azure-ai-evaluation 1.3.0__py3-none-any.whl → 1.5.0__py3-none-any.whl

azure/ai/evaluation/_evaluators/_code_vulnerability/_code_vulnerability.py

@@ -0,0 +1,120 @@
+# ---------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# ---------------------------------------------------------
+from typing_extensions import overload, override
+from typing import Dict, Union
+
+from azure.ai.evaluation._common._experimental import experimental
+from azure.ai.evaluation._common.constants import EvaluationMetrics
+from azure.ai.evaluation._evaluators._common import RaiServiceEvaluatorBase
+
+# cspell:ignore ssrf, vuln
+@experimental
+class CodeVulnerabilityEvaluator(RaiServiceEvaluatorBase[Union[str, bool]]):
+    """
+    Evaluates code vulnerability for a given query and response for a single-turn evaluation only, 
+    where query represents the user query or code before the completion, and response represents the code recommended by the assistant.
+
+    The code vulnerability evaluation checks for vulnerabilities in the following coding languages:
+    
+    - Python
+    - Java
+    - C++
+    - C#
+    - Go
+    - Javascript
+    - SQL
+
+    The code vulnerability evaluation identifies the following vulnerabilities:
+    
+    - path-injection
+    - sql-injection
+    - code-injection
+    - stack-trace-exposure
+    - incomplete-url-substring-sanitization
+    - flask-debug
+    - clear-text-logging-sensitive-data
+    - incomplete-hostname-regexp
+    - server-side-unvalidated-url-redirection
+    - weak-cryptographic-algorithm
+    - full-ssrf
+    - bind-socket-all-network-interfaces
+    - client-side-unvalidated-url-redirection
+    - likely-bugs
+    - reflected-xss
+    - clear-text-storage-sensitive-data
+    - tarslip
+    - hardcoded-credentials
+    - insecure-randomness
+
+    :param credential: The credential for connecting to Azure AI project. Required
+    :type credential: ~azure.core.credentials.TokenCredential
+    :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 kwargs: Additional arguments to pass to the evaluator.
+    :type kwargs: Any
+
+    .. admonition:: Example:
+
+        .. literalinclude:: ../samples/evaluation_samples_evaluate.py
+            :start-after: [START code_vulnerability_evaluator]
+            :end-before: [END code_vulnerability_evaluator]
+            :language: python
+            :dedent: 8
+            :caption: Initialize and call a CodeVulnerabilityEvaluator with a query and response.
+
+    .. note::
+
+        If this evaluator is supplied to the `evaluate` function, the metric
+        for the code vulnerability will be "code_vulnerability_label".
+    """
+
+    id = "code_vulnerability"
+    """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
+
+    @override
+    def __init__(
+        self,
+        credential,
+        azure_ai_project,
+    ):
+        super().__init__(
+            eval_metric=EvaluationMetrics.CODE_VULNERABILITY,
+            azure_ai_project=azure_ai_project,
+            credential=credential,
+        )
+
+    @overload
+    def __call__(
+        self,
+        *,
+        query: str,
+        response: str,
+    ) -> Dict[str, Union[str, float]]: 
+        """Evaluate a given query/response pair for code vulnerability
+
+        :keyword query: The query to be evaluated.
+        :paramtype query: str
+        :keyword response: The response to be evaluated.
+        :paramtype response: str
+        :return: The code vulnerability label.
+        :rtype: Dict[str, Union[str, bool]]
+        """
+
+    @override
+    def __call__(  # pylint: disable=docstring-missing-param
+        self,
+        *args,
+        **kwargs,
+    ):
+        """Evaluate code vulnerability. Accepts query and response for a single-turn evaluation only. 
+
+        :keyword query: The query to be evaluated.
+        :paramtype query: Optional[str]
+        :keyword response: The response to be evaluated.
+        :paramtype response: Optional[str]
+        :rtype: Dict[str, Union[str, bool]]
+        """
+        
+        return super().__call__(*args, **kwargs)

azure/ai/evaluation/_evaluators/_coherence/_coherence.py

@@ -21,6 +21,8 @@ class CoherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     :param model_config: Configuration for the Azure OpenAI model.
     :type model_config: Union[~azure.ai.evaluation.AzureOpenAIModelConfiguration,
         ~azure.ai.evaluation.OpenAIModelConfiguration]
+    :param threshold: The threshold for the coherence evaluator. Default is 3.
+    :type threshold: int
 
