judgeval 0.0.7__py3-none-any.whl → 0.0.9__py3-none-any.whl

judgeval/judgment_client.py

@@ -267,7 +267,6 @@ class JudgmentClient:
             
         return response.json()["slug"]
     
-    
     def assert_test(
         self, 
         examples: List[Example],
@@ -275,12 +274,14 @@ class JudgmentClient:
         model: Union[str, List[str], JudgevalJudge],
         aggregator: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
-        log_results: bool = False,
-        project_name: str = "",
-        eval_run_name: str = "",
+        log_results: bool = True,
+        project_name: str = "default_project",
+        eval_run_name: str = "default_eval_run",
         override: bool = False,
     ) -> None:
-        
+        """
+        Asserts a test by running the evaluation and checking the results for success
+        """
         results = self.run_evaluation(
             examples=examples,
             scorers=scorers,

judgeval/scorers/__init__.py

@@ -13,6 +13,7 @@ from judgeval.scorers.judgeval_scorers import (
     AnswerRelevancyScorer,
     ScorerWrapper,
     AnswerCorrectnessScorer,
+    Text2SQLScorer,
 )
 
 __all__ = [
@@ -31,4 +32,5 @@ __all__ = [
     "AnswerRelevancyScorer",
     "ScorerWrapper",
     "AnswerCorrectnessScorer",
+    "Text2SQLScorer",
 ]

judgeval/scorers/judgeval_scorer.py

@@ -58,6 +58,8 @@ class JudgevalScorer:
         additional_metadata: Optional[Dict] = None
         ):
             debug(f"Initializing CustomScorer with score_type={score_type}, threshold={threshold}")
+            if not 0 <= threshold <= 1:
+                raise ValueError("Threshold must be between 0 and 1")
             if strict_mode:
                 warning("Strict mode enabled - scoring will be more rigorous")
             info(f"CustomScorer initialized with evaluation_model: {evaluation_model}")

judgeval/scorers/judgeval_scorers/__init__.py

@@ -28,6 +28,9 @@ from judgeval.scorers.judgeval_scorers.local_implementations import (
     AnswerCorrectnessScorer as LocalAnswerCorrectnessScorer
 )
 
+from judgeval.scorers.judgeval_scorers.classifiers import Text2SQLScorer
+
+
 class ScorerWrapper:
     """
     Wrapper class that can dynamically load either API or local implementation of a scorer.
@@ -141,4 +144,5 @@ __all__ = [
     "ContextualPrecisionScorer",
     "ContextualRecallScorer",
     "AnswerRelevancyScorer",
+    "Text2SQLScorer",
 ]

judgeval/scorers/judgeval_scorers/classifiers/__init__.py

@@ -0,0 +1,3 @@
+from .text2sql import Text2SQLScorer
+
+__all__ = ["Text2SQLScorer"]

judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py

@@ -0,0 +1,3 @@
+from .text2sql_scorer import Text2SQLScorer
+
+__all__ = ["Text2SQLScorer"]

judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py

@@ -0,0 +1,54 @@
+"""
+ClassifierScorer implementation for basic Text-to-SQL evaluation.
+
+Takes a natural language query, a corresponding LLM-generated SQL query, and a table schema + (optional) metadata.
+Determines if the LLM-generated SQL query is valid and works for the natural language query.
+"""
+from judgeval.scorers import ClassifierScorer
+
+Text2SQLScorer = ClassifierScorer(
+    "Text to SQL",
+    slug="text2sql-1010101010",
+    threshold=1.0,
+    conversation=[{
+        "role": "system",
+        "content": """You will be given a natural language query, a corresponding LLM-generated SQL query, and a table schema + (optional) metadata.
+
+** TASK INSTRUCTIONS **
+Your task is to decide whether the LLM generated SQL query properly filters for what the natural language query is asking, based on the table schema + (optional) metadata. 
+Additionally, you should check if the SQL query is valid based on the table schema (checking for syntax errors, false column names, etc.)
+
+** TIPS **
+- Look for correct references to the table schema for column names, table names, etc.
+- Check that the SQL query can be executed; make sure JOINs, GROUP BYs, ORDER BYs, etc. are valid with respect to the table schema.
+- Check that aggregation functions (COUNT, SUM, AVG, etc.) are used appropriately with GROUP BY clauses
+- Verify that WHERE conditions use the correct operators and data types for comparisons
+- Ensure LIMIT and OFFSET clauses make sense for the query's purpose
+- Check that JOINs use the correct keys and maintain referential integrity
+- Verify that ORDER BY clauses use valid column names and sort directions
+- Check for proper handling of NULL values where relevant
+- Ensure subqueries are properly constructed and correlated when needed
+- EVEN IF THE QUERY IS VALID, IF IT DOESN'T WORK FOR THE NATURAL LANGUAGE QUERY, YOU SHOULD CHOOSE "N" AS THE ANSWER.
+
+** FORMATTING YOUR ANSWER **
+If the SQL query is valid and works for the natural language query, choose option "Y" and otherwise "N". Provide a justification for your decision; if you choose "N", explain what about the LLM-generated SQL query is incorrect, or explain why it doesn't address the natural language query. 
+IF YOUR JUSTIFICATION SHOWS THAT THE SQL QUERY IS VALID AND WORKS FOR THE NATURAL LANGUAGE QUERY, YOU SHOULD CHOOSE "Y" AS THE ANSWER. 
+IF THE SQL QUERY IS INVALID, YOU SHOULD CHOOSE "N" AS THE ANSWER. 
+
+** YOUR TURN **
+Natural language query:
+{{input}}
+
+LLM generated SQL query:
+{{actual_output}}
+
+Table schema:
+{{context}}
+        """
+    }],
+    options={
+        "Y": 1.0, 
+        "N": 0.0
+    }
+)
+

judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py

@@ -1,6 +1,7 @@
 from typing import Optional, List, Union, Tuple
 from pydantic import BaseModel
 
+from judgeval.constants import APIScorer
 from judgeval.judges import JudgevalJudge
 from judgeval.judges.utils import create_judge
 from judgeval.data import Example, ExampleParams
@@ -38,13 +39,17 @@ class AnswerCorrectnessScorer(JudgevalScorer):
         strict_mode: bool = False,
         verbose_mode: bool = False
     ):
-        self.threshold = 1 if strict_mode else threshold
-        self.include_reason = include_reason
+        super().__init__(
+            score_type=APIScorer.ANSWER_CORRECTNESS,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.model, self.using_native_model = create_judge(model)
         self.evaluation_model = self.model.get_model_name()
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
 
     async def _a_get_statements(self, expected_output: str) -> List[str]:
         prompt = AnswerCorrectnessTemplate.deduce_statements(

judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py

@@ -1,5 +1,6 @@
 from typing import Optional, List, Union, Tuple
 
+from judgeval.constants import APIScorer
 from judgeval.scorers.utils import (get_or_create_event_loop,
                                     scorer_progress_meter,
                                     create_verbose_logs,
@@ -34,13 +35,18 @@ class AnswerRelevancyScorer(JudgevalScorer):
         strict_mode: bool = False,
         verbose_mode: bool = False,
     ):
-        self.threshold = 1 if strict_mode else threshold
+        super().__init__(
+            score_type=APIScorer.ANSWER_RELEVANCY,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.model, self.using_native_model = create_judge(model)
         self.evaluation_model = self.model.get_model_name()
-        self.include_reason = include_reason
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
+        print(self.model)
 
     def score_example(
         self,

judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py

@@ -4,6 +4,7 @@ from judgeval.judges import JudgevalJudge
 from judgeval.judges.utils import create_judge
 from judgeval.data import Example, ExampleParams
 from judgeval.scorers import JudgevalScorer
+from judgeval.constants import APIScorer
 from judgeval.scorers.utils import (
     get_or_create_event_loop,
     parse_response_json,
@@ -30,13 +31,17 @@ class ContextualPrecisionScorer(JudgevalScorer):
         strict_mode: bool = False,
         verbose_mode: bool = False,
     ):
-        self.threshold = 1 if strict_mode else threshold
-        self.include_reason = include_reason
+        super().__init__(
+            score_type=APIScorer.CONTEXTUAL_PRECISION,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.model, self.using_native_model = create_judge(model)
         self.evaluation_model = self.model.get_model_name()
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
 
