Optional[bool]
@@ -236,6 +241,7 @@ class AttackDetails(TypedDict):
     risk_category: str
     conversation: List[Dict[str, str]]
     risk_assessment: Optional[RiskAssessment]
+    attack_success_threshold: Optional[int]
 
 
 @experimental

azure/ai/evaluation/red_team/_utils/_rai_service_eval_chat_target.py

@@ -11,11 +11,16 @@ import asyncio
 import re
 from typing import Dict, Optional, Any, Tuple, List
 from azure.ai.evaluation._common.rai_service import evaluate_with_rai_service
-from azure.ai.evaluation.simulator._model_tools._generated_rai_client import GeneratedRAIClient
+from azure.ai.evaluation.simulator._model_tools._generated_rai_client import (
+    GeneratedRAIClient,
+)
 from pyrit.models import PromptRequestResponse, construct_response_from_request
 from pyrit.prompt_target import PromptChatTarget
-from .constants import USER_AGENT
-from .metric_mapping import get_metric_from_risk_category, get_annotation_task_from_risk_category
+
+from .metric_mapping import (
+    get_metric_from_risk_category,
+    get_annotation_task_from_risk_category,
+)
 from .._attack_objective_generator import RiskCategory
 
 

azure/ai/evaluation/red_team/_utils/constants.py

@@ -55,5 +55,3 @@ TASK_STATUS = {
     "TIMEOUT": "timeout",
     "INCOMPLETE": "incomplete",
 }
-
-USER_AGENT = "azure-ai-evaluation-redteam"

azure/ai/evaluation/simulator/_adversarial_simulator.py

@@ -239,8 +239,11 @@ class AdversarialSimulator:
             # So randomize a the selection instead of the parameter list directly,
             # or a potentially large deep copy.
             if randomization_seed is not None:
-                random.seed(randomization_seed)
-            random.shuffle(templates)
+                # Create a local random instance to avoid polluting global state
+                local_random = random.Random(randomization_seed)
+                local_random.shuffle(templates)
+            else:
+                random.shuffle(templates)
 
         # Prepare task parameters based on scenario - but use a single append call for all scenarios
         tasks = []

azure/ai/evaluation/simulator/_indirect_attack_simulator.py

@@ -5,7 +5,8 @@
 # noqa: E501
 import asyncio
 import logging
-from typing import Callable, cast, Union
+import random
+from typing import Callable, cast, Union, Optional
 
 from tqdm import tqdm
 
@@ -105,6 +106,7 @@ class IndirectAttackSimulator(AdversarialSimulator):
         api_call_retry_sleep_sec: int = 1,
         api_call_delay_sec: int = 0,
         concurrent_async_task: int = 3,
+        randomization_seed: Optional[int] = None,
         **kwargs,
     ):
         """
@@ -130,6 +132,9 @@ class IndirectAttackSimulator(AdversarialSimulator):
         :keyword concurrent_async_task: The number of asynchronous tasks to run concurrently during the simulation.
             Defaults to 3.
         :paramtype concurrent_async_task: int
+        :keyword randomization_seed: The seed used to randomize prompt selection. If unset, the system's
+            default seed is used. Defaults to None.
+        :paramtype randomization_seed: Optional[int]
         :return: A list of dictionaries, each representing a simulated conversation. Each dictionary contains:
 
          - 'template_parameters': A dictionary with parameters used in the conversation template,
@@ -190,6 +195,13 @@ class IndirectAttackSimulator(AdversarialSimulator):
             ncols=100,
             unit="simulations",
         )
+
+        # Apply randomization to templates if seed is provided
+        if randomization_seed is not None:
+            # Create a local random instance to avoid polluting global state
+            local_random = random.Random(randomization_seed)
+            local_random.shuffle(templates)
+
         for template in templates:
             for parameter in template.template_parameters:
                 tasks.append(

azure/ai/evaluation/simulator/_model_tools/_generated_rai_client.py

@@ -124,7 +124,7 @@ class GeneratedRAIClient:
                 risk_category=risk_category,
                 lang="en",
                 strategy=strategy,
-                headers={"client_request_id": scan_session_id},
+                headers={"x-ms-client-request-id": scan_session_id},
             )
             return response
 
@@ -146,7 +146,7 @@ class GeneratedRAIClient:
         try:
             # Send the request using the autogenerated client
             response = self._client.get_jail_break_dataset_with_type(
-                type="upia", headers={"client_request_id": scan_session_id}
+                type="upia", headers={"x-ms-client-request-id": scan_session_id}
             )
             if isinstance(response, list):
                 return response

azure/ai/evaluation/simulator/_model_tools/_proxy_completion_model.py

@@ -10,7 +10,7 @@ from typing import Any, Dict, List, Optional, cast, Union
 
 from azure.ai.evaluation._http_utils import AsyncHttpPipeline, get_async_http_client
 from azure.ai.evaluation._user_agent import UserAgentSingleton
-from azure.core.exceptions import HttpResponseError
+from azure.core.exceptions import HttpResponseError, ServiceResponseError
 from azure.core.pipeline.policies import AsyncRetryPolicy, RetryMode
 from azure.ai.evaluation._common.onedp._client import AIProjectClient
 from azure.ai.evaluation._common.onedp.models import SimulationDTO
@@ -225,7 +225,25 @@ class ProxyChatCompletionsModel(OpenAIChatCompletionsModel):
                     sleep_time = RAIService.SLEEP_TIME**request_count
                     await asyncio.sleep(sleep_time)
         else:
-            response = await session.post(url=self.endpoint_url, headers=proxy_headers, json=sim_request_dto.to_dict())
+            # Retry policy for POST request to RAI service
+            service_call_retry_policy = AsyncRetryPolicy(
+                retry_on_exceptions=[ServiceResponseError],
+                retry_total=7,
+                retry_backoff_factor=10.0,
+                retry_backoff_max=180,
+                retry_mode=RetryMode.Exponential,
+            )
+
+            response = None
+            async with get_async_http_client().with_policies(retry_policy=service_call_retry_policy) as retry_client:
+                try:
+                    response = await retry_client.post(
+                        url=self.endpoint_url, headers=proxy_headers, json=sim_request_dto.to_dict()
+                    )
+                except ServiceResponseError as e:
+                    self.logger.error("ServiceResponseError during POST request to rai svc after retries: %s", str(e))
+                    raise
+
             # response.raise_for_status()
             if response.status_code != 202:
                 raise HttpResponseError(

azure/ai/evaluation/simulator/_simulator.py

@@ -7,6 +7,7 @@ import asyncio
 import importlib.resources as pkg_resources
 import json
 import os
+import random
 import re
 import warnings
 from typing import Any, Callable, Dict, List, Optional, Union, Tuple
@@ -104,6 +105,7 @@ class Simulator:
         user_simulator_prompty_options: Dict[str, Any] = {},
         conversation_turns: List[List[Union[str, Dict[str, Any]]]] = [],
         concurrent_async_tasks: int = 5,
+        randomization_seed: Optional[int] = None,
         **kwargs,
     ) -> List[JsonLineChatProtocol]:
         """
@@ -134,6 +136,9 @@ class Simulator:
         :keyword concurrent_async_tasks: The number of asynchronous tasks to run concurrently during the simulation.
             Defaults to 5.
         :paramtype concurrent_async_tasks: int
+        :keyword randomization_seed: The seed used to randomize task/query order. If unset, the system's
+            default seed is used. Defaults to None.
+        :paramtype randomization_seed: Optional[int]
         :return: A list of simulated conversations represented as JsonLineChatProtocol objects.
         :rtype: List[JsonLineChatProtocol]
 
