judgeval 0.0.26__py3-none-any.whl → 0.0.27__py3-none-any.whl

{judgeval-0.0.26.dist-info → judgeval-0.0.27.dist-info}/RECORD

@@ -1,23 +1,22 @@
 judgeval/__init__.py,sha256=dtXxsCmI4eEsZdGSUMy8P_pA0bc2-OSGAgb2C__yJoA,252
 judgeval/clients.py,sha256=6VQmEqmfCngUdS2MuPBIpHvtDFqOENm8-_BmMvjLyRQ,944
-judgeval/constants.py,sha256=iTUro5SdXcYX00W18l32zL_EEEqHf5OT9uA5yZAme_s,5158
+judgeval/constants.py,sha256=ksAXhAXovzJKH0uHOdQtREs168uCJRG79PooHNmEbYQ,5313
 judgeval/evaluation_run.py,sha256=RgJD60lJsunNQzObjo7iXnAzXWgubCLOAAuuamAAuoI,6354
-judgeval/judgment_client.py,sha256=2z134M0GeW3CdOZDx688UXmqJUlU31hlcFlLwUhF_Tg,25429
+judgeval/judgment_client.py,sha256=uf0V1-eu3qnFTwrQ_Ckcv8IiWRVv7dbvou4P4KjU6hM,26794
 judgeval/rules.py,sha256=B0ZL0pn72D4Jnlr0zMQ6CPHi7D8AQQRariXCVsiCMiI,20542
-judgeval/run_evaluation.py,sha256=8FZ-shJ0120iTuT2S1rXzmVcoIHPsFPb0THTGOtKoHM,25772
+judgeval/run_evaluation.py,sha256=N2ppmEE5WoSReChKjr_n0NcdAUlUR6Nua7M1C_3zHQ8,24949
 judgeval/common/__init__.py,sha256=7d24BRxtncpMj3AAJCj8RS7TqgjXmW777HVZH6-3sBs,289
 judgeval/common/exceptions.py,sha256=U-TxHLn7oVMezsMuoYouNDb2XuS8RCggfntYf5_6u4E,565
 judgeval/common/logger.py,sha256=KO75wWXCxhUHUMvLaTU31ZzOk6tkZBa7heQ7y0f-zFE,6062
-judgeval/common/tracer.py,sha256=Z87Q3pQrtfHYvE1vsTMdIUfR-iz_IM8dqvW9VwVdtMQ,42434
+judgeval/common/tracer.py,sha256=L6JkCHj6kxhtDzf9OPg5ZC-NUUH4VDvDcV4utPi_I38,57544
 judgeval/common/utils.py,sha256=LUQV5JfDr6wj7xHAJoNq-gofNZ6mjXbeKrGKzBME1KM,33533
-judgeval/data/__init__.py,sha256=YferxwmUqoBi18hrdgro0BD0h4pt20LAqISeUzGMcVU,474
-judgeval/data/api_example.py,sha256=dzkrQ0xno08y6qNfqL2djXbapUyc2B2aQ5iANn0o4CY,3667
+judgeval/data/__init__.py,sha256=dG5ytBOeOWCTd5o0KP7IblqtW4G1EBaGreLWepM3jas,345
 judgeval/data/example.py,sha256=BhGBhamFWgH6wtvrRYM8dGtDfXh-cDxDhtNL5Gbdz_M,5892
-judgeval/data/result.py,sha256=4fgjKtUmT3br7K6fkRiNIxTGKUuwMeGyRLqzkpxwXKE,4436
+judgeval/data/result.py,sha256=YHD-dVYJN4JFpM-YCGgBtSdFcGAOyWYL41sf0TE9Hzg,3122
 judgeval/data/scorer_data.py,sha256=JVlaTx1EP2jw2gh3Vgx1CSEsvIFABAN26IquKyxwiJQ,3273
 judgeval/data/datasets/__init__.py,sha256=IdNKhQv9yYZ_op0rdBacrFaFVmiiYQ3JTzXzxOTsEVQ,176
 judgeval/data/datasets/dataset.py,sha256=AFYjksV_wXx5CqFYJsl3aN8yZ6hC50O1myRuOJ8s8_E,12867
-judgeval/data/datasets/eval_dataset_client.py,sha256=B4bRy0Di2oFlaBbvp4_hRx2g_9e6Cs0y3ZUT9reMyhw,10926
+judgeval/data/datasets/eval_dataset_client.py,sha256=P9fEmcNrjPPaiYbbLiEiBziZrIexA39HN9qzClt6uPE,12691
 judgeval/integrations/langgraph.py,sha256=fGDZOTlVbxTO4ErC-m9OSg3h-RkOIIWXCfhjgkKRh4E,11187
 judgeval/judges/__init__.py,sha256=6X7VSwrwsdxGBNxCyapVRWGghhKOy3MVxFNMQ62kCXM,308
 judgeval/judges/base_judge.py,sha256=ch_S7uBB7lyv44Lf1d7mIGFpveOO58zOkkpImKgd9_4,994
@@ -31,7 +30,7 @@ judgeval/scorers/base_scorer.py,sha256=xdUlY3CnLdCQ1Z5iUeY22Bim5v-OQruZmaVF_4Y1m
 judgeval/scorers/exceptions.py,sha256=eGW5CuJgZ5YJBFrE4FHDSF651PO1dKAZ379mJ8gOsfo,178
 judgeval/scorers/judgeval_scorer.py,sha256=jq_rzfTG0XBTuLCaa6TlaK4YcT-LlgsO1LEm6hpOYdg,6601
 judgeval/scorers/prompt_scorer.py,sha256=PaAs2qRolw1P3_I061Xvk9qzvF4O-JR8g_39RqXnHcM,17728
-judgeval/scorers/score.py,sha256=PhyAyMkc7KO_DZpFSN1HD_FS3BvdleQPZhYvQkNAdxI,18816
+judgeval/scorers/score.py,sha256=ObFAlMbNRcGrfBpH4WW_6OA3CjrneC539xSWhGH60GQ,18578
 judgeval/scorers/utils.py,sha256=iHQVTlIANbmCTXz9kTeSdOytgUZ_T74Re61ajqsk_WQ,6827
 judgeval/scorers/judgeval_scorers/__init__.py,sha256=xFRb62sp4JmBUSeuAB_pC_7kEGp-lGdqCRIu9--Bbdg,5992
 judgeval/scorers/judgeval_scorers/api_scorers/__init__.py,sha256=mZ6b_5Dl04k3PaG24ICBajB_j43ody1II1OJhO1DkXo,1648
@@ -87,7 +86,7 @@ judgeval/scorers/judgeval_scorers/local_implementations/summarization/prompts.py
 judgeval/scorers/judgeval_scorers/local_implementations/summarization/summarization_scorer.py,sha256=Qk7lwHgRPYeGoxTOyclAh1VfGItfvHJ6l1t7Nk3SWFM,20927
 judgeval/tracer/__init__.py,sha256=wy3DYpH8U_z0GO_K_gOSkK0tTTD-u5eLDo0T5xIBoAc,147
 judgeval/utils/alerts.py,sha256=O19Xj7DA0YVjl8PWiuH4zfdZeu3yiLVvHfY8ah2wG0g,2759
-judgeval-0.0.26.dist-info/METADATA,sha256=rhTpfY5GRclxtkkXU4RrUj1ckpuxd2xsgF53oQyK6qo,5418
-judgeval-0.0.26.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.0.26.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.0.26.dist-info/RECORD,,
+judgeval-0.0.27.dist-info/METADATA,sha256=yoUWIaLIDPksMYQSxDIbVFjtFVCxim6-5LSQ2P13a-U,5418
+judgeval-0.0.27.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.0.27.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.0.27.dist-info/RECORD,,

