judgeval 0.0.35__py3-none-any.whl → 0.0.36__py3-none-any.whl

judgeval/judgment_client.py

@@ -232,11 +232,17 @@ class JudgmentClient(metaclass=SingletonMeta):
         dataset.judgment_api_key = self.judgment_api_key
         return self.eval_dataset_client.push(dataset, alias, project_name, overwrite)
     
-    def append_dataset(self, alias: str, examples: List[Example], project_name: str) -> bool:
+    def append_example_dataset(self, alias: str, examples: List[Example], project_name: str) -> bool:
         """
         Appends an `EvalDataset` to the Judgment platform for storage.
         """
-        return self.eval_dataset_client.append(alias, examples, project_name)
+        return self.eval_dataset_client.append_examples(alias, examples, project_name)
+    
+    def append_sequence_dataset(self, alias: str, sequences: List[Sequence], project_name: str) -> bool:
+        """
+        Appends a `Sequence` to the Judgment platform for storage.
+        """
+        return self.eval_dataset_client.append_sequences(alias, sequences, project_name)
     
     def pull_dataset(self, alias: str, project_name: str) -> EvalDataset:
         """

judgeval/run_evaluation.py

@@ -198,6 +198,40 @@ def check_missing_scorer_data(results: List[ScoringResult]) -> List[ScoringResul
             )
     return results
 
+def check_experiment_type(eval_name: str, project_name: str, judgment_api_key: str, organization_id: str, is_sequence: bool) -> None:
+    """
+    Checks if the current experiment, if one exists, has the same type (examples of sequences)
+    """
+    try:
+        response = requests.post(
+            f"{ROOT_API}/check_experiment_type/",
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {judgment_api_key}",
+                "X-Organization-Id": organization_id
+            },
+            json={
+                "eval_name": eval_name,
+                "project_name": project_name,
+                "judgment_api_key": judgment_api_key,
+                "is_sequence": is_sequence
+            },
+            verify=True
+        )
+        
+        if response.status_code == 422:
+            error(f"{response.json()}")
+            raise ValueError(f"{response.json()}")
+        
+        if not response.ok:
+            response_data = response.json()
+            error_message = response_data.get('detail', 'An unknown error occurred.')
+            error(f"Error checking eval run name: {error_message}")
+            raise JudgmentAPIError(error_message)
+            
+    except requests.exceptions.RequestException as e:
+        error(f"Failed to check if experiment type exists: {str(e)}")
+        raise JudgmentAPIError(f"Failed to check if experiment type exists: {str(e)}")
 
 def check_eval_run_name_exists(eval_name: str, project_name: str, judgment_api_key: str, organization_id: str) -> None:
     """
@@ -264,7 +298,7 @@ def log_evaluation_results(merged_results: List[ScoringResult], run: Union[Evalu
                 "X-Organization-Id": run.organization_id
             },
             json={
-                "results": [result.model_dump(warnings=False) for result in merged_results],
+                "results": merged_results,
                 "run": run.model_dump(warnings=False)
             },
             verify=True
@@ -318,21 +352,18 @@ def run_with_spinner(message: str, func, *args, **kwargs) -> Any:
 
         return result
 
-def check_examples(examples: List[Example], scorers: List[APIJudgmentScorer]) -> None:
+def check_examples(examples: List[Example], scorers: List[Union[APIJudgmentScorer, JudgevalScorer]]) -> None:
     """
     Checks if the example contains the necessary parameters for the scorer.
     """
     for scorer in scorers:
-        if isinstance(scorer, APIJudgmentScorer):
-            for example in examples:
-                missing_params = []
-                for param in scorer.required_params:
-                    if getattr(example, param.value) is None:
-                        missing_params.append(f"'{param.value}'")
-                if missing_params:
-                    # We do this because we want to inform users that an example is missing parameters for a scorer
-                    # Example ID (usually random UUID) does not provide any helpful information for the user but printing the entire example is overdoing it
-                    print(f"WARNING: Example {example.example_id} is missing the following parameters: {missing_params} for scorer {scorer.score_type.value}")
+        for example in examples:
+            missing_params = []
+            for param in scorer.required_params:
+                if getattr(example, param.value) is None:
+                    missing_params.append(f"'{param.value}'")
+            if missing_params:
+                print(f"WARNING: Example {example.example_id} is missing the following parameters: {missing_params} for scorer {scorer.score_type.value}")
 