@@ -159,6 +164,13 @@ class Simulator:
                 f"Only the first {num_queries} lines of the specified tasks will be simulated."
             )
 
+        # Apply randomization to tasks if seed is provided
+        if randomization_seed is not None and tasks:
+            # Create a local random instance to avoid polluting global state
+            local_random = random.Random(randomization_seed)
+            tasks = tasks.copy()  # Don't modify the original list
+            local_random.shuffle(tasks)
+
         max_conversation_turns *= 2  # account for both user and assistant turns
 
         prompty_model_config = self.model_config

{azure_ai_evaluation-1.9.0.dist-info → azure_ai_evaluation-1.10.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: azure-ai-evaluation
-Version: 1.9.0
+Version: 1.10.0
 Summary: Microsoft Azure Evaluation Library for Python
 Home-page: https://github.com/Azure/azure-sdk-for-python
 Author: Microsoft Corporation
@@ -21,8 +21,6 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: NOTICE.txt
-Requires-Dist: promptflow-devkit>=1.17.1
-Requires-Dist: promptflow-core>=1.17.1
 Requires-Dist: pyjwt>=2.8.0
 Requires-Dist: azure-identity>=1.16.0
 Requires-Dist: azure-core>=1.30.2
@@ -400,6 +398,34 @@ This project has adopted the [Microsoft Open Source Code of Conduct][code_of_con
 
 # Release History
 
+## 1.10.0 (2025-07-31)
+
+### Breaking Changes
+
+- Added `evaluate_query` parameter to all RAI service evaluators that can be passed as a keyword argument. This parameter controls whether queries are included in evaluation data when evaluating query-response pairs. Previously, queries were always included in evaluations. When set to `True`, both query and response will be evaluated; when set to `False` (default), only the response will be evaluated. This parameter is available across all RAI service evaluators including `ContentSafetyEvaluator`, `ViolenceEvaluator`, `SexualEvaluator`, `SelfHarmEvaluator`, `HateUnfairnessEvaluator`, `ProtectedMaterialEvaluator`, `IndirectAttackEvaluator`, `CodeVulnerabilityEvaluator`, `UngroundedAttributesEvaluator`, `GroundednessProEvaluator`, and `EciEvaluator`.  Existing code that relies on queries being evaluated will need to explicitly set `evaluate_query=True` to maintain the previous behavior.
+
+### Features Added
+
+- Added support for Azure OpenAI Python grader via `AzureOpenAIPythonGrader` class, which serves as a wrapper around Azure Open AI Python grader configurations. This new grader object can be supplied to the main `evaluate` method as if it were a normal callable evaluator.
+- Added `attack_success_thresholds` parameter to `RedTeam` class for configuring custom thresholds that determine attack success. This allows users to set specific threshold values for each risk category, with scores greater than the threshold considered successful attacks (i.e. higher threshold means higher 
+tolerance for harmful responses).
+- Enhanced threshold reporting in RedTeam results to include default threshold values when custom thresholds aren't specified, providing better transparency about the evaluation criteria used.
+
+
+### Bugs Fixed
+
+- Fixed red team scan `output_path` issue where individual evaluation results were overwriting each other instead of being preserved as separate files. Individual evaluations now create unique files while the user's `output_path` is reserved for final aggregated results.
+- Significant improvements to TaskAdherence evaluator. New version has less variance, is much faster and consumes fewer tokens.
+- Significant improvements to Relevance evaluator. New version has more concrete rubrics and has less variance, is much faster and consumes fewer tokens.
+
+
+### Other Changes
+
+- The default engine for evaluation was changed from `promptflow` (PFClient) to an in-SDK batch client (RunSubmitterClient)
+  - Note: We've temporarily kept an escape hatch to fall back to the legacy `promptflow` implementation by setting `_use_pf_client=True` when invoking `evaluate()`.
+    This is due to be removed in a future release.
+
+
 ## 1.9.0 (2025-07-02)
 
 ### Features Added
@@ -411,8 +437,11 @@ This project has adopted the [Microsoft Open Source Code of Conduct][code_of_con
 ### Bugs Fixed
 
 - Significant improvements to IntentResolution evaluator. New version has less variance, is nearly 2x faster and consumes fewer tokens.
+
+- Fixes and improvements to ToolCallAccuracy evaluator. New version has less variance. and now works on all tool calls that happen in a turn at once. Previously, it worked on each tool call independently without having context on the other tool calls that happen in the same turn, and then aggregated the results to a score in the range [0-1]. The score range is now [1-5].
 - Fixed MeteorScoreEvaluator and other threshold-based evaluators returning incorrect binary results due to integer conversion of decimal scores. Previously, decimal scores like 0.9375 were incorrectly converted to integers (0) before threshold comparison, causing them to fail even when above the threshold. [#41415](https://github.com/Azure/azure-sdk-for-python/issues/41415)
 - Added a new enum `ADVERSARIAL_QA_DOCUMENTS` which moves all the "file_content" type prompts away from `ADVERSARIAL_QA` to the new enum
+- `AzureOpenAIScoreModelGrader` evaluator now supports `pass_threshold` parameter to set the minimum score required for a response to be considered passing. This allows users to define custom thresholds for evaluation results, enhancing flexibility in grading AI model responses.
 
 ## 1.8.0 (2025-05-29)
 

{azure_ai_evaluation-1.9.0.dist-info → azure_ai_evaluation-1.10.0.dist-info}/RECORD