     def score_example(
         self,

judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py

@@ -1,5 +1,6 @@
 from typing import Optional, List, Union
 
+from judgeval.constants import APIScorer
 from judgeval.scorers.utils import (
     get_or_create_event_loop, 
     parse_response_json, 
@@ -32,14 +33,18 @@ class ContextualRecallScorer(JudgevalScorer):
         verbose_mode: bool = False,
         user: Optional[str] = None
     ):
+        super().__init__(
+            score_type=APIScorer.CONTEXTUAL_RECALL,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.user = user
-        self.threshold = 1 if strict_mode else threshold
         self.model, self.using_native_model = create_judge(model)
         self.evaluation_model = self.model.get_model_name()
-        self.include_reason = include_reason
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
 
     def score_example(
         self,

judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py

@@ -1,6 +1,7 @@
 from typing import Optional, List, Union
 import asyncio
 
+from judgeval.constants import APIScorer
 from judgeval.scorers.utils import (get_or_create_event_loop,
                                     scorer_progress_meter,
                                     create_verbose_logs,
@@ -32,14 +33,18 @@ class ContextualRelevancyScorer(JudgevalScorer):
         verbose_mode: bool = False,
         user: Optional[str] = None
     ):
+        super().__init__(
+            score_type=APIScorer.CONTEXTUAL_RELEVANCY,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.user = user
-        self.threshold = 1 if strict_mode else threshold
         self.model, self.using_native_model = create_judge(model)
         self.evaluation_model = self.model.get_model_name()
-        self.include_reason = include_reason
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
 
     def score_example(
         self,

judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py

@@ -3,7 +3,7 @@ Code for the local implementation of the Faithfulness metric.
 """
 from typing import List, Optional, Union
 
-
+from judgeval.constants import APIScorer
 from judgeval.data import (
     Example, 
     ExampleParams
@@ -47,14 +47,19 @@ class FaithfulnessScorer(JudgevalScorer):
         verbose_mode: bool = False,
         user: Optional[str] = None
     ):
-        self.threshold = 1 if strict_mode else threshold
+        super().__init__(
+            score_type=APIScorer.FAITHFULNESS,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
+        self.user = user
         self.model, self.using_native_model = create_judge(model)
         self.using_native_model = True  # NOTE: SETTING THIS FOR LITELLM and TOGETHER usage
         self.evaluation_model = self.model.get_model_name()
-        self.include_reason = include_reason
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
 
     def score_example(
         self,

judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py

@@ -20,6 +20,7 @@ Hallucination is measuring the fraction of contexts that agree with output (do n
 
 from typing import Optional, Union, List
 
+from judgeval.constants import APIScorer
 from judgeval.scorers.utils import (get_or_create_event_loop,
                                     scorer_progress_meter,
                                     create_verbose_logs,
@@ -50,13 +51,17 @@ class HallucinationScorer(JudgevalScorer):
         strict_mode: bool = False,
         verbose_mode: bool = False,
     ):
-        self.threshold = 1 if strict_mode else threshold
+        super().__init__(
+            score_type=APIScorer.HALLUCINATION,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.model, self.using_native_model = create_judge(model)
         self.evaluation_model = self.model.get_model_name()
-        self.include_reason = include_reason
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
 
     def score_example(
         self,

judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/__init__.py

@@ -0,0 +1,5 @@
+from judgeval.scorers.judgeval_scorers.local_implementations.json_correctness.json_correctness_scorer import JsonCorrectnessScorer
+
+__all__ = [
+    "JsonCorrectnessScorer",
+]

judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py

@@ -1,7 +1,9 @@
 from typing import List, Optional, Union, Any
 from pydantic import BaseModel, ValidationError, create_model
 
