judgeval 0.14.0__py3-none-any.whl → 0.15.0__py3-none-any.whl

judgeval/api/__init__.py

@@ -111,16 +111,6 @@ class JudgmentSyncClient:
             payload,
         )
 
-    def get_evaluation_status(self, experiment_run_id: str, project_name: str) -> Any:
-        query_params = {}
-        query_params["experiment_run_id"] = experiment_run_id
-        query_params["project_name"] = project_name
-        return self._request(
-            "GET",
-            url_for("/get_evaluation_status/"),
-            query_params,
-        )
-
     def datasets_insert_examples_for_judgeval(
         self, payload: DatasetInsertExamples
     ) -> Any:
@@ -318,18 +308,6 @@ class JudgmentAsyncClient:
             payload,
         )
 
-    async def get_evaluation_status(
-        self, experiment_run_id: str, project_name: str
-    ) -> Any:
-        query_params = {}
-        query_params["experiment_run_id"] = experiment_run_id
-        query_params["project_name"] = project_name
-        return await self._request(
-            "GET",
-            url_for("/get_evaluation_status/"),
-            query_params,
-        )
-
     async def datasets_insert_examples_for_judgeval(
         self, payload: DatasetInsertExamples
     ) -> Any:

judgeval/api/api_types.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  .openapi.json
-#   timestamp: 2025-09-24T18:25:18+00:00
+#   timestamp: 2025-09-30T18:06:51+00:00
 
 from __future__ import annotations
 from typing import Any, Dict, List, Literal, Optional, TypedDict, Union
@@ -24,6 +24,15 @@ class DatasetsFetch(TypedDict):
     project_name: str
 
 
+class DatasetsTableRow(TypedDict):
+    dataset_id: str
+    name: str
+    created_at: str
+    kind: Literal["trace", "example"]
+    entries: int
+    creator: str
+
+
 class ProjectAdd(TypedDict):
     project_name: str
 
@@ -54,6 +63,8 @@ class SavePromptScorerRequest(TypedDict):
     threshold: float
     model: NotRequired[str]
     is_trace: NotRequired[bool]
+    options: NotRequired[Optional[Dict[str, float]]]
+    description: NotRequired[Optional[str]]
 
 
 class SavePromptScorerResponse(TypedDict):
@@ -143,6 +154,8 @@ class PromptScorer(TypedDict):
     prompt: str
     threshold: float
     model: NotRequired[str]
+    options: NotRequired[Optional[Dict[str, float]]]
+    description: NotRequired[Optional[str]]
     created_at: NotRequired[Optional[str]]
     updated_at: NotRequired[Optional[str]]
     is_trace: NotRequired[Optional[bool]]
@@ -176,18 +189,10 @@ class OtelTraceSpan(TypedDict):
     resource_attributes: NotRequired[Optional[Dict[str, Any]]]
     span_attributes: NotRequired[Optional[Dict[str, Any]]]
     duration: NotRequired[Optional[int]]
-    status_code: NotRequired[Optional[str]]
+    status_code: NotRequired[Optional[int]]
     status_message: NotRequired[Optional[str]]
     events: NotRequired[Optional[List[Dict[str, Any]]]]
     links: NotRequired[Optional[List[Dict[str, Any]]]]
-    legacy_span_id: NotRequired[Optional[str]]
-    inputs: NotRequired[Optional[Dict[str, Any]]]
-    output: Any
-    error: NotRequired[Optional[Dict[str, Any]]]
-    agent_id: NotRequired[Optional[str]]
-    cumulative_llm_cost: NotRequired[Optional[float]]
-    state_after: NotRequired[Optional[Dict[str, Any]]]
-    state_before: NotRequired[Optional[Dict[str, Any]]]
 
 
 class OtelSpanListItemScores(TypedDict):
@@ -202,7 +207,7 @@ class OtelSpanDetailScores(TypedDict):
     score: float
     reason: NotRequired[Optional[str]]
     name: str
-    data: NotRequired[Optional[Dict[str, Any]]]
+    example_id: NotRequired[Optional[str]]
 
 
 class ExampleEvaluationRun(TypedDict):
@@ -240,15 +245,6 @@ class DatasetInsertExamples(TypedDict):
     project_name: str
 