@@ -1,16 +1,17 @@
-azure/ai/evaluation/__init__.py,sha256=VvxtyvozSmYqWjl62kbwLAZJY7vwXZD0QOsS0ah7mmc,4231
+azure/ai/evaluation/__init__.py,sha256=hrP2gqioHoUe5QBvpkmNpQ45zu6g-ErReY-fqzWeOf8,5298
 azure/ai/evaluation/_constants.py,sha256=FNVxCt3_0MwZHtDsjRYPH5h6mT_48KCbJTBWBDTNujE,3729
 azure/ai/evaluation/_eval_mapping.py,sha256=CHabrfaRlWbrAYUZV5YXYH0GX_zk9tG9y1og6RtUAnU,2584
 azure/ai/evaluation/_exceptions.py,sha256=y5zVwhyoNuqjaE8P6E65j0-NRDE2Nx0iMq8F7_0kO-4,5848
 azure/ai/evaluation/_http_utils.py,sha256=d1McnMRT5lnaoR8x4r3pkfH2ic4T3JArclOK4kAaUmg,17261
 azure/ai/evaluation/_model_configurations.py,sha256=MNN6cQlz7P9vNfHmfEKsUcly3j1FEOEFsA8WV7GPuKQ,4043
 azure/ai/evaluation/_user_agent.py,sha256=SgUm6acnwyoENu8KroyaWRrJroJNqLZBccpQoeKyrHw,1144
-azure/ai/evaluation/_version.py,sha256=CPV5vdeD0bAfJPGm-RemVSV56PL9JcRpA5-wuCsNBPc,229
+azure/ai/evaluation/_version.py,sha256=6wd-PDI7lXxIj0JWkLpHM3nxqs22YSfHFt4rjZRC69E,230
 azure/ai/evaluation/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 azure/ai/evaluation/_aoai/__init__.py,sha256=0Ji05ShlsJaytvexXUpCe69t0jSNd3PpNbhr0zCkr6A,265
 azure/ai/evaluation/_aoai/aoai_grader.py,sha256=8mp_dwMK-MdKkoiTud9ra6ExKyYV1SAPXr1m46j4lm4,4434
 azure/ai/evaluation/_aoai/label_grader.py,sha256=5HOLLkiqCOQS5LPJ5Nm0PE5I1uGEhvoi-6DRgG-H1KM,2696
-azure/ai/evaluation/_aoai/score_model_grader.py,sha256=rwSneYpVXemlmmY0aiIBYSnauT_AhgaqGvXoXqhZNHA,3675
+azure/ai/evaluation/_aoai/python_grader.py,sha256=Ef3Rkr2dTi751RbCb9XpqHZgHmN1ueen_w3IUxuek00,3120
+azure/ai/evaluation/_aoai/score_model_grader.py,sha256=jJPZIARbZj6PTd7h072tZf5eFaTfQ-DO-2YmnBwNGRM,3737
 azure/ai/evaluation/_aoai/string_check_grader.py,sha256=5aRMEMoM0FUvxx_ftwySV-KN_Daw3R4-brFaND_NR_E,2321
 azure/ai/evaluation/_aoai/text_similarity_grader.py,sha256=BxJ5Z6npKPkfuVzy84IZXHZVlg4EJrkq2NA8XixBxm4,2889
 azure/ai/evaluation/_azure/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
@@ -23,8 +24,8 @@ azure/ai/evaluation/_common/_experimental.py,sha256=GVtSn9r1CeR_yEa578dJVNDJ3P24
 azure/ai/evaluation/_common/constants.py,sha256=lkdGK6xrMhVogqBudU4B8-6Ko2aSxKl3HzzVTh1D9Ho,2286
 azure/ai/evaluation/_common/evaluation_onedp_client.py,sha256=3HMiG37Cl46q9-kE6zxIEoQbgK96YelX1AFWldfk7Ok,7485
 azure/ai/evaluation/_common/math.py,sha256=d4bwWe35_RWDIZNcbV1BTBbHNx2QHQ4-I3EofDyyNE0,2863
-azure/ai/evaluation/_common/rai_service.py,sha256=sLqX9XVRL3_v5AkrbDc4OPOu7OvHonzBBs-XljI6lyo,35471
-azure/ai/evaluation/_common/utils.py,sha256=zKDsMoALUxvgE6rg5xYBzcqTkDXjWs_uXzAa-ngobuU,26590
+azure/ai/evaluation/_common/rai_service.py,sha256=jyBLRWpaQY2qGumP3JyTrRb3bAIqu5d6CPRtMYaJi5w,35491
+azure/ai/evaluation/_common/utils.py,sha256=GWeNGUdEup2qzmn0N-D1Os_xlpIKFdTe6Y7Qn0AF0uQ,30120
 azure/ai/evaluation/_common/onedp/__init__.py,sha256=C7Ddtjy__BxKkRCydRS7BhtQnM7TFZo179UUVC5krVY,1026
 azure/ai/evaluation/_common/onedp/_client.py,sha256=cE37dQkl6aFfPZD-jyDa1QKUYKe5UQuC3SJX6XndFFY,6667
 azure/ai/evaluation/_common/onedp/_configuration.py,sha256=F_KmJnzEgtmPTZViFS2nTMtKYHxi_YOn81BDx24L3gI,3629
@@ -97,11 +98,11 @@ azure/ai/evaluation/_converters/_models.py,sha256=WjAJntMPlc_CpnHZ2pFqW5yezlvfGJ
 azure/ai/evaluation/_converters/_sk_services.py,sha256=NfjflVgeJUF0MrvAiUd_uF2magn38Q_MKmHzaY41vOA,18239
 azure/ai/evaluation/_evaluate/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
 azure/ai/evaluation/_evaluate/_eval_run.py,sha256=ZlDvTNDiMSZ2VfzVicPmEGx65LL3LmcKcPWft6XjWcA,21991
-azure/ai/evaluation/_evaluate/_evaluate.py,sha256=Gl6_w-j91AqsA_GiIzxmOLfWD25HUf41EyIcnaITi1U,51371
-azure/ai/evaluation/_evaluate/_evaluate_aoai.py,sha256=jcwgDpwZ3BphUYLOQR0eu12xGbGv9wXxnHdc7O1eNNY,26128
-azure/ai/evaluation/_evaluate/_utils.py,sha256=jJ6fuRcD4tUwRiO62uTmrljIDN5NgG_j63_Z7wImYnE,19170
+azure/ai/evaluation/_evaluate/_evaluate.py,sha256=XlJT0VWuNDIRSee7z63p5AP3dRNwZ7vJbSYOUGJfD_E,56540
+azure/ai/evaluation/_evaluate/_evaluate_aoai.py,sha256=-5oR9rPzXns6DQMiwJAp0iBHdK74JtlpTlx-xoGDhmo,26222
+azure/ai/evaluation/_evaluate/_utils.py,sha256=e9Jha5zAkDaidZjFf1-FnNSmT02BjYWkleV9P1E0Iq8,19095
 azure/ai/evaluation/_evaluate/_batch_run/__init__.py,sha256=cPLi_MJ_pCp8eKBxJbiSoxgTnN3nDLuaP57dMkKuyhg,552
-azure/ai/evaluation/_evaluate/_batch_run/_run_submitter_client.py,sha256=myLUp8S650elK5i9LmKXW2b7MRES1mUO_HmBbOZyzCk,4645
+azure/ai/evaluation/_evaluate/_batch_run/_run_submitter_client.py,sha256=2Rl4j_f4qK6_J-Gl_qUV-4elpWbegWzIkJuQOdPP-ig,7046
 azure/ai/evaluation/_evaluate/_batch_run/batch_clients.py,sha256=dTZYdQGweGzEN6OHtn1jOmGG767AJ7RJwfHoCCeRddg,2761
 azure/ai/evaluation/_evaluate/_batch_run/code_client.py,sha256=n4JxDAFNnetfpAj4FyhtZms3kuGmDWXCBOogqeO4F98,8607