+from judgeval.constants import APIScorer
 from judgeval.judges import JudgevalJudge
+from judgeval.judges.utils import create_judge
 from judgeval.scorers.utils import (get_or_create_event_loop,
                                     scorer_progress_meter,
                                     create_verbose_logs,
@@ -30,13 +32,18 @@ class JsonCorrectnessScorer(JudgevalScorer):
         verbose_mode: bool = False,
         user: Optional[str] = None
     ):
-        self.score_type = "json_correctness"
-        self.model = model
-        self.threshold = threshold
-        self.async_mode = async_mode
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
+        super().__init__(
+            score_type=APIScorer.JSON_CORRECTNESS,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=False,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.user = user
+        self.model, self.using_native_model = create_judge(model)
+        self.evaluation_model = self.model.get_model_name()
 
         if isinstance(json_schema, dict):
             # Convert to BaseModel

judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py

@@ -1,6 +1,7 @@
 from typing import List, Optional, Union
 import asyncio
 
+from judgeval.constants import APIScorer
 from judgeval.scorers.utils import (get_or_create_event_loop,
                                     scorer_progress_meter,
                                     create_verbose_logs,
@@ -36,7 +37,15 @@ class SummarizationScorer(JudgevalScorer):
         strict_mode: bool = False,
         verbose_mode: bool = False,
     ):
-        self.threshold = 1 if strict_mode else threshold
+        super().__init__(
+            score_type=APIScorer.SUMMARIZATION,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=async_mode,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.model, self.using_native_model = create_judge(model)
         self.evaluation_model = self.model.get_model_name()
 

judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/tool_correctness_scorer.py

@@ -1,5 +1,6 @@
 from typing import List, Union
 
+from judgeval.constants import APIScorer
 from judgeval.scorers.utils import (
     scorer_progress_meter,
     create_verbose_logs,
@@ -55,10 +56,15 @@ class ToolCorrectnessScorer(JudgevalScorer):
         should_exact_match: bool = False,
         should_consider_ordering: bool = False,
     ):
-        self.threshold = 1 if strict_mode else threshold
-        self.include_reason = include_reason
-        self.strict_mode = strict_mode
-        self.verbose_mode = verbose_mode
+        super().__init__(
+            score_type=APIScorer.TOOL_CORRECTNESS,
+            threshold=1 if strict_mode else threshold,
+            evaluation_model=None,
+            include_reason=include_reason,
+            async_mode=False,
+            strict_mode=strict_mode,
+            verbose_mode=verbose_mode
+        )
         self.should_exact_match = should_exact_match
         self.should_consider_ordering = should_consider_ordering
 

{judgeval-0.0.7.dist-info → judgeval-0.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: judgeval
-Version: 0.0.7
+Version: 0.0.9
 Summary: Judgeval Package
 Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
 Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues

{judgeval-0.0.7.dist-info → judgeval-0.0.9.dist-info}/RECORD

@@ -2,7 +2,7 @@ judgeval/__init__.py,sha256=xiiG4CkeaOtey4fusCd9CBz0BVqzTIbV-K2EFIU0rUM,283
 judgeval/clients.py,sha256=Ns5ljrgPPXUMo7fSPJxO12H64lcPyKeQPIVG_RMi2cM,1162
 judgeval/constants.py,sha256=5O1jWvxMCRyMSWhmkrvPqfBctx42c7kMtgTS7ORVcFw,1965
 judgeval/evaluation_run.py,sha256=KcIS7mDR_9XEdqYrJXFcrLz5IDMof34HcD5VtjZgV8w,5884
-judgeval/judgment_client.py,sha256=8Z4Woiv56qphYqlMI3bNy4rvQItZl_z9vNNd3UdrCes,11241
+judgeval/judgment_client.py,sha256=lVVVDxRQ750nd0wT827dca94YzThNjuFWWJ-BTFW7lg,11367
 judgeval/run_evaluation.py,sha256=A9jjtWPH2_5W43a1f98R8u-8PuVczoJZNCZIyCoRqi8,18918
 judgeval/common/__init__.py,sha256=7d24BRxtncpMj3AAJCj8RS7TqgjXmW777HVZH6-3sBs,289
 judgeval/common/exceptions.py,sha256=U-TxHLn7oVMezsMuoYouNDb2XuS8RCggfntYf5_6u4E,565
@@ -24,15 +24,15 @@ judgeval/judges/litellm_judge.py,sha256=EIL58Teptv8DzZUO3yP2RDQCDq-aoBB6HPZzPdK6
 judgeval/judges/mixture_of_judges.py,sha256=OuGWCuXyqe7s_Y74ij90TJFRfHU-VAFyJVVrwBM0RO0,15532
 judgeval/judges/together_judge.py,sha256=x3jf-tq77QPXHeeoF739f69hE_0VceXD9FHLrVFdGVA,2275
 judgeval/judges/utils.py,sha256=YUvivcGV1OKLPMJ9N6aTvhA0r_zzJ2NXriPguiiaVaY,2110
-judgeval/scorers/__init__.py,sha256=3rq2VtszrJk9gZ3oAMVd7EGlSugr8aRlHWprMDgQPaQ,956
+judgeval/scorers/__init__.py,sha256=XcDdLn_s16rSQob0896oj4JXTA8-Xfl271TUEBj6Oew,998
 judgeval/scorers/api_scorer.py,sha256=88kCWr6IetLFn3ziTPG-lwDWvMhFUC6xfINU1MJBoho,2125
 judgeval/scorers/base_scorer.py,sha256=mbOReG88fWaqCnC8F0u5QepRlzgVkuOz89KEKYxrmMc,1794
 judgeval/scorers/exceptions.py,sha256=eGW5CuJgZ5YJBFrE4FHDSF651PO1dKAZ379mJ8gOsfo,178
-judgeval/scorers/judgeval_scorer.py,sha256=qpjyj7JZEgxoF8LR3pwkKeebmVC8qlITnKFN4YOUKXc,6165
+judgeval/scorers/judgeval_scorer.py,sha256=14SZ3sBZtGNM3BCegKebkNad9LTs5Tyhs0kD6l3wLAA,6275
 judgeval/scorers/prompt_scorer.py,sha256=bUv8eZNy1XGVM1gNMt33dgIVX6zj63bGAV6O0o0c7yg,17821
 judgeval/scorers/score.py,sha256=zJKG21h9Njyj2vS36CAFK2wlbOcHSKgrLgHV5_25KKw,18630
 judgeval/scorers/utils.py,sha256=dtueaJm8e3Ph3wj1vC-srzadgK_CoIlOefdvMQ-cwK8,6826
-judgeval/scorers/judgeval_scorers/__init__.py,sha256=077QnuBfw9Sy9RP2TF2oKCtt5PbaqBZLyiP-gczKShk,5092
+judgeval/scorers/judgeval_scorers/__init__.py,sha256=D12jJAKTcfmz8fDBkYeOmdzZMZsURuODIJ5p7Nk1lWE,5189
 judgeval/scorers/judgeval_scorers/api_scorers/__init__.py,sha256=zFwH2TC5AFlpDRfVKc6GN4YTtnmeyALl-JRLoZD_Jco,1284
 judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py,sha256=690G5askjE8dcbKPGvCF6JxAEM9QJUqb-3K-D6lI6oM,463
 judgeval/scorers/judgeval_scorers/api_scorers/answer_relevancy.py,sha256=CqvvjV7AZqPlXh-PZaPKYPILHr15u4bIYiKBFjlk5i0,457
@@ -44,35 +44,39 @@ judgeval/scorers/judgeval_scorers/api_scorers/hallucination.py,sha256=ffYwH3CexP
 judgeval/scorers/judgeval_scorers/api_scorers/json_correctness.py,sha256=CAZBQKwNSqpqAoOgStYfr-yP1Brug_6VRimRIQY-zdg,894
 judgeval/scorers/judgeval_scorers/api_scorers/summarization.py,sha256=-E3oxYbI0D_0q-_fGWh2jQHW9O4Pu7I7xvLWsHU6cn8,450