 
-class DatasetInfo(TypedDict):
-    dataset_id: str
-    name: str
-    created_at: str
-    dataset_kind: DatasetKind
-    entries: int
-    creator: str
-
-
 class DatasetCreate(TypedDict):
     name: str
     dataset_kind: DatasetKind
@@ -275,14 +271,14 @@ class OtelTraceListItem(TypedDict):
     organization_id: str
     project_id: str
     trace_id: str
-    timestamp: str
+    created_at: str
     duration: NotRequired[Optional[int]]
     has_notification: NotRequired[Optional[bool]]
     tags: NotRequired[Optional[List[str]]]
     experiment_run_id: NotRequired[Optional[str]]
     span_name: NotRequired[Optional[str]]
-    cumulative_llm_cost: NotRequired[Optional[float]]
-    error: NotRequired[Optional[Dict[str, Any]]]
+    llm_cost: NotRequired[Optional[float]]
+    error: NotRequired[str]
     scores: NotRequired[List[OtelSpanListItemScores]]
     customer_id: NotRequired[Optional[str]]
     input_preview: NotRequired[Optional[str]]
@@ -306,9 +302,9 @@ class OtelSpanDetail(TypedDict):
     resource_attributes: NotRequired[Optional[Dict[str, Any]]]
     span_attributes: NotRequired[Optional[Dict[str, Any]]]
     duration: NotRequired[Optional[int]]
-    status_code: NotRequired[Optional[str]]
+    status_code: NotRequired[Optional[int]]
     status_message: NotRequired[Optional[str]]
-    events: NotRequired[Optional[Union[List[Dict[str, Any]], Dict[str, Any]]]]
+    events: NotRequired[Optional[List[Dict[str, Any]]]]
     links: NotRequired[Optional[Union[List[Dict[str, Any]], Dict[str, Any]]]]
     llm_cost: NotRequired[Optional[float]]
     prompt_tokens: NotRequired[Optional[int]]
@@ -331,5 +327,5 @@ class DatasetReturn(TypedDict):
     name: str
     project_name: str
     dataset_kind: DatasetKind
-    examples: NotRequired[Optional[List[Example]]]
+    examples: NotRequired[List[Example]]
     traces: NotRequired[Optional[List[DatasetTraceWithSpans]]]

judgeval/data/judgment_types.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  .openapi.json
-#   timestamp: 2025-09-24T18:25:17+00:00
+#   timestamp: 2025-09-30T18:06:50+00:00
 
 from __future__ import annotations
 from typing import Annotated, Any, Dict, List, Optional, Union
@@ -26,6 +26,20 @@ class DatasetsFetch(BaseModel):
     project_name: Annotated[str, Field(title="Project Name")]
 
 
+class Kind(Enum):
+    trace = "trace"
+    example = "example"
+
+
+class DatasetsTableRow(BaseModel):
+    dataset_id: Annotated[str, Field(title="Dataset Id")]
+    name: Annotated[str, Field(title="Name")]
+    created_at: Annotated[str, Field(title="Created At")]
+    kind: Annotated[Kind, Field(title="Kind")]
+    entries: Annotated[int, Field(title="Entries")]
+    creator: Annotated[str, Field(title="Creator")]
+
+
 class ProjectAdd(BaseModel):
     project_name: Annotated[str, Field(title="Project Name")]
 
@@ -56,6 +70,8 @@ class SavePromptScorerRequest(BaseModel):
     threshold: Annotated[float, Field(title="Threshold")]
     model: Annotated[Optional[str], Field(title="Model")] = "gpt-5"
     is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = False
+    options: Annotated[Optional[Dict[str, float]], Field(title="Options")] = None
+    description: Annotated[Optional[str], Field(title="Description")] = None
 
 
 class SavePromptScorerResponse(BaseModel):
@@ -156,6 +172,8 @@ class PromptScorer(BaseModel):
     prompt: Annotated[str, Field(title="Prompt")]
     threshold: Annotated[float, Field(title="Threshold")]
     model: Annotated[Optional[str], Field(title="Model")] = "gpt-5"
+    options: Annotated[Optional[Dict[str, float]], Field(title="Options")] = None
+    description: Annotated[Optional[str], Field(title="Description")] = None
     created_at: Annotated[Optional[AwareDatetime], Field(title="Created At")] = None
     updated_at: Annotated[Optional[AwareDatetime], Field(title="Updated At")] = None
     is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = False
@@ -195,22 +213,10 @@ class OtelTraceSpan(BaseModel):
         Optional[Dict[str, Any]], Field(title="Span Attributes")
     ] = None
     duration: Annotated[Optional[int], Field(title="Duration")] = None
-    status_code: Annotated[Optional[str], Field(title="Status Code")] = None
+    status_code: Annotated[Optional[int], Field(title="Status Code")] = None
     status_message: Annotated[Optional[str], Field(title="Status Message")] = None
     events: Annotated[Optional[List[Dict[str, Any]]], Field(title="Events")] = None
     links: Annotated[Optional[List[Dict[str, Any]]], Field(title="Links")] = None
-    legacy_span_id: Annotated[Optional[str], Field(title="Legacy Span Id")] = None
-    inputs: Annotated[Optional[Dict[str, Any]], Field(title="Inputs")] = None
-    output: Annotated[Any, Field(title="Output")]
-    error: Annotated[Optional[Dict[str, Any]], Field(title="Error")] = None
-    agent_id: Annotated[Optional[str], Field(title="Agent Id")] = None
-    cumulative_llm_cost: Annotated[
-        Optional[float], Field(title="Cumulative Llm Cost")
-    ] = None
-    state_after: Annotated[Optional[Dict[str, Any]], Field(title="State After")] = None
-    state_before: Annotated[Optional[Dict[str, Any]], Field(title="State Before")] = (
-        None
-    )
 