 azure/ai/evaluation/_evaluate/_batch_run/eval_run_context.py,sha256=Z0m6nDNF7TiIIW1woC7TCeuh7XIBAwTNFfPKXJhE7_k,4076
@@ -110,74 +111,74 @@ azure/ai/evaluation/_evaluate/_batch_run/target_run_context.py,sha256=TrZ_IkbU8D
 azure/ai/evaluation/_evaluate/_telemetry/__init__.py,sha256=KARq4sFLAh72Rhr8nefbOLXFnKqdO6i6zAYRqr4SWJ4,3475
 azure/ai/evaluation/_evaluators/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
 azure/ai/evaluation/_evaluators/_bleu/__init__.py,sha256=quKKO0kvOSkky5hcoNBvgBuMeeVRFCE9GSv70mAdGP4,260
-azure/ai/evaluation/_evaluators/_bleu/_bleu.py,sha256=DEwO5ZeAlp_e84F50f_gcVsaBgOw6PUepZJ3hbhnd4E,4962
+azure/ai/evaluation/_evaluators/_bleu/_bleu.py,sha256=CJOmTL_5vC477Q4dAKTArApj2d4UZVHuz_KB8Aw7ZMk,4935
 azure/ai/evaluation/_evaluators/_code_vulnerability/__init__.py,sha256=zRHHxYA6CI72iqZaZz9eSbDHwhhjp5hjicEK_RWXlL0,109
-azure/ai/evaluation/_evaluators/_code_vulnerability/_code_vulnerability.py,sha256=gyglQMaUnqar3ww0kECISki30ocNk8sF-cGc0jNGf0I,4642
+azure/ai/evaluation/_evaluators/_code_vulnerability/_code_vulnerability.py,sha256=KrOtAxtipZf2FDQ9uiHQ4pTAzD-aev14EPgaQUdFVNA,4890
 azure/ai/evaluation/_evaluators/_coherence/__init__.py,sha256=GRqcSCQse02Spyki0UsRNWMIXiea2lLtPPXNGvkJzQ0,258
-azure/ai/evaluation/_evaluators/_coherence/_coherence.py,sha256=Ss3J-n-j7bf9n721YbK4b7kjvuO1A-x_9dd_xKIkOrw,5871
+azure/ai/evaluation/_evaluators/_coherence/_coherence.py,sha256=MqifhqPRbvMH1AsvAO8D7sbN1xSZ7VtkiWQIFFrR0_8,5844
 azure/ai/evaluation/_evaluators/_coherence/coherence.prompty,sha256=ANvh9mDFW7KMejrgdWqBLjj4SIqEO5WW9gg5pE0RLJk,6798
 azure/ai/evaluation/_evaluators/_common/__init__.py,sha256=xAymP_CZy4aPzWplMdXgQUQVDIUEMI-0nbgdm_umFYY,498
-azure/ai/evaluation/_evaluators/_common/_base_eval.py,sha256=hLC-4Q7tpHvZTj5vrFQ5IIpLY09yAsTq9_AyxUyjwaY,25921
+azure/ai/evaluation/_evaluators/_common/_base_eval.py,sha256=qv1W6gQR5-SLq6hTvDBqSusaPzOX6I6mH8feI2JFSOk,26050
 azure/ai/evaluation/_evaluators/_common/_base_multi_eval.py,sha256=yYFpoCDe2wMFQck0ykbX8IJBBidk6NT1wUTkVFlVSy8,2728
 azure/ai/evaluation/_evaluators/_common/_base_prompty_eval.py,sha256=11ZMNPLF50O7om7UOq8BzeWiarVpU9qnC1exotnw1Lo,6866
-azure/ai/evaluation/_evaluators/_common/_base_rai_svc_eval.py,sha256=N_ZxXFJ_6IJYh5RzqJjyHPjxgbFXhjPCN6HRxn7wdqA,8628
+azure/ai/evaluation/_evaluators/_common/_base_rai_svc_eval.py,sha256=mW8jErfouw1rVST2YO5nWEdMwIaXWCaw46-s8-Avilc,9068
 azure/ai/evaluation/_evaluators/_common/_conversation_aggregators.py,sha256=gjDBjRxJKwaHbshWH0j2idjlzfzNMnT9a9RL0fQiKeM,2129
 azure/ai/evaluation/_evaluators/_content_safety/__init__.py,sha256=PEYMIybfP64f7byhuTaiq4RiqsYbjqejpW1JsJIG1jA,556
-azure/ai/evaluation/_evaluators/_content_safety/_content_safety.py,sha256=RNrEVw2-dnKmmI8KPjlnhrN08spJ2Yre3KHppAdNwDQ,6959
-azure/ai/evaluation/_evaluators/_content_safety/_hate_unfairness.py,sha256=zqDOdZ0HMGaQnIRlC9Eu25LaKuqm0igSyL6a3OYrURc,7323
-azure/ai/evaluation/_evaluators/_content_safety/_self_harm.py,sha256=cCQWySBudV9CpUdpFoZnllOhm1cEVylHtrpynHQ5rz0,6119
-azure/ai/evaluation/_evaluators/_content_safety/_sexual.py,sha256=hq5QZ1Lhn3ugnX7jqrfD2K8pRgzZCgNzekk7hl2ViMs,6670
-azure/ai/evaluation/_evaluators/_content_safety/_violence.py,sha256=3fCjKT6bj-hKhV95cpa8YyTr1stGY5MzJUF3bnjfjSE,6740
+azure/ai/evaluation/_evaluators/_content_safety/_content_safety.py,sha256=0JVsptT5koRCXOhcd5_NIvQPQxMRHhlCfisc_KRKE6k,7502
+azure/ai/evaluation/_evaluators/_content_safety/_hate_unfairness.py,sha256=j2WNVtDuacrNMO5NbKjwxtugvOlG0Mroo_RIxfeZhFA,7365
+azure/ai/evaluation/_evaluators/_content_safety/_self_harm.py,sha256=Qof3CIDOY3X71Jy55ZT4Pv5hrk27DLmYBJqo9NKA6ZY,6149
+azure/ai/evaluation/_evaluators/_content_safety/_sexual.py,sha256=ssBNqH7lSJ6Ifw87lT6z3vo1v9oepjWXECmRs5vznKE,6707
+azure/ai/evaluation/_evaluators/_content_safety/_violence.py,sha256=MDHnSbefslrlarkh5rcjJVIwpkMl9oZJBJLra5XylDg,6779
 azure/ai/evaluation/_evaluators/_document_retrieval/__init__.py,sha256=wEAbjkMQTlwmRsa7_XeOP0EAT1g7AJyaYlvPdZElAb4,385
-azure/ai/evaluation/_evaluators/_document_retrieval/_document_retrieval.py,sha256=hWFEolGdhcNH2G1TIRBhxGGcphO61ONDnmoPSAsz4po,20186
+azure/ai/evaluation/_evaluators/_document_retrieval/_document_retrieval.py,sha256=fEkwnuvOCLUiyNMf1c_BmdLwR0ECgieRtAri_CPE9PI,20338
 azure/ai/evaluation/_evaluators/_eci/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-azure/ai/evaluation/_evaluators/_eci/_eci.py,sha256=WH99JeLmwGVtI2kHcpAM7oZXZbQdjREBZZjeOduP3Tw,3030
+azure/ai/evaluation/_evaluators/_eci/_eci.py,sha256=3Zrf6xxaw7e2adQLb0TM_KFWf-4RSTnjI4uYfHev2tQ,3103
 azure/ai/evaluation/_evaluators/_f1_score/__init__.py,sha256=aEVbO7iMoF20obdpLQKcKm69Yyu3mYnblKELLqu8OGI,260