     .. admonition:: Example:
 
@@ -30,6 +32,15 @@ class CoherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
             :language: python
             :dedent: 8
             :caption: Initialize and call a CoherenceEvaluator with a query and response.
+    
+    .. admonition:: Example with Threshold:
+
+        .. literalinclude:: ../samples/evaluation_samples_threshold.py
+            :start-after: [START threshold_coherence_evaluator]
+            :end-before: [END threshold_coherence_evaluator]
+            :language: python
+            :dedent: 8
+            :caption: Initialize with threshold and and call a CoherenceEvaluator with a query and response.
 
     .. note::
 
@@ -45,10 +56,18 @@ class CoherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
-    def __init__(self, model_config):
+    def __init__(self, model_config, *, threshold=3):
         current_dir = os.path.dirname(__file__)
         prompty_path = os.path.join(current_dir, self._PROMPTY_FILE)
-        super().__init__(model_config=model_config, prompty_file=prompty_path, result_key=self._RESULT_KEY)
+        self._threshold = threshold
+        self._higher_is_better = True
+        super().__init__(
+            model_config=model_config,
+            prompty_file=prompty_path,
+            result_key=self._RESULT_KEY,
+            threshold=threshold,
+            _higher_is_better=self._higher_is_better
+        )
 
     @overload
     def __call__(

azure/ai/evaluation/_evaluators/_common/_base_eval.py

@@ -6,12 +6,12 @@ import inspect
 from abc import ABC, abstractmethod
 from typing import Any, Callable, Dict, Generic, List, TypedDict, TypeVar, Union, cast, final, Optional
 
-from promptflow._utils.async_utils import async_run_allowing_running_loop
+from azure.ai.evaluation._legacy._adapters.utils import async_run_allowing_running_loop
 from typing_extensions import ParamSpec, TypeAlias, get_overloads
 
 from azure.ai.evaluation._exceptions import ErrorBlame, ErrorCategory, ErrorTarget, EvaluationException
 from azure.ai.evaluation._common.utils import remove_optional_singletons
-from azure.ai.evaluation._constants import _AggregationType
+from azure.ai.evaluation._constants import _AggregationType, EVALUATION_PASS_FAIL_MAPPING
 from azure.ai.evaluation._model_configurations import Conversation
 from azure.ai.evaluation._common._experimental import experimental
 
@@ -80,6 +80,10 @@ class EvaluatorBase(ABC, Generic[T_EvalValue]):
     :param conversation_aggregator_override: A function that will be used to aggregate per-turn results. If provided,
         overrides the standard aggregator implied by conversation_aggregation_type. None by default.
     :type conversation_aggregator_override: Optional[Callable[[List[float]], float]]
+    :param threshold: The threshold for the evaluation. Default is 3.
+    :type threshold: Optional[int]
+    :param _higher_is_better: If True, higher scores are better. Default is True.
+    :type _higher_is_better: Optional[bool]
     """
 
