Update src/deepeval/deepeval_task_manager.py

src/deepeval/deepeval_task_manager.py

@@ -14,6 +14,13 @@ from src.deepeval.reading_comp_mc import ReadingComprehensionMCTask
 from src.deepeval.complex_reasoning import ComplexReasoningTask
 from src.deepeval.truthfulness_task import TruthfulnessTask
 from src.deepeval.nli import NLITask
+from src.deepeval.math import MathTask
+from src.deepeval.turkish_vocabulary import TurkishVocabularyTask
+from src.deepeval.metaphors_and_idioms import MetaphorsAndIdiomsTask
+from src.deepeval.topic_detection import TopicDetectionTask
+from src.deepeval.sts import STSTask
+from src.deepeval.mmlu import MMLUTask
+from src.deepeval.bias import BiasTask
 from typing import List
 from datetime import datetime
 load_dotenv()
@@ -34,6 +41,14 @@ class Task(Enum):
     COMPLEX_REASONING = "complex_reasoning"
     TRUTHFULNESS = "sosyoloji_truthfulness"
     NLI = "nli"
+    MATH = "math"
+    TURKISH_VOCABULARY = "turkish_vocabulary"
+    METAPHORS_AND_IDIOMS = "metaphors_and_idioms"
+    TOPIC_DETECTION = "topic_detection"
+    STS = "sts"
+    MMLU = "mmlu"
+    BIAS_MC = "bias"
+    
 
 
 class DeepEvalTaskManager:
@@ -143,6 +158,42 @@ class DeepEvalTaskManager:
         res = nli_task.evaluate()
         return res
 
+        def math(self):
+        math_task = MathTask(self.model_name)
+        res = math_task.evaluate()
+        return res
+
+    def turkish_vocabulary(self):
+        turkish_vocabulary_task = TurkishVocabularyTask(self.model_name)
+        res = turkish_vocabulary_task.evaluate()
+        return res
+
+    def metaphors_and_idioms(self):
+        metaphors_and_idioms_task = MetaphorsAndIdiomsTask(self.model_name)
+        res = metaphors_and_idioms_task.evaluate()
+        return res
+
+    def topic_detection(self):
+        topic_detection_task = TopicDetectionTask(self.model_name)
+        res = topic_detection_task.evaluate()
+        return res
+
+    def sts(self):
+        sts_task = STSTask(self.model_name)
+        res = sts_task.evaluate()
+        return res
+
+    def mmlu(self):
+        mmlu_task = MMLUTask(self.model_name)
+        res = mmlu_task.evaluate()
+        return res
+
+    def bias(self):
+        bias_task = BiasTask(self.model_name)
+        res = bias_task.evaluate()
+        return res
+
+
 if __name__ == "__main__":
     des = DeepEvalTaskManager("google/gemma-2-2b-it", ["TOXICITY", "BIAS"])
     res = des.run_tasks()