-azure/ai/evaluation/_evaluators/_f1_score/_f1_score.py,sha256=hEs07Yq8D08RLOJyIRB_E2iHwe8Kpcoo8bL4ORHWTE8,6966
+azure/ai/evaluation/_evaluators/_f1_score/_f1_score.py,sha256=8xKB0SDqseQ2Vnhf3CNftXVMjV6co8h-gfKOTcmNJJw,6940
 azure/ai/evaluation/_evaluators/_fluency/__init__.py,sha256=EEJw39xRa0bOAA1rELTTKXQu2s60n_7CZQRD0Gu2QVw,259
-azure/ai/evaluation/_evaluators/_fluency/_fluency.py,sha256=s_--X5B0sLMOf6QcYqzWnRPwXDaZXy3BRBjVOghHwkE,5579
+azure/ai/evaluation/_evaluators/_fluency/_fluency.py,sha256=iIgN2DQDvAoZldeCYRv8Z-kzNvEPsS4KEuDQBhXiQog,5552
 azure/ai/evaluation/_evaluators/_fluency/fluency.prompty,sha256=n9v0W9eYwgIO-JSsLTSKEM_ApJuxxuKWQpNblrTEkFY,4861
 azure/ai/evaluation/_evaluators/_gleu/__init__.py,sha256=Ae2EvQ7gqiYAoNO3LwGIhdAAjJPJDfT85rQGKrRrmbA,260
-azure/ai/evaluation/_evaluators/_gleu/_gleu.py,sha256=aNmEBXYOOUgtDMeavnKrVAGa5P02m3Zoh-a7ibObZy8,4911
+azure/ai/evaluation/_evaluators/_gleu/_gleu.py,sha256=bm46V_t4NpIEaAAZMtMAxMMe_u3SgOY0201RihpFxEc,4884
 azure/ai/evaluation/_evaluators/_groundedness/__init__.py,sha256=UYNJUeRvBwcSVFyZpdsf29un5eyaDzYoo3QvC1gvlLg,274
-azure/ai/evaluation/_evaluators/_groundedness/_groundedness.py,sha256=dZaG2_T1UDSQmCPJwr00J3VxkC9t13EYHJ4DPsTYllw,8235
+azure/ai/evaluation/_evaluators/_groundedness/_groundedness.py,sha256=DF1rEC1AZp8yXGVQc4i_0Nn4joKVCas2cBKyVOgJnPg,8208
 azure/ai/evaluation/_evaluators/_groundedness/groundedness_with_query.prompty,sha256=v7TOm75DyW_1gOU6gSiZoPcRnHcJ65DrzR2cL_ucWDY,5814
 azure/ai/evaluation/_evaluators/_groundedness/groundedness_without_query.prompty,sha256=8kNShdfxQvkII7GnqjmdqQ5TNelA2B6cjnqWZk8FFe4,5296
 azure/ai/evaluation/_evaluators/_intent_resolution/__init__.py,sha256=Lr8krXt2yfShFTAuwjTFgrUbO75boLLrRSnF1mriN_Q,280
-azure/ai/evaluation/_evaluators/_intent_resolution/_intent_resolution.py,sha256=jC4eDUIobN9m5qoo1Z2oAEkpSuZLokyZ_AqS0EyjRRI,11386
+azure/ai/evaluation/_evaluators/_intent_resolution/_intent_resolution.py,sha256=3cWMeUSUGJmFtIFLHNH0rHX4KNUfVeermeTJpIRHh4M,11431
 azure/ai/evaluation/_evaluators/_intent_resolution/intent_resolution.prompty,sha256=5xLdYQ9FUfJVNtkbFMjiFhFH17eyRYF4WFIE6_3zvxc,8449
 azure/ai/evaluation/_evaluators/_meteor/__init__.py,sha256=209na3pPsdmcuYpYHUYtqQybCpc3yZkc93HnRdicSlI,266
-azure/ai/evaluation/_evaluators/_meteor/_meteor.py,sha256=CooCk3130gVJwXeIMrxnBDp9EEkzNVvL-MsEomNteXY,5953
+azure/ai/evaluation/_evaluators/_meteor/_meteor.py,sha256=6OkRH78wfn61lkR-1MuDw2J980SCm7LU-B567cS_8ho,5926
 azure/ai/evaluation/_evaluators/_protected_material/__init__.py,sha256=eRAQIU9diVXfO5bp6aLWxZoYUvOsrDIfy1gnDOeNTiI,109
-azure/ai/evaluation/_evaluators/_protected_material/_protected_material.py,sha256=jugv82Ovn35m6OGWHCrbmTy618hds1j8TnX5sdyKpEU,5216
+azure/ai/evaluation/_evaluators/_protected_material/_protected_material.py,sha256=95vJ55K3ONCmF4MP_q4FiuJhe8iejLHOA1k1o7DtWKo,5407
 azure/ai/evaluation/_evaluators/_qa/__init__.py,sha256=bcXfT--C0hjym2haqd1B2-u9bDciyM0ThOFtU1Q69sk,244
-azure/ai/evaluation/_evaluators/_qa/_qa.py,sha256=FzUq5vZolZIcrmIfc9XyT0-RfpAcfOszE6slCkVtOSg,6240
+azure/ai/evaluation/_evaluators/_qa/_qa.py,sha256=y8Magyzb2DESoN6vFllJkf8bLZ28UFFYyKVHCv1ah3o,6270
 azure/ai/evaluation/_evaluators/_relevance/__init__.py,sha256=JlxytW32Nl8pbE-fI3GRpfgVuY9EG6zxIAn5VZGSwyc,265
-azure/ai/evaluation/_evaluators/_relevance/_relevance.py,sha256=Prb-vx98IpzxFHnhpZ-tial9dG4HrrrFa1KbmCqTeUY,6517
-azure/ai/evaluation/_evaluators/_relevance/relevance.prompty,sha256=VHKzVlC2Cv1xuholgIGmerPspspAI0t6IgJ2cxOuYDE,4811
+azure/ai/evaluation/_evaluators/_relevance/_relevance.py,sha256=TwApL9yRB47O_n8OOGhg7E2WLpNAWWX6Pqiku3PIR2Q,8944
+azure/ai/evaluation/_evaluators/_relevance/relevance.prompty,sha256=1F45mS6phDhUCjWD7AVAeCJE8UJHytCgRwHrndcH99E,6462
 azure/ai/evaluation/_evaluators/_response_completeness/__init__.py,sha256=U3eqkQQAgRif46B6UGdq3yWefgbkZGJ3ZE2sKoZQDlU,292
-azure/ai/evaluation/_evaluators/_response_completeness/_response_completeness.py,sha256=9_zalnYiCEPdQLvXKWAmNdqohUjB5u6UuZOM0Ko50Tk,7883
+azure/ai/evaluation/_evaluators/_response_completeness/_response_completeness.py,sha256=gNZHxw-sk99DDvwhLGh3Az4RVfauPv9QMRt6d2lyNoY,7922
 azure/ai/evaluation/_evaluators/_response_completeness/response_completeness.prompty,sha256=25PqzWWtpwvsKNnBGDNfqsKKo2RpyeiIFzvK8sauPDg,7520
 azure/ai/evaluation/_evaluators/_retrieval/__init__.py,sha256=kMu47ZyTZ7f-4Yh6H3KHxswmxitmPJ8FPSk90qgR0XI,265
-azure/ai/evaluation/_evaluators/_retrieval/_retrieval.py,sha256=ShAHEwdLeUUP7WpzM-W7PauPj7sNiUgcKd0EoTDS4Fg,6281
+azure/ai/evaluation/_evaluators/_retrieval/_retrieval.py,sha256=hiCVZOg_dn7q87OPdizhdYqK3SkK46evpEUBphNfIBY,6254
 azure/ai/evaluation/_evaluators/_retrieval/retrieval.prompty,sha256=_YVoO4Gt_WD42bUcj5n6BDW0dMUqNf0yF3Nj5XMOX2c,16490