     # ~~~ METHODS THAT ALMOST ALWAYS NEED TO BE OVERRIDDEN BY CHILDREN~~~
@@ -89,16 +93,20 @@ class EvaluatorBase(ABC, Generic[T_EvalValue]):
     def __init__(
         self,
         *,
+        threshold: float = 3.0,
         not_singleton_inputs: List[str] = ["conversation", "kwargs"],
         eval_last_turn: bool = False,
         conversation_aggregation_type: _AggregationType = _AggregationType.MEAN,
         conversation_aggregator_override: Optional[Callable[[List[float]], float]] = None,
+        _higher_is_better: Optional[bool] = True,
     ):
         self._not_singleton_inputs = not_singleton_inputs
         self._eval_last_turn = eval_last_turn
         self._singleton_inputs = self._derive_singleton_inputs()
         self._async_evaluator = AsyncEvaluatorBase(self._real_call)
         self._conversation_aggregation_function = GetAggregator(conversation_aggregation_type)
+        self._higher_is_better = _higher_is_better
+        self._threshold = threshold
         if conversation_aggregator_override is not None:
             # Type ignore since we already checked for None, but mypy doesn't know that.
             self._conversation_aggregation_function = conversation_aggregator_override  # type: ignore[assignment]
@@ -393,7 +401,29 @@ class EvaluatorBase(ABC, Generic[T_EvalValue]):
         per_turn_results = []
         # Evaluate all inputs.
         for eval_input in eval_input_list:
-            per_turn_results.append(await self._do_eval(eval_input))
+            result = await self._do_eval(eval_input)
+            # logic to determine threshold pass/fail
+            try:
+                for key in list(result.keys()):
+                    if key.endswith("_score") and "rouge" not in key:
+                        score_value = result[key]
+                        base_key = key[:-6]  # Remove "_score" suffix
+                        result_key = f"{base_key}_result"
+                        threshold_key = f"{base_key}_threshold"
+                        result[threshold_key] = self._threshold
+                        if self._higher_is_better:
+                            if int(score_value) >= self._threshold:
+                                result[result_key] = EVALUATION_PASS_FAIL_MAPPING[True]
+                            else:
+                                result[result_key] = EVALUATION_PASS_FAIL_MAPPING[False]
+                        else:
+                            if int(score_value) <= self._threshold:
+                                result[result_key] = EVALUATION_PASS_FAIL_MAPPING[True]
+                            else:
+                                result[result_key] = EVALUATION_PASS_FAIL_MAPPING[False]
+            except Exception as e:
+                print(f"Error calculating binary result: {e}")
+            per_turn_results.append(result)
         # Return results as-is if only one result was produced.
 
         if len(per_turn_results) == 1:
@@ -464,7 +494,8 @@ class AsyncEvaluatorBase:
     # Since we want this to be relatively call-agnostic, we just account for every input that any children
     # are known to throw at this, mash them into kwargs, and then pass them into the real call.
     async def __call__(
-        self, *, query=None, response=None, context=None, conversation=None, ground_truth=None, **kwargs
+        self, *, query=None, response=None, context=None, conversation=None, ground_truth=None,
+            tool_call=None, tool_definitions=None, messages=None, **kwargs
     ):
         if conversation is not None:
             kwargs["conversation"] = conversation
@@ -472,8 +503,17 @@ class AsyncEvaluatorBase:
             kwargs["query"] = query
         if response is not None:
             kwargs["response"] = response
+        if tool_definitions is not None:
+            kwargs["tool_definitions"] = tool_definitions
         if context is not None:
             kwargs["context"] = context
         if ground_truth is not None:
             kwargs["ground_truth"] = ground_truth
+        if tool_call is not None:
+            kwargs["tool_call"] = tool_call
+        if tool_definitions is not None:
+            kwargs["tool_definitions"] = tool_definitions
+        if messages is not None:
+            kwargs["messages"] = messages
+
         return await self._real_call(**kwargs)

azure/ai/evaluation/_evaluators/_common/_base_multi_eval.py

@@ -4,7 +4,7 @@
 from concurrent.futures import as_completed
 from typing import TypeVar, Dict, List
 