 judgeval/scorers/judgeval_scorers/api_scorers/tool_correctness.py,sha256=17ppPXm962ew67GU5m0npzbPu3CuhgdKY_KmfPvKfu4,457
+judgeval/scorers/judgeval_scorers/classifiers/__init__.py,sha256=Qt81W5ZCwMvBAne0LfQDb8xvg5iOG1vEYP7WizgwAZo,67
+judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py,sha256=8iTzMvou1Dr8pybul6lZHKjc9Ye2-0_racRGYkhEdTY,74
+judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py,sha256=ly72Z7s_c8NID6-nQnuW8qEGEW2MqdvpJ-5WfXzbAQg,2579
 judgeval/scorers/judgeval_scorers/local_implementations/__init__.py,sha256=ZDbmYHwIbPD75Gj9JKtEWnpBdSVGGRmbn1_IOR6GR-c,1627
 judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/__init__.py,sha256=cxxUEspgoIdSzJbwIIioamC0-xDqhYVfYAWxaYF-D_Y,177
-judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py,sha256=ZjLw3Usx3SsSRXGXLItNL_IEWo_UV8dxhc2mS9j-nGM,10073
+judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/answer_correctness_scorer.py,sha256=PDThn6SzqxgMXT7BpQs2TEBOsgfD5fi6fnKk31qaCTo,10227
 judgeval/scorers/judgeval_scorers/local_implementations/answer_correctness/prompts.py,sha256=5B_G7PPEsfLq6cwWkKWcLuy2k_5RgoOzsW3wOZLIeMk,6703
 judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/__init__.py,sha256=r6yae5iaWtlBL_cP8I-1SuhS9dulsy1e7W9Rcz82v6E,169
-judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py,sha256=3T3pDxJde6M8RxsPLXvQA16Dpo-sLECEnMCe7rpvNcY,10536
+judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/answer_relevancy_scorer.py,sha256=QG-oxa6-c74VzTuni17RQ9aeT0t1lCuxQXDMznqX8rc,10714
 judgeval/scorers/judgeval_scorers/local_implementations/answer_relevancy/prompts.py,sha256=GfbKv595s1a0dB1No_kDsap6gfcr6dYRGiXx0PDb89k,6557
 judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/__init__.py,sha256=J6tc-T60AVOEaNVuoVU0XIG6dvQri99Q0tnX_Tm-0vc,108
-judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py,sha256=5EYjUusMyDfiqatg8-_OJg8IDax-8Ib6aI1sQgi-6JA,9493
+judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/contextual_precision_scorer.py,sha256=tRgRyjGpc4Pe3nQ1c-5NeNYFvbulL7YEnoRa9zLp1gc,9649
 judgeval/scorers/judgeval_scorers/local_implementations/contextual_precision/prompts.py,sha256=gddK6BQAFcW04vAad81kxIXCHJQp8CbCqMwudWKy7aM,4892
 judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/__init__.py,sha256=4kjfqD_95muHZFo75S8_fbTcC1DI1onNIfMmr8gMZaI,99
-judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py,sha256=u8sknD9IsPfU7iF4725w5OmFKe1JEZbOYwsLcAy4m3E,9107
+judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/contextual_recall_scorer.py,sha256=hwAv_x3XwGDnSW3a75CTCgIW6eVg8ymdjDdJQvw5p0Y,9260
 judgeval/scorers/judgeval_scorers/local_implementations/contextual_recall/prompts.py,sha256=boVq6IM7Iambc1ky_JJQ4ejnYoQQtYreG0SjO4iMyFU,6558
 judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/__init__.py,sha256=JPCvrekKLbl_xdD49evhtiFIVocuegCpCBkn1auzTSE,184
-judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py,sha256=NCGFLrdkpEK_LPVQC21qY-0pEOrsdVC0RRcNn9IdREE,8759
+judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/contextual_relevancy_scorer.py,sha256=BtVgE7z-9PHfFRcvn96aEG5mXVcWBweVyty934hZdiU,8915