 azure/ai/evaluation/_evaluators/_rouge/__init__.py,sha256=kusCDaYcXogDugGefRP8MQSn9xv107oDbrMCqZ6K4GA,291
-azure/ai/evaluation/_evaluators/_rouge/_rouge.py,sha256=_qPmSLmp-6NH0LuEGccfgpbYVmrsKCMzuAs4cdpKUgM,10060
+azure/ai/evaluation/_evaluators/_rouge/_rouge.py,sha256=6xfAc18Cqa2bq_GtGTKUEIZdWFqdjAYPjsqNl1ok10E,10033
 azure/ai/evaluation/_evaluators/_service_groundedness/__init__.py,sha256=0DODUGTOgaYyFbO9_zxuwifixDL3SIm3EkwP1sdwn6M,288
-azure/ai/evaluation/_evaluators/_service_groundedness/_service_groundedness.py,sha256=7bKXq-3T0wImNomoEX0to3R4zukNYEqocpAu5uxzPBQ,8152
+azure/ai/evaluation/_evaluators/_service_groundedness/_service_groundedness.py,sha256=qdwVlgoPB870mcwDzDfsfmWlSocpyQJPvQxROGaiTXg,8158
 azure/ai/evaluation/_evaluators/_similarity/__init__.py,sha256=V2Mspog99_WBltxTkRHG5NpN5s9XoiTSN4I8POWEkLA,268
-azure/ai/evaluation/_evaluators/_similarity/_similarity.py,sha256=_bj1YespJ8ZMNq7u-5Ktw5w6f3U98raP9nHMgI6tZls,5430
+azure/ai/evaluation/_evaluators/_similarity/_similarity.py,sha256=W86KDcAjf6_tXUVEYM80mmWNHVJ2O_WQD1AT6yRQ6r8,5460
 azure/ai/evaluation/_evaluators/_similarity/similarity.prompty,sha256=eoludASychZoGL625bFCaZai-OY7DIAg90ZLax_o4XE,4594
 azure/ai/evaluation/_evaluators/_task_adherence/__init__.py,sha256=9HtNrG7yYX0Ygq3cZoS_0obAvGgmy5HWcsBcPKoB15c,271
-azure/ai/evaluation/_evaluators/_task_adherence/_task_adherence.py,sha256=VokR01FyGV3V5wLkbdOB6k_OInhhBO2jPwjYE9oyYxA,10208
-azure/ai/evaluation/_evaluators/_task_adherence/task_adherence.prompty,sha256=tOgTrDO41jsFHloabSBCWcbwKB1MtGGxHH_pyFIn2Vk,5350
+azure/ai/evaluation/_evaluators/_task_adherence/_task_adherence.py,sha256=DjlgI9LWhVZEJAnLhh4X2rH76ON4ORVfWpoVreSsOfE,11054
+azure/ai/evaluation/_evaluators/_task_adherence/task_adherence.prompty,sha256=b1beQUEBPFLkcJUhiVvH7s07RArcPRVtHvXKKZKHbPg,12795
 azure/ai/evaluation/_evaluators/_tool_call_accuracy/__init__.py,sha256=vYB4Y_3n1LqTiEeZB1O1A0b14wpURBwtW0wPEN2FG9Q,288
-azure/ai/evaluation/_evaluators/_tool_call_accuracy/_tool_call_accuracy.py,sha256=HJ6Ehbpks1e6Si4zCXMjHDMAos5qehyA-ARRuE-2nBI,18317
-azure/ai/evaluation/_evaluators/_tool_call_accuracy/tool_call_accuracy.prompty,sha256=L2EyEj4jHLE_RPzO6a1m7gakX3N9eiQ4sbwnFEwbTsw,3895
+azure/ai/evaluation/_evaluators/_tool_call_accuracy/_tool_call_accuracy.py,sha256=lyqy4Gm1n0_6ixrYLb39wSA6a0B-sH8GspbdZL2QiTY,17399
+azure/ai/evaluation/_evaluators/_tool_call_accuracy/tool_call_accuracy.prompty,sha256=mJ8fILFrJ8AjJ-kNwDk_zrOUxWxYBBJVHeL5_6MX48M,10488
 azure/ai/evaluation/_evaluators/_ungrounded_attributes/__init__.py,sha256=wGZBd_cRDgkuS-0HV9qm81dHK7ScYdKd98xLPtk6EwQ,118
-azure/ai/evaluation/_evaluators/_ungrounded_attributes/_ungrounded_attributes.py,sha256=G4eZ72QfVmjtwfMiD7UdfDsB4XCPAXuw06UtNvWwkHk,4408
+azure/ai/evaluation/_evaluators/_ungrounded_attributes/_ungrounded_attributes.py,sha256=5Y4JMUGRkGiMyBg95OgMVf2AFLEtKnP_GbpeDqwxIGE,4656
 azure/ai/evaluation/_evaluators/_xpia/__init__.py,sha256=VMEL8WrpJQeh4sQiOLzP7hRFPnjzsvwfvTzaGCVJPCM,88
-azure/ai/evaluation/_evaluators/_xpia/xpia.py,sha256=aiBKbs0sKeTizOhXHyEbmz64XAE66SSyU0QNIAhQe4w,6564
+azure/ai/evaluation/_evaluators/_xpia/xpia.py,sha256=YJqcl86-IJWxKVKNyq5lTdDyoeRRyv632JUxGkBV1e8,6610
 azure/ai/evaluation/_legacy/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
 azure/ai/evaluation/_legacy/_adapters/__init__.py,sha256=LGQk1gGjDTCtd-vEQj6ObYyK7Mff9zL1jFOq7iTrOSU,450
 azure/ai/evaluation/_legacy/_adapters/_check.py,sha256=ojKjHEtjzfg9QA4o4vH4cLVpdw1F-7snxCQ-sdjRFig,426
@@ -192,14 +193,14 @@ azure/ai/evaluation/_legacy/_adapters/tracing.py,sha256=jm-lkzLA-agRY1meIzs9mFrz
 azure/ai/evaluation/_legacy/_adapters/types.py,sha256=q7n0TtpFxd1WttbUR_Q8ODd8bTcMaJjIrxLXx1onirc,447
 azure/ai/evaluation/_legacy/_adapters/utils.py,sha256=2KdYqfeuHLcfqk1qJRviNoqqsghxBZNmyoGcUTNphl0,1306
 azure/ai/evaluation/_legacy/_batch_engine/__init__.py,sha256=NNX2DhtPVzJCX8kR_QzZ6EkUsdGifvwip2LHEcRwy1Y,594
-azure/ai/evaluation/_legacy/_batch_engine/_config.py,sha256=-B37cIbWOWEB3kTaNjHGLfQNbLa-XAP1gWm0Kvyv82k,1724
-azure/ai/evaluation/_legacy/_batch_engine/_engine.py,sha256=Q-Z7Pvz1gsVCOs0LEV619CMA5C0SQuqzj2UNFqp9LBY,16636
+azure/ai/evaluation/_legacy/_batch_engine/_config.py,sha256=9fdRz5YVdf_95mCOugiJuna2pYMEmWKcsWaZCT4IwXM,1820
+azure/ai/evaluation/_legacy/_batch_engine/_engine.py,sha256=MY7nHt36ABwPaj47agPJXF2bn3GHGGHBKNkOS4qAznw,19580
 azure/ai/evaluation/_legacy/_batch_engine/_exceptions.py,sha256=_QQLowht6ww4wBJbShQBo00Y8HFdaWh-dWd44sGvJBc,2870
 azure/ai/evaluation/_legacy/_batch_engine/_openai_injector.py,sha256=jP_ZHre2REdQh2l2JJNuP6arW9pHxOlc-WHG5jLnX6g,5059