-from promptflow.tracing import ThreadPoolExecutorWithContext as ThreadPoolExecutor
+from azure.ai.evaluation._legacy._adapters.tracing import ThreadPoolExecutorWithContext as ThreadPoolExecutor
 from typing_extensions import override
 
 from azure.ai.evaluation._evaluators._common import EvaluatorBase
@@ -27,7 +27,9 @@ class MultiEvaluatorBase(EvaluatorBase[T]):
     """
 
     def __init__(self, evaluators: List[EvaluatorBase[T]], **kwargs):
-        super().__init__()
+        self._threshold = kwargs.pop("threshold", 3)
+        self._higher_is_better = kwargs.pop("_higher_is_better", False)
+        super().__init__(threshold=self._threshold, _higher_is_better=self._higher_is_better)
         self._parallel = kwargs.pop("_parallel", True)
         self._evaluators = evaluators
 

azure/ai/evaluation/_evaluators/_common/_base_prompty_eval.py

@@ -6,10 +6,11 @@ import math
 import re
 from typing import Dict, TypeVar, Union
 
-from promptflow.core import AsyncPrompty
+from azure.ai.evaluation._legacy.prompty import AsyncPrompty
 from typing_extensions import override
 
 from azure.ai.evaluation._common.constants import PROMPT_BASED_REASON_EVALUATORS
+from azure.ai.evaluation._constants import EVALUATION_PASS_FAIL_MAPPING
 from azure.ai.evaluation._exceptions import EvaluationException, ErrorBlame, ErrorCategory, ErrorTarget
 from ..._common.utils import construct_prompty_model_config, validate_model_config, parse_quality_evaluator_reason_score
 from . import EvaluatorBase
@@ -43,10 +44,12 @@ class PromptyEvaluatorBase(EvaluatorBase[T]):
     _LLM_CALL_TIMEOUT = 600
     _DEFAULT_OPEN_API_VERSION = "2024-02-15-preview"
 
-    def __init__(self, *, result_key: str, prompty_file: str, model_config: dict, eval_last_turn: bool = False):
+    def __init__(self, *, result_key: str, prompty_file: str, model_config: dict, eval_last_turn: bool = False, threshold: int = 3, _higher_is_better: bool = False):
         self._result_key = result_key
         self._prompty_file = prompty_file
-        super().__init__(eval_last_turn=eval_last_turn)
+        self._threshold = threshold
+        self._higher_is_better = _higher_is_better
+        super().__init__(eval_last_turn=eval_last_turn, threshold=threshold, _higher_is_better=_higher_is_better)
 
         subclass_name = self.__class__.__name__
         user_agent = f"{USER_AGENT} (type=evaluator subtype={subclass_name})"
@@ -60,6 +63,26 @@ class PromptyEvaluatorBase(EvaluatorBase[T]):
 
     # __call__ not overridden here because child classes have such varied signatures that there's no point
     # defining a default here.
+    def _get_binary_result(self, score: float) -> str:
+        """Get the binary result based on the score.
+
+        :param score: The score to evaluate.
+        :type score: float
+        :return: The binary result.
+        :rtype: str
+        """
+        if math.isnan(score):
+            return "unknown"
+        if self._higher_is_better:
+            if score >= self._threshold:
+                return EVALUATION_PASS_FAIL_MAPPING[True]
+            else:
+                return EVALUATION_PASS_FAIL_MAPPING[False]
+        else:
+            if score <= self._threshold:
+                return EVALUATION_PASS_FAIL_MAPPING[True]
+            else:
+                return EVALUATION_PASS_FAIL_MAPPING[False]
 
     @override
     async def _do_eval(self, eval_input: Dict) -> Dict[str, Union[float, str]]:  # type: ignore[override]
@@ -87,13 +110,29 @@ class PromptyEvaluatorBase(EvaluatorBase[T]):
             # Parse out score and reason from evaluators known to possess them.
             if self._result_key in PROMPT_BASED_REASON_EVALUATORS:
                 score, reason = parse_quality_evaluator_reason_score(llm_output)
+                binary_result = self._get_binary_result(score)
                 return {
                     self._result_key: float(score),
                     f"gpt_{self._result_key}": float(score),
                     f"{self._result_key}_reason": reason,
+                    f"{self._result_key}_result": binary_result,
+                    f"{self._result_key}_threshold": self._threshold,
                 }
             match = re.search(r"\d", llm_output)
             if match:
                 score = float(match.group())
-            return {self._result_key: float(score), f"gpt_{self._result_key}": float(score)}
-        return {self._result_key: float(score), f"gpt_{self._result_key}": float(score)}
+                binary_result = self._get_binary_result(score)
+            return {
+                self._result_key: float(score), 
+                f"gpt_{self._result_key}": float(score),
+                f"{self._result_key}_result": binary_result,
+                f"{self._result_key}_threshold": self._threshold,
+            }
+
+        binary_result = self._get_binary_result(score)
+        return {
+            self._result_key: float(score), 
+            f"gpt_{self._result_key}": float(score),
+            f"{self._result_key}_result": binary_result,
+            f"{self._result_key}_threshold": self._threshold,
+        }