 judgeval/scorers/judgeval_scorers/local_implementations/contextual_relevancy/prompts.py,sha256=6EHBfxWvhur9z14l8zCw5Z4Hb2uRo9Yv7qIhTRT7-aM,4591
 judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/__init__.py,sha256=NbkSqPwxgF4T8KsvuIWhVyRwdOlo7mNHMFuRStTFnvk,154
-judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py,sha256=HdpxzQVYs79AdoNWmInS6yNYwPdwgqN23OHSzo1e9_4,11169
+judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/faithfulness_scorer.py,sha256=4XqdcdgHg3evrg-IQwXmUHEyee1lZUjXRNEiQSvdpmQ,11341
 judgeval/scorers/judgeval_scorers/local_implementations/faithfulness/prompts.py,sha256=oxmCsouh5ExUMmlSuCDolpYR2y9c-yKth6PHrdsCH_g,11387
 judgeval/scorers/judgeval_scorers/local_implementations/hallucination/__init__.py,sha256=fZk3UQxI9Nljf5qjCRLRkF0D-AERFHElI9cC83_cgV8,158
-judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py,sha256=ud-P20erpiLR-i-ycma7Bg8M_mxJ2yQliXPXr-Iwq3M,9521
+judgeval/scorers/judgeval_scorers/local_implementations/hallucination/hallucination_scorer.py,sha256=orCrEe1IH4NE7m-AkKMX0EHbysTuAwIqfohcQaU7XxQ,9670
 judgeval/scorers/judgeval_scorers/local_implementations/hallucination/prompts.py,sha256=BkEu7Q_jIVdcdZSq37tMjitZFzACd8-iBTDDXfGbZig,4346
-judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py,sha256=eYqHTWiw0NOPHueswknmpdxrmrmSm6Jadq56Ncmv9B0,4218
+judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/__init__.py,sha256=xQDw7o9JQ6qajusPnBH0MWBRJ5ct_Ao3pJELXxxVMRo,175
+judgeval/scorers/judgeval_scorers/local_implementations/json_correctness/json_correctness_scorer.py,sha256=WxIIK_sgHMQ3aLGvkzvYpcmUm6r62gvrAELimMLw3iM,4529
 judgeval/scorers/judgeval_scorers/local_implementations/summarization/__init__.py,sha256=mv6-XeLSV5yj1H98YYV2iTYVd88zKftZJP42Lgl6R80,89
 judgeval/scorers/judgeval_scorers/local_implementations/summarization/prompts.py,sha256=6GnRz2h-6Fwt4sl__0RgQOyo3n3iDO4MNuHWxdu-rrM,10242
-judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py,sha256=3FMn7EhM5IxNwJLGTcpeHODaOPJefMHW6rRizmlA93U,20775
+judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py,sha256=CBuE6oCxMzTdJoXFt_YPWBte88kedEQ9t3g52ZRztGY,21086
 judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/__init__.py,sha256=JUB3TMqS1OHr6PqpIGqkyiBNbyfUaw7lZuUATjU3_ek,168
-judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/tool_correctness_scorer.py,sha256=oxhVDR3Pb55Kxp9KsvmuvHWKtMiV1BQRG6yaXEr5Bp8,5309
-judgeval-0.0.7.dist-info/METADATA,sha256=mo6GssA1Es1FTG8saMwzsoL5AoIHbKDXnTiTA238ZzQ,1204
-judgeval-0.0.7.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.0.7.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.0.7.dist-info/RECORD,,
+judgeval/scorers/judgeval_scorers/local_implementations/tool_correctness/tool_correctness_scorer.py,sha256=CYGRJY5EuyICYzHrmFdLykwXakX8AC7G3Bhj7p6szfY,5493
+judgeval-0.0.9.dist-info/METADATA,sha256=D9-pDQVSwfHCVcZ85-AS6MaMhd1AGz1CAJ5fRLwrRsA,1204
+judgeval-0.0.9.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.0.9.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.0.9.dist-info/RECORD,,