 
 class OtelSpanListItemScores(BaseModel):
@@ -225,7 +231,7 @@ class OtelSpanDetailScores(BaseModel):
     score: Annotated[float, Field(title="Score")]
     reason: Annotated[Optional[str], Field(title="Reason")] = None
     name: Annotated[str, Field(title="Name")]
-    data: Annotated[Optional[Dict[str, Any]], Field(title="Data")] = None
+    example_id: Annotated[Optional[str], Field(title="Example Id")] = None
 
 
 class ExampleEvaluationRun(BaseModel):
@@ -273,15 +279,6 @@ class DatasetInsertExamples(BaseModel):
     project_name: Annotated[str, Field(title="Project Name")]
 
 
-class DatasetInfo(BaseModel):
-    dataset_id: Annotated[str, Field(title="Dataset Id")]
-    name: Annotated[str, Field(title="Name")]
-    created_at: Annotated[str, Field(title="Created At")]
-    dataset_kind: DatasetKind
-    entries: Annotated[int, Field(title="Entries")]
-    creator: Annotated[str, Field(title="Creator")]
-
-
 class DatasetCreate(BaseModel):
     name: Annotated[str, Field(title="Name")]
     dataset_kind: DatasetKind
@@ -310,16 +307,14 @@ class OtelTraceListItem(BaseModel):
     organization_id: Annotated[str, Field(title="Organization Id")]
     project_id: Annotated[str, Field(title="Project Id")]
     trace_id: Annotated[str, Field(title="Trace Id")]
-    timestamp: Annotated[str, Field(title="Timestamp")]
+    created_at: Annotated[AwareDatetime, Field(title="Created At")]
     duration: Annotated[Optional[int], Field(title="Duration")] = None
     has_notification: Annotated[Optional[bool], Field(title="Has Notification")] = None
     tags: Annotated[Optional[List[str]], Field(title="Tags")] = None
     experiment_run_id: Annotated[Optional[str], Field(title="Experiment Run Id")] = None
     span_name: Annotated[Optional[str], Field(title="Span Name")] = None
-    cumulative_llm_cost: Annotated[
-        Optional[float], Field(title="Cumulative Llm Cost")
-    ] = None
-    error: Annotated[Optional[Dict[str, Any]], Field(title="Error")] = None
+    llm_cost: Annotated[Optional[float], Field(title="Llm Cost")] = None
+    error: Annotated[Optional[str], Field(title="Error")] = ""
     scores: Annotated[
         Optional[List[OtelSpanListItemScores]], Field(title="Scores")
     ] = []
@@ -334,7 +329,7 @@ class OtelTraceListItem(BaseModel):
 class OtelSpanDetail(BaseModel):
     organization_id: Annotated[str, Field(title="Organization Id")]
     project_id: Annotated[str, Field(title="Project Id")]
-    timestamp: Annotated[str, Field(title="Timestamp")]
+    timestamp: Annotated[AwareDatetime, Field(title="Timestamp")]
     trace_id: Annotated[str, Field(title="Trace Id")]
     span_id: Annotated[str, Field(title="Span Id")]
     parent_span_id: Annotated[Optional[str], Field(title="Parent Span Id")] = None
@@ -349,11 +344,9 @@ class OtelSpanDetail(BaseModel):
         Optional[Dict[str, Any]], Field(title="Span Attributes")
     ] = None
     duration: Annotated[Optional[int], Field(title="Duration")] = None
-    status_code: Annotated[Optional[str], Field(title="Status Code")] = None
+    status_code: Annotated[Optional[int], Field(title="Status Code")] = None
     status_message: Annotated[Optional[str], Field(title="Status Message")] = None
-    events: Annotated[
-        Optional[Union[List[Dict[str, Any]], Dict[str, Any]]], Field(title="Events")
-    ] = None
+    events: Annotated[Optional[List[Dict[str, Any]]], Field(title="Events")] = None
     links: Annotated[
         Optional[Union[List[Dict[str, Any]], Dict[str, Any]]], Field(title="Links")
     ] = None