 def run_sequence_eval(sequence_run: SequenceRun, override: bool = False, ignore_errors: bool = True) -> List[ScoringResult]:
     # Call endpoint to check to see if eval run name exists (if we DON'T want to override and DO want to log results)
@@ -344,6 +375,17 @@ def run_sequence_eval(sequence_run: SequenceRun, override: bool = False, ignore_
             sequence_run.organization_id
         )
 
+    if sequence_run.append:
+        # Check that the current experiment, if one exists, has the same type (examples of sequences)
+        check_experiment_type(
+            sequence_run.eval_name,
+            sequence_run.project_name,
+            sequence_run.judgment_api_key,
+            sequence_run.organization_id,
+            True
+        )
+    
+
     # Execute evaluation using Judgment API
     info("Starting API evaluation")
     try:  # execute an EvaluationRun with just JudgmentScorers
@@ -359,13 +401,9 @@ def run_sequence_eval(sequence_run: SequenceRun, override: bool = False, ignore_
     
     # Convert the response data to `ScoringResult` objects
     debug("Processing API results")
-    api_results = []
-    for result in response_data["results"]:
-        api_results.append(ScoringResult(**result))
-        
     # TODO: allow for custom scorer on sequences
     if sequence_run.log_results:
-        pretty_str = run_with_spinner("Logging Results: ", log_evaluation_results, api_results, sequence_run)
+        pretty_str = run_with_spinner("Logging Results: ", log_evaluation_results, response_data["results"], sequence_run)
         rprint(pretty_str)
     
     
@@ -404,6 +442,16 @@ def run_eval(evaluation_run: EvaluationRun, override: bool = False, ignore_error
             evaluation_run.organization_id
         )
     
+    if evaluation_run.append:
+        # Check that the current experiment, if one exists, has the same type (examples of sequences)
+        check_experiment_type(
+            evaluation_run.eval_name,
+            evaluation_run.project_name,
+            evaluation_run.judgment_api_key,
+            evaluation_run.organization_id,
+            False
+        )
+    
     # Set example IDs if not already set
     debug("Initializing examples with IDs and timestamps")
     for idx, example in enumerate(evaluation_run.examples):
@@ -539,7 +587,8 @@ def run_eval(evaluation_run: EvaluationRun, override: bool = False, ignore_error
         #     )
         # print(merged_results)
         if evaluation_run.log_results:
-            pretty_str = run_with_spinner("Logging Results: ", log_evaluation_results, merged_results, evaluation_run)
+            send_results = [result.model_dump(warnings=False) for result in merged_results]
+            pretty_str = run_with_spinner("Logging Results: ", log_evaluation_results, send_results, evaluation_run)
             rprint(pretty_str)
 
         for i, result in enumerate(merged_results):

judgeval/scorers/score.py

@@ -271,6 +271,7 @@ async def a_execute_scoring(
     Returns:
         List[ScoringResult]: A list of `ScoringResult` objects containing the evaluation results.
     """
+
     semaphore = asyncio.Semaphore(max_concurrent)
 
     async def execute_with_semaphore(func: Callable, *args, **kwargs):

{judgeval-0.0.35.dist-info → judgeval-0.0.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: judgeval
-Version: 0.0.35
+Version: 0.0.36
 Summary: Judgeval Package
 Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
 Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues
@@ -11,7 +11,6 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.11
 Requires-Dist: anthropic
-Requires-Dist: boto3==1.38.3
 Requires-Dist: fastapi
 Requires-Dist: google-genai
 Requires-Dist: langchain