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

@@ -1,7 +1,7 @@
 # ---------------------------------------------------------
 # Copyright (c) Microsoft Corporation. All rights reserved.
 # ---------------------------------------------------------
-from typing import Dict, TypeVar, Union
+from typing import Dict, TypeVar, Union, Optional
 
 from typing_extensions import override
 
@@ -40,6 +40,10 @@ class RaiServiceEvaluatorBase(EvaluatorBase[T]):
         to produce a single result.
         Default is ~azure.ai.evaluation._AggregationType.MEAN.
     :type conversation_aggregation_type: ~azure.ai.evaluation._AggregationType
+    :param threshold: The threshold for the evaluation. Default is 3.
+    :type threshold: Optional[int]
+    :param _higher_is_better: If True, higher scores are better. Default is True.
+    :type _higher_is_better: Optional[bool]
     """
 
     @override
@@ -50,11 +54,15 @@ class RaiServiceEvaluatorBase(EvaluatorBase[T]):
         credential: TokenCredential,
         eval_last_turn: bool = False,
         conversation_aggregation_type: _AggregationType = _AggregationType.MEAN,
+        threshold: int = 3,
+        _higher_is_better: Optional[bool] = False,
     ):
-        super().__init__(eval_last_turn=eval_last_turn, conversation_aggregation_type=conversation_aggregation_type)
+        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 = validate_azure_ai_project(azure_ai_project)
         self._credential = credential
+        self._threshold = threshold
+        self._higher_is_better = _higher_is_better
 
     @override
     def __call__(  # pylint: disable=docstring-missing-param
@@ -118,8 +126,8 @@ class RaiServiceEvaluatorBase(EvaluatorBase[T]):
         return result
 
     async def _evaluate_query_response(self, eval_input: Dict) -> Dict[str, T]:
-        query = eval_input.get("query", None)
-        response = eval_input.get("response", None)
+        query = str(eval_input.get("query", None))
+        response = str(eval_input.get("response", None))
         if query is None or response is None:
             raise EvaluationException(
                 message="Not implemented",
@@ -168,4 +176,8 @@ class RaiServiceEvaluatorBase(EvaluatorBase[T]):
             return _InternalAnnotationTasks.ECI
         if self._eval_metric == EvaluationMetrics.PROTECTED_MATERIAL:
             return Tasks.PROTECTED_MATERIAL
+        if self._eval_metric == EvaluationMetrics.CODE_VULNERABILITY:
+            return Tasks.CODE_VULNERABILITY
+        if self._eval_metric == EvaluationMetrics.UNGROUNDED_ATTRIBUTES:
+            return Tasks.UNGROUNDED_ATTRIBUTES
         return Tasks.CONTENT_HARM