judgeval/data/api_example.py

@@ -1,98 +0,0 @@
-from typing import List, Optional, Dict, Any, Union
-from pydantic import BaseModel, ConfigDict, model_validator
-
-from judgeval.data.example import Example
-from judgeval.data.scorer_data import ScorerData
-from judgeval.common.logger import debug, error
-
-class ProcessExample(BaseModel):
-    """
-    ProcessExample is an `Example` object that contains intermediate information 
-    about an undergoing evaluation on the original `Example`. It is used purely for
-    internal operations and keeping track of the evaluation process.
-    """
-    name: str
-    input: Optional[str] = None
-    actual_output: Optional[Union[str, List[str]]] = None
-    expected_output: Optional[Union[str, List[str]]] = None
-    context: Optional[list] = None
-    retrieval_context: Optional[list] = None
-    tools_called: Optional[list] = None
-    expected_tools: Optional[list] = None
-
-    # make these optional, not all test cases in a conversation will be evaluated
-    success: Optional[bool] = None
-    scorers_data: Optional[List[ScorerData]] = None
-    run_duration: Optional[float] = None 
-    evaluation_cost: Optional[float] = None
-
-    order: Optional[int] =  None
-    # These should map 1 to 1 from golden
-    additional_metadata: Optional[Dict] = None
-    comments: Optional[str] = None
-    trace_id: Optional[str] = None
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-
-    def update_scorer_data(self, scorer_data: ScorerData):
-        """
-        Updates scorer data field of test case after the scorers have been
-        evaluated on this test case.
-        """
-        debug(f"Updating scorer data for example '{self.name}' with scorer: {scorer_data}")
-        # self.scorers_data is a list of ScorerData objects that contain the 
-        # evaluation results of each scorer on this test case
-        if self.scorers_data is None:
-            self.scorers_data = [scorer_data]
-        else:
-            self.scorers_data.append(scorer_data)
-
-        if self.success is None:
-            # self.success will be None when it is a message
-            # in that case we will be setting success for the first time
-            self.success = scorer_data.success
-        else:
-            if scorer_data.success is False:
-                debug(f"Example '{self.name}' marked as failed due to scorer: {scorer_data}")
-                self.success = False
-
-    def update_run_duration(self, run_duration: float):
-        self.run_duration = run_duration
-    
-
-def create_process_example(
-    example: Example,
-) -> ProcessExample:
-    """
-    When an LLM Test Case is executed, we track its progress using an ProcessExample.
-
-    This will track things like the success of the test case, as well as the metadata (such as verdicts and claims in Faithfulness).
-    """
-    success = True
-    if example.name is not None:
-        name = example.name
-    else:
-        name = "Test Case Placeholder"
-        debug(f"No name provided for example, using default name: {name}")
-    order = None
-    scorers_data = []
-
-    debug(f"Creating ProcessExample for: {name}")
-    process_ex = ProcessExample(
-        name=name,
-        input=example.input,
-        actual_output=example.actual_output,
-        expected_output=example.expected_output,
-        context=example.context,
-        retrieval_context=example.retrieval_context,
-        tools_called=example.tools_called,
-        expected_tools=example.expected_tools,
-        success=success,
-        scorers_data=scorers_data,
-        run_duration=None,
-        evaluation_cost=None,
-        order=order,
-        additional_metadata=example.additional_metadata,
-        trace_id=example.trace_id
-    )
-    return process_ex
-