{judgeval-0.0.35.dist-info → judgeval-0.0.36.dist-info}/RECORD

@@ -1,16 +1,16 @@
 judgeval/__init__.py,sha256=x9HWt4waJwJMAqTuJSg2MezF9Zg-macEjeU-ajbly-8,330
 judgeval/clients.py,sha256=6VQmEqmfCngUdS2MuPBIpHvtDFqOENm8-_BmMvjLyRQ,944
-judgeval/constants.py,sha256=_XmVAkebMyGrDvvanAVlMgVd4p6MLHdEVsTQFI0kz1k,5411
+judgeval/constants.py,sha256=Gc1xpft2BkFRUIjj-puCzILsG1EUOEs8V-bUWP9b1WM,5508
 judgeval/evaluation_run.py,sha256=WGzx-Ug2qhSmunFo8NrmSstBRsOUc5KpKq0Lc51rqsM,6739
-judgeval/judgment_client.py,sha256=brRYmphZR-2IUre9kdOhfse1mYDilcIqUzzH21ROAdk,22208
+judgeval/judgment_client.py,sha256=slYLE80FqEIsqgShMtML4I64p-RrEfELbMgZnlXhxP0,22515
 judgeval/rules.py,sha256=jkh1cXXcUf8oRY7xJUZfcQBYWn_rjUW4GvrhRt15PeU,20265
-judgeval/run_evaluation.py,sha256=elMpFHahyeukKKa09fmJM3c_afwJ00mbZRqm18l5f00,28481
+judgeval/run_evaluation.py,sha256=1G-KYNHowfMKTD5j3cDd4EuEme00AqZkn6wpP3zMKUo,30241
 judgeval/version_check.py,sha256=bvJEidB7rAeXozoUbN9Yb97QOR_s2hgvpvj74jJ5HlY,943
 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/s3_storage.py,sha256=W8wq9S7qJZdqdBR4sk3aEZ4K3-pz40DOoolOJrWs9Vo,3768
-judgeval/common/tracer.py,sha256=YsObK8VQXp1DDbU9xncU8NjuY-JUI54BqmG4olezrZc,92507
+judgeval/common/tracer.py,sha256=bkN0Jol0mNosJeEJMtjM54jJDhEYL3OSBtkS4FB1m8E,105461
 judgeval/common/utils.py,sha256=LUQV5JfDr6wj7xHAJoNq-gofNZ6mjXbeKrGKzBME1KM,33533
 judgeval/data/__init__.py,sha256=xuKx_KCVHGp6CXvQuVmKl3v7pJp-qDaz0NccKxwjtO0,481
 judgeval/data/custom_example.py,sha256=QRBqiRiZS8UgVeTRHY0r1Jzm6yAYsyg6zmHxQGxdiQs,739
@@ -20,9 +20,9 @@ judgeval/data/scorer_data.py,sha256=JVlaTx1EP2jw2gh3Vgx1CSEsvIFABAN26IquKyxwiJQ,
 judgeval/data/sequence.py,sha256=FmKVdzQP5VTujRCHDWk097MKRR-rJgbsdrxyCKee6tA,1994
 judgeval/data/sequence_run.py,sha256=RmYjfWKMWg-pcF5PLeiWfrhuDkjDZi5VEmAIEXN3Ib0,2104
 judgeval/data/datasets/__init__.py,sha256=IdNKhQv9yYZ_op0rdBacrFaFVmiiYQ3JTzXzxOTsEVQ,176
-judgeval/data/datasets/dataset.py,sha256=dhLo30hvpmmOK2R6O5wDs_neawUJ4lS8bb4S42SufNQ,13034
-judgeval/data/datasets/eval_dataset_client.py,sha256=xjj66BO9Es9IxXqzQe1RT_e0kpeKlt7OrhRoSuj4KHM,15085
-judgeval/integrations/langgraph.py,sha256=J-cQfFP52TjJewdSTe-fcsUC4HDvjNbXoxmbmF0SgiE,11743