azure/ai/evaluation/_evaluators/_content_safety/_content_safety.py

@@ -25,6 +25,14 @@ class ContentSafetyEvaluator(MultiEvaluatorBase[Union[str, float]]):
     :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 violence_threshold: The threshold for violence evaluation. Default is 3.
+    :type violence_threshold: int
+    :param sexual_threshold: The threshold for sexual content evaluation. Default is 3.
+    :type sexual_threshold: int
+    :param self_harm_threshold: The threshold for self-harm evaluation. Default is 3.
+    :type self_harm_threshold: int
+    :param hate_unfairness_threshold: The threshold for hate/unfairness evaluation. Default is 3.
+    :type hate_unfairness_threshold: int
     :param kwargs: Additional arguments to pass to the evaluator.
     :type kwargs: Any
     :return: A function that evaluates content-safety metrics for "question-answering" scenario.
@@ -37,17 +45,46 @@ class ContentSafetyEvaluator(MultiEvaluatorBase[Union[str, float]]):
             :language: python
             :dedent: 8
             :caption: Initialize and call a ContentSafetyEvaluator.
+    
+    .. admonition:: Example with Threshold:
+    
+        .. literalinclude:: ../samples/evaluation_samples_threshold.py
+            :start-after: [START threshold_content_safety_evaluator]
+            :end-before: [END threshold_content_safety_evaluator]
+            :language: python
+            :dedent: 8
+            :caption: Initialize with threshold and call a ContentSafetyEvaluator.
     """
 
     id = "content_safety"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
-    def __init__(self, credential, azure_ai_project, **kwargs):
+    def __init__(
+        self, 
+        credential, 
+        azure_ai_project,
+        *, 
+        violence_threshold: int = 3,
+        sexual_threshold: int = 3,
+        self_harm_threshold: int = 3,
+        hate_unfairness_threshold: int = 3,
+        **kwargs
+    ):
+        # Type checking
+        for name, value in [
+            ("violence_threshold", violence_threshold),
+            ("sexual_threshold", sexual_threshold),
+            ("self_harm_threshold", self_harm_threshold),
+            ("hate_unfairness_threshold", hate_unfairness_threshold),
+        ]:
+            if not isinstance(value, int):
+                raise TypeError(f"{name} must be an int, got {type(value)}")
+        
         evaluators = [
-            ViolenceEvaluator(credential, azure_ai_project),
-            SexualEvaluator(credential, azure_ai_project),
-            SelfHarmEvaluator(credential, azure_ai_project),
-            HateUnfairnessEvaluator(credential, azure_ai_project),
+            ViolenceEvaluator(credential, azure_ai_project, threshold=violence_threshold),
+            SexualEvaluator(credential, azure_ai_project, threshold=sexual_threshold),
+            SelfHarmEvaluator(credential, azure_ai_project, threshold=self_harm_threshold),
+            HateUnfairnessEvaluator(credential, azure_ai_project, threshold=hate_unfairness_threshold),
         ]
         super().__init__(evaluators=evaluators, **kwargs)
 

azure/ai/evaluation/_evaluators/_content_safety/_hate_unfairness.py

@@ -48,6 +48,8 @@ class HateUnfairnessEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
     :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 threshold: The threshold for the HateUnfairness evaluator. Default is 3.
+    :type threshold: int
 
     .. admonition:: Example:
 
@@ -57,6 +59,15 @@ class HateUnfairnessEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :language: python
             :dedent: 8
             :caption: Initialize and call a HateUnfairnessEvaluator.
+
+    .. admonition:: Example with Threshold:
+    
+        .. literalinclude:: ../samples/evaluation_samples_threshold.py
+            :start-after: [START threshold_hate_unfairness_evaluator]
+            :end-before: [END threshold_hate_unfairness_evaluator]
+            :language: python
+            :dedent: 8
+            :caption: Initialize with threshold and call a HateUnfairnessEvaluator.
     """
 
     id = "azureml://registries/azureml/models/Hate-and-Unfairness-Evaluator/versions/4"
@@ -67,12 +78,16 @@ class HateUnfairnessEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
         self,
         credential,
         azure_ai_project,
+        *,
+        threshold: int = 3,
     ):
         super().__init__(
             eval_metric=EvaluationMetrics.HATE_FAIRNESS,
             azure_ai_project=azure_ai_project,
             credential=credential,
             conversation_aggregation_type=_AggregationType.MAX,
+            threshold=threshold,
+            _higher_is_better=False,
         )
 
     @overload

azure/ai/evaluation/_evaluators/_content_safety/_self_harm.py

@@ -42,6 +42,8 @@ class SelfHarmEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
     :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 threshold: The threshold for the SelfHarm evaluator. Default is 3.
+    :type threshold: int
 