-azure/ai/evaluation/_legacy/_batch_engine/_result.py,sha256=tPnI7Ab2t89ri4kvplJPvKBb0BOrMDQm3HAPXZuhp60,3471
-azure/ai/evaluation/_legacy/_batch_engine/_run.py,sha256=iNLMtkjvsbgivB59xWuB77kyZKxU40YhwoaJ_djuAcc,4491
+azure/ai/evaluation/_legacy/_batch_engine/_result.py,sha256=mqwCNATvH2Tavpnk_u1000HfXLauNMgcPT9dpqKh4L4,3516
+azure/ai/evaluation/_legacy/_batch_engine/_run.py,sha256=-fXq3s6_anZ3Qf0i16D_HNGzgjPKCiNwXaUz3qUG3EQ,4537
 azure/ai/evaluation/_legacy/_batch_engine/_run_storage.py,sha256=KjiKaSjT16L_wLYrZpIeBANtin3fa4Gqd3L-Xjw-59I,3418
-azure/ai/evaluation/_legacy/_batch_engine/_run_submitter.py,sha256=lI_bhKEWQRAyZHG_G56jf0JM2YbSI6ycH4TBhIM2NGY,11085
+azure/ai/evaluation/_legacy/_batch_engine/_run_submitter.py,sha256=wtRQ7COg3fstHqcjhCf-M-Au3G6OVE0sDlCM-ELNOjs,11064
 azure/ai/evaluation/_legacy/_batch_engine/_status.py,sha256=xSpJaMmBroGOL8U_iTpAr_PgyNKaxfawqak6TpuUrkk,780
 azure/ai/evaluation/_legacy/_batch_engine/_trace.py,sha256=xh52vKgs8TKYj1WlqcenlOXiPmcfgdPei2P8BLAIO5g,4430
 azure/ai/evaluation/_legacy/_batch_engine/_utils.py,sha256=pBOw5WTt64POR1c6yxGH5D5MhUxvXcMKJ2Rzzqth0XQ,2957
@@ -216,41 +217,41 @@ azure/ai/evaluation/_legacy/prompty/_utils.py,sha256=NCuZYuAZSguDtFsLAcgVwwPyAPM
 azure/ai/evaluation/_legacy/prompty/_yaml_utils.py,sha256=pVL6xgTHC3AKKD5plJ4d6hiBuComaOlUww1uqqDQlB4,3350
 azure/ai/evaluation/_safety_evaluation/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
 azure/ai/evaluation/_safety_evaluation/_generated_rai_client.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-azure/ai/evaluation/_safety_evaluation/_safety_evaluation.py,sha256=aGzMJPzB_6NYtMcnc-8KMCGuFvONMXSdg6F4bs6XUbs,44856
+azure/ai/evaluation/_safety_evaluation/_safety_evaluation.py,sha256=OlylVGIM8aI7cX8qsUzFEZuylS5mhWThhvJ6qS7_FfI,45047
 azure/ai/evaluation/_vendor/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
 azure/ai/evaluation/_vendor/rouge_score/__init__.py,sha256=03OkyfS_UmzRnHv6-z9juTaJ6OXJoEJM989hgifIZbc,607
 azure/ai/evaluation/_vendor/rouge_score/rouge_scorer.py,sha256=DtNSeshHipzc6vFnvx7kbs5viXe4LNq-ZrgllFvfR4U,11299
 azure/ai/evaluation/_vendor/rouge_score/scoring.py,sha256=0sqdiNE-4R_EmTTqyWL9_DAOgl54250H5004tZDGxEE,1878
 azure/ai/evaluation/_vendor/rouge_score/tokenize.py,sha256=IyHVsWY6IFFZdB23cLiJs8iBZ0DXk1mQlWE1xtdjuuk,1826
 azure/ai/evaluation/_vendor/rouge_score/tokenizers.py,sha256=3_-y1TyvyluHuERhSJ5CdXSwnpcMA7aAKU6PCz9wH_Q,1745
-azure/ai/evaluation/red_team/__init__.py,sha256=fWI2mik_8NQmR-cfNdbPL8Xi9z15OFnxCZ1SPzSYW4Q,627
+azure/ai/evaluation/red_team/__init__.py,sha256=goB0RudQS4_BFvhvb634RXGR2FoZ49Q-fDfQfHDtucQ,632
 azure/ai/evaluation/red_team/_attack_objective_generator.py,sha256=3l5cOfWCfX9-fdFkBdJ0yONv7kL7w6TyghzPVErYN_w,11070
 azure/ai/evaluation/red_team/_attack_strategy.py,sha256=5VEES4AdiHc057Bt8STAKpKvpJ7gKPGxjkh6kjlQ2og,1488
 azure/ai/evaluation/red_team/_callback_chat_target.py,sha256=-kd5voHTnWtTwQVXr3fl_OaxKXLic-GnwELN_e9SG_g,3016
 azure/ai/evaluation/red_team/_default_converter.py,sha256=tewcQgYNqQA8EJ0IIDOA3HhZOR7vpCn8E1hP787gg9k,776
-azure/ai/evaluation/red_team/_red_team.py,sha256=xe0utQlVa7GyJ-u_wCbZQ_N7QeznjyoXpPwGB03FKsQ,162020
-azure/ai/evaluation/red_team/_red_team_result.py,sha256=QIf8L3hMaTHCo3FGfhBTrfaM6lWZ6UoQdFXyheAXZsM,17014
+azure/ai/evaluation/red_team/_red_team.py,sha256=Hn1jbyd2ywZQ4XYirTVJxIHee9xfauUMzeu3-Jov6ZA,177525
+azure/ai/evaluation/red_team/_red_team_result.py,sha256=9DM8vDQWDhQ1TBj2KsQCCd5fGAh2gZBeT4evJnsq0Vk,17410
 azure/ai/evaluation/red_team/_agent/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
 azure/ai/evaluation/red_team/_agent/_agent_functions.py,sha256=kLV2lQ5PHMucGK9IsrnZsmSvlhL2fhgzxa1G0NPF6eM,10482
 azure/ai/evaluation/red_team/_agent/_agent_tools.py,sha256=-ClGcNexUYa6_SxBPERAl2u4LgR0UP5Dk0TeYfUcBW8,20653
 azure/ai/evaluation/red_team/_agent/_agent_utils.py,sha256=3wtUg0BUp68l5Vm01K3zjzd1CKKt_N2Xd295yY1itdo,3224
 azure/ai/evaluation/red_team/_agent/_semantic_kernel_plugin.py,sha256=Q-9uVkIM9Hq63pXhnxg6vwmIf9gTVXmmnC3c3ikbO0w,10601
 azure/ai/evaluation/red_team/_utils/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
-azure/ai/evaluation/red_team/_utils/_rai_service_eval_chat_target.py,sha256=Deel5fvuIc-Zd6cruPWVg8X7z7jUJi2dOWGLxhNmOr8,4951
+azure/ai/evaluation/red_team/_utils/_rai_service_eval_chat_target.py,sha256=mC3MmSyfTvyKzZ0p4_bQ2lDh7Sk_v4vLLRcJ0iHh3mw,4940
 azure/ai/evaluation/red_team/_utils/_rai_service_target.py,sha256=BsSffRght1caZh9EsUpRcb8fh5W78ORmTUE7X9XvWd0,29811
 azure/ai/evaluation/red_team/_utils/_rai_service_true_false_scorer.py,sha256=_NZ1OGgXPtKPaOqRjOr-59JguHT_EOfeFuZUQ5FmwAE,4119
-azure/ai/evaluation/red_team/_utils/constants.py,sha256=bd2bQNOsDpstgDBtapnRe8guNzNJjGRotHtWF9bxlho,1992