+judgeval/data/datasets/dataset.py,sha256=RmZ28oyDPfRsCx4k5ftMscoq0M0LN78MW6ofTiM81BI,13134
+judgeval/data/datasets/eval_dataset_client.py,sha256=uirHpkpLOfygXIz0xKAGTPx1qjbBTzdLFQK6yyoZduU,17544
+judgeval/integrations/langgraph.py,sha256=7LpWDpb8wgOkeRJvlr2COvF_O1f01zm-cwsI5trKoiw,123150
 judgeval/judges/__init__.py,sha256=6X7VSwrwsdxGBNxCyapVRWGghhKOy3MVxFNMQ62kCXM,308
 judgeval/judges/base_judge.py,sha256=ch_S7uBB7lyv44Lf1d7mIGFpveOO58zOkkpImKgd9_4,994
 judgeval/judges/litellm_judge.py,sha256=EIL58Teptv8DzZUO3yP2RDQCDq-aoBB6HPZzPdK6KTg,2424
@@ -34,7 +34,7 @@ judgeval/scorers/api_scorer.py,sha256=NQ_CrrUPhSUk1k2Q8rKpCG_TU2FT32sFEqvb-Yi54B
 judgeval/scorers/exceptions.py,sha256=eGW5CuJgZ5YJBFrE4FHDSF651PO1dKAZ379mJ8gOsfo,178
 judgeval/scorers/judgeval_scorer.py,sha256=79-JJurqHP-qTaWNWInx4SjvQYwXc9lvfPPNgwsh2yA,6773
 judgeval/scorers/prompt_scorer.py,sha256=PaAs2qRolw1P3_I061Xvk9qzvF4O-JR8g_39RqXnHcM,17728
-judgeval/scorers/score.py,sha256=r9QiT4-LIvivcJ6XxByrbswKSO8eQTtAD1UlXT_lcmo,18741
+judgeval/scorers/score.py,sha256=fZuaZPumqkLCWcZdpTn3bJeHPNHXaDqgyb0WBp2EYgE,18742
 judgeval/scorers/utils.py,sha256=iHQVTlIANbmCTXz9kTeSdOytgUZ_T74Re61ajqsk_WQ,6827
 judgeval/scorers/judgeval_scorers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 judgeval/scorers/judgeval_scorers/api_scorers/__init__.py,sha256=_sDUBxSG536KGqXNi6dFpaYKghjEAadxBxaaxV9HuuE,1764
@@ -57,7 +57,7 @@ judgeval/scorers/judgeval_scorers/classifiers/text2sql/__init__.py,sha256=8iTzMv
 judgeval/scorers/judgeval_scorers/classifiers/text2sql/text2sql_scorer.py,sha256=ly72Z7s_c8NID6-nQnuW8qEGEW2MqdvpJ-5WfXzbAQg,2579
 judgeval/tracer/__init__.py,sha256=wy3DYpH8U_z0GO_K_gOSkK0tTTD-u5eLDo0T5xIBoAc,147
 judgeval/utils/alerts.py,sha256=O19Xj7DA0YVjl8PWiuH4zfdZeu3yiLVvHfY8ah2wG0g,2759
-judgeval-0.0.35.dist-info/METADATA,sha256=oAaDqpJCCZxUBOoVPTFbSjZgZ5xJMpGTxjngoJqmTO8,6126
-judgeval-0.0.35.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.0.35.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.0.35.dist-info/RECORD,,
+judgeval-0.0.36.dist-info/METADATA,sha256=oexg66X9idECkevPAF2VkuQJBt-hYHvKmsZz5p5Y-LI,6097
+judgeval-0.0.36.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.0.36.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.0.36.dist-info/RECORD,,