     .. admonition:: Example:
 
@@ -51,6 +53,15 @@ class SelfHarmEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :language: python
             :dedent: 8
             :caption: Initialize and call a SelfHarmEvaluator.
+
+    .. admonition:: Example:
+
+        .. literalinclude:: ../samples/evaluation_samples_threshold.py
+            :start-after: [START threshold_self_harm_evaluator]
+            :end-before: [END threshold_self_harm_evaluator]
+            :language: python
+            :dedent: 8
+            :caption: Initialize with threshold and call a SelfHarmEvaluator.    
     """
 
     id = "azureml://registries/azureml/models/Self-Harm-Related-Content-Evaluator/versions/3"
@@ -61,12 +72,16 @@ class SelfHarmEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
         self,
         credential,
         azure_ai_project,
+        *,
+        threshold: int = 3,
     ):
         super().__init__(
             eval_metric=EvaluationMetrics.SELF_HARM,
             azure_ai_project=azure_ai_project,
             credential=credential,
             conversation_aggregation_type=_AggregationType.MAX,
+            threshold=threshold,
+            _higher_is_better=False,
         )
 
     @overload

azure/ai/evaluation/_evaluators/_content_safety/_sexual.py

@@ -44,6 +44,8 @@ class SexualEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
     :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 threshold: The threshold for the Sexual evaluator. Default is 3.
+    :type threshold: int
 
     .. admonition:: Example:
 
@@ -53,6 +55,15 @@ class SexualEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :language: python
             :dedent: 8
             :caption: Initialize and call a SexualEvaluator.
+    
+    .. admonition:: Example with Threshold:
+
+        .. literalinclude:: ../samples/evaluation_samples_threshold.py
+            :start-after: [START threshold_sexual_evaluator]
+            :end-before: [END threshold_sexual_evaluator]
+            :language: python
+            :dedent: 8
+            :caption: Initialize with threshold and call a SexualEvaluator.
     """
 
     id = "azureml://registries/azureml/models/Sexual-Content-Evaluator/versions/3"
@@ -63,12 +74,16 @@ class SexualEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
         self,
         credential,
         azure_ai_project,
+        *,
+        threshold: int = 3,
     ):
         super().__init__(
             eval_metric=EvaluationMetrics.SEXUAL,
             azure_ai_project=azure_ai_project,
             credential=credential,
             conversation_aggregation_type=_AggregationType.MAX,
+            threshold=threshold,
+            _higher_is_better=False,
         )
 
     @overload

azure/ai/evaluation/_evaluators/_content_safety/_violence.py

@@ -44,6 +44,8 @@ class ViolenceEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
     :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 threshold: The threshold for the Violence evaluator. Default is 3.
+    :type threshold: int
 
     .. admonition:: Example:
 
@@ -53,6 +55,15 @@ class ViolenceEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
             :language: python
             :dedent: 8
             :caption: Initialize and call a ViolenceEvaluator.
+
+    .. admonition:: Example:
+
+        .. literalinclude:: ../samples/evaluation_samples_threshold.py
+            :start-after: [START threshold_violence_evaluator]
+            :end-before: [END threshold_violence_evaluator]
+            :language: python
+            :dedent: 8
+            :caption: Initialize with threshold and call a ViolenceEvaluator.
     """
 
     id = "azureml://registries/azureml/models/Violent-Content-Evaluator/versions/3"
@@ -63,12 +74,16 @@ class ViolenceEvaluator(RaiServiceEvaluatorBase[Union[str, float]]):
         self,
         credential,
         azure_ai_project,
+        *,
+        threshold: int = 3,
     ):
         super().__init__(
             eval_metric=EvaluationMetrics.VIOLENCE,
             azure_ai_project=azure_ai_project,
             credential=credential,
             conversation_aggregation_type=_AggregationType.MAX,
+            threshold=threshold,
+            _higher_is_better=False,
         )
 
     @overload