+azure/ai/evaluation/red_team/_utils/constants.py,sha256=Lujaa8X72lieAiYK0TLn59fErb1v9hWAI8JlMpmM92w,1948
 azure/ai/evaluation/red_team/_utils/formatting_utils.py,sha256=zoTywXnslhQBUz2NLowny6Q0FclijDxiahsuoON-GQs,6263
 azure/ai/evaluation/red_team/_utils/logging_utils.py,sha256=1EK7xRO0eA0nKJmqz7WhMwjP8M3i1je1KxHdGfH9HVI,4775
 azure/ai/evaluation/red_team/_utils/metric_mapping.py,sha256=TU9Z9umtjwmJy3SQNqbc2Fj-oJUX_7rFlg1NEGXaSK4,2130
 azure/ai/evaluation/red_team/_utils/strategy_utils.py,sha256=gW0cfsB8alXTIV02RHNVsz7vmQLjq7SXNf8ZHY0_OHs,8088
 azure/ai/evaluation/simulator/__init__.py,sha256=JbrPZ8pvTBalyX94SvZ9btHNoovX8rbZV03KmzxxWys,552
 azure/ai/evaluation/simulator/_adversarial_scenario.py,sha256=ISMjXfcmquvuBhM8l2u_X3jbEbNa7F7dR-AwgKNaJw0,1884
-azure/ai/evaluation/simulator/_adversarial_simulator.py,sha256=w1wvDPJgB8uF7xn-0QUPx3lwjj_eTNzB9joFpBAPOUI,25543
+azure/ai/evaluation/simulator/_adversarial_simulator.py,sha256=NuUhI-wzFylCwpQxaQYJ-Q67bQ4dn0Jp70TGHNnsCq0,25711
 azure/ai/evaluation/simulator/_constants.py,sha256=jtsj-XzbseurEAxWmB-iSPmXu7B6ZHrM3bl07j-zruM,875
 azure/ai/evaluation/simulator/_direct_attack_simulator.py,sha256=g3170PdieqzN_98PHVbpmoFKUapLN_Yns_JBF71UNog,11025
-azure/ai/evaluation/simulator/_indirect_attack_simulator.py,sha256=pLBH_HRUGMNbFxDo24dmRynV549kp1dbYrZB9oSr6e8,11236
-azure/ai/evaluation/simulator/_simulator.py,sha256=6738F2ScNO0OCS1hODw_VBE6Ib3nXJErBAOxKHe-8hc,36635
+azure/ai/evaluation/simulator/_indirect_attack_simulator.py,sha256=VPTq33pRiXbiGrUo4UPPvYLSuCK0uR39Ylm0WQ2k0Yc,11810
+azure/ai/evaluation/simulator/_simulator.py,sha256=T1w_mF40KLoYQJNUTVO34D_Vuv1I_O43Ii_9L_4u_ps,37267
 azure/ai/evaluation/simulator/_utils.py,sha256=16NltlywpbMtoFtULwTKqeURguIS1kSKSo3g8uKV8TA,5181
 azure/ai/evaluation/simulator/_conversation/__init__.py,sha256=x8bDZIVm10DynqpfrURbeoidAjYv_EFxWr7G7sFShZA,18236
 azure/ai/evaluation/simulator/_conversation/_conversation.py,sha256=aWiodVvzA9yy1itkoVtW88B4qhEpxpnztx0G1-w7U_Y,7729
@@ -261,17 +262,17 @@ azure/ai/evaluation/simulator/_helpers/__init__.py,sha256=FQwgrJvzq_nv3wF9DBr2py
 azure/ai/evaluation/simulator/_helpers/_language_suffix_mapping.py,sha256=sbKc3O5qsg77LEaSEQfWDfzqEFXVDw612BaDcBo3E7A,1095
 azure/ai/evaluation/simulator/_helpers/_simulator_data_classes.py,sha256=BOttMTec3muMiA4OzwD_iW08GTrhja7PL9XVjRCN3jM,3029
 azure/ai/evaluation/simulator/_model_tools/__init__.py,sha256=soaUHfmd_IK1FINPRKgKens7qKOVw9BZwc7ms7N6zrk,860
-azure/ai/evaluation/simulator/_model_tools/_generated_rai_client.py,sha256=gDP0-WarWmoRkUnj8rqsD0vljYeAagSD8KPA_8jNMUc,7935
+azure/ai/evaluation/simulator/_model_tools/_generated_rai_client.py,sha256=m8VSBeFYyj1OKgOKHEoDKvmYSYlIg6RZkPyqbTWw7y0,7945
 azure/ai/evaluation/simulator/_model_tools/_identity_manager.py,sha256=kRmKm8etMq6fM2PjVKL0P7TtXfhDESNME3PenGTryjU,6475
-azure/ai/evaluation/simulator/_model_tools/_proxy_completion_model.py,sha256=Alk6deMeimSKO0JkxrmO6BzsmMdWFBz7PM_ihKwV9q8,11028
+azure/ai/evaluation/simulator/_model_tools/_proxy_completion_model.py,sha256=GJkxtEHp1lv0kQ1gnK-D04Ci18KFkMQ8MZK_2OgJgWo,11827
 azure/ai/evaluation/simulator/_model_tools/_rai_client.py,sha256=fC38IptUtoumxu2CWLmErNoGxMdVlNr60XbpJeKdQ18,11379
 azure/ai/evaluation/simulator/_model_tools/_template_handler.py,sha256=ghQNP8ur19BfbLilEnIio85RbYwQ8APAm45-iNcimYY,8375
 azure/ai/evaluation/simulator/_model_tools/models.py,sha256=H7tjmj9wzLT-6bI542eAfecOKl1sHBZhcd-YNF522Sg,22372
 azure/ai/evaluation/simulator/_prompty/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 azure/ai/evaluation/simulator/_prompty/task_query_response.prompty,sha256=2BzSqDDYilDushvR56vMRDmqFIaIYAewdUlUZg_elMg,2182
 azure/ai/evaluation/simulator/_prompty/task_simulate.prompty,sha256=NE6lH4bfmibgMn4NgJtm9_l3PMoHSFrfjjosDJEKM0g,939
-azure_ai_evaluation-1.9.0.dist-info/METADATA,sha256=EHztRXYMcujJuH9Vmy5iNk1L7pn4G8eB7JWEsmPc48k,39485
-azure_ai_evaluation-1.9.0.dist-info/NOTICE.txt,sha256=4tzi_Yq4-eBGhBvveobWHCgUIVF-ZeouGN0m7hVq5Mk,3592
-azure_ai_evaluation-1.9.0.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-azure_ai_evaluation-1.9.0.dist-info/top_level.txt,sha256=S7DhWV9m80TBzAhOFjxDUiNbKszzoThbnrSz5MpbHSQ,6
-azure_ai_evaluation-1.9.0.dist-info/RECORD,,
+azure_ai_evaluation-1.10.0.dist-info/METADATA,sha256=jPRl1bvOIg6J2b2pCfoLPp4esbKesiUEFy1bbomwpyQ,42772
+azure_ai_evaluation-1.10.0.dist-info/NOTICE.txt,sha256=4tzi_Yq4-eBGhBvveobWHCgUIVF-ZeouGN0m7hVq5Mk,3592
+azure_ai_evaluation-1.10.0.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+azure_ai_evaluation-1.10.0.dist-info/top_level.txt,sha256=S7DhWV9m80TBzAhOFjxDUiNbKszzoThbnrSz5MpbHSQ,6
+azure_ai_evaluation-1.10.0.dist-info/RECORD,,