judgeval/dataset/__init__.py

@@ -20,7 +20,7 @@ class DatasetInfo:
     dataset_id: str
     name: str
     created_at: str
-    dataset_kind: DatasetKind
+    kind: DatasetKind
     entries: int
     creator: str
 

judgeval/evaluation/__init__.py

@@ -84,7 +84,7 @@ def log_evaluation_results(
 
 def _poll_evaluation_until_complete(
     evaluation_run: ExampleEvaluationRun,
-    expected_scorer_data_count: int,
+    expected_examples_count: int,
     poll_interval_seconds: float = 5,
     max_failures: int = 5,
     max_poll_count: int = 60,  # This should be equivalent to 5 minutes
@@ -117,29 +117,22 @@ def _poll_evaluation_until_complete(
         poll_count += 1
         try:
             # Check status
-            status_response = api_client.get_evaluation_status(
-                experiment_run_id, project_name
-            )
-
-            if status_response.get("status") != "completed":
-                time.sleep(poll_interval_seconds)
-                continue
-
-            example_scorer_pairings = status_response.get("results", [])
-            if len(example_scorer_pairings) != expected_scorer_data_count:
-                time.sleep(poll_interval_seconds)
-                continue
-
             results_response = api_client.fetch_experiment_run(
                 {
                     "experiment_run_id": experiment_run_id,
                     "project_name": project_name,
                 }
             )
+
+            example_scorer_pairings = results_response.get("results", [])
+            if len(example_scorer_pairings) != expected_examples_count:
+                time.sleep(poll_interval_seconds)
+                continue
+
             url = results_response.get("ui_results_url")
 
             scoring_result_list = []
-            for res in results_response.get("results", []):
+            for res in example_scorer_pairings:
                 example = res.get("data", {}).copy()
                 example["example_id"] = res.get("example_id")
                 scoring_result = ScoringResult(
@@ -241,14 +234,9 @@ def run_eval(
                 )
                 raise JudgmentRuntimeError(error_message)
 
-            num_scorers = (
-                len(evaluation_run.judgment_scorers)
-                if evaluation_run.judgment_scorers
-                else sum(1 for cs in evaluation_run.custom_scorers if cs.server_hosted)
-            )
             results, url = _poll_evaluation_until_complete(
                 evaluation_run=evaluation_run,
-                expected_scorer_data_count=(num_scorers * len(evaluation_run.examples)),
+                expected_examples_count=len(evaluation_run.examples),
             )
         finally:
             stop_event.set()

judgeval/integrations/openlit/__init__.py

@@ -0,0 +1,50 @@
+from abc import ABC
+from judgeval.tracer import Tracer
+from judgeval.logger import judgeval_logger
+from judgeval.utils.url import url_for
+
+
+try:
+    import openlit  # type: ignore
+except ImportError:
+    raise ImportError(
+        "Openlit is not installed and required for the openlit integration. Please install it with `pip install openlit`."
+    )
+
+
+class Openlit(ABC):
+    @staticmethod
+    def initialize(
+        **kwargs,
+    ):
+        tracer = Tracer.get_instance()
+        if not tracer or not tracer._initialized:
+            raise ValueError(
+                "Openlit must be initialized after the tracer has been initialized. Please create the Tracer instance first before initializing Openlit."
+            )
+
+        api_key = tracer.api_key
+        organization_id = tracer.organization_id
+        project_name = tracer.project_name
+
+        project_id = Tracer._resolve_project_id(project_name, api_key, organization_id)
+        if not project_id:
+            judgeval_logger.warning(
+                f"Project {project_name} not found. Please create it first at https://app.judgmentlabs.ai/org/{organization_id}/projects."
+            )
+            return
+
+        openlit.init(
+            service_name=project_name,
+            otlp_endpoint=url_for("/otel"),
+            otlp_headers={
+                "Authorization": f"Bearer {api_key}",
+                "X-Organization-Id": organization_id,
+                "X-Project-Id": project_id,
+            },
+            tracer=tracer.get_tracer(),
+            **kwargs,
+        )
+
+
+__all__ = ["Openlit"]

judgeval/scorers/judgeval_scorers/api_scorers/prompt_scorer.py

@@ -4,20 +4,23 @@ from judgeval.scorers.api_scorer import (
     TraceAPIScorerConfig,
 )
 from judgeval.constants import APIScorerType
-from typing import Dict, Any
+from typing import Dict, Any, Optional
 from judgeval.api import JudgmentSyncClient
 from judgeval.exceptions import JudgmentAPIError
 import os
 from judgeval.logger import judgeval_logger
 from abc import ABC
 from judgeval.env import JUDGMENT_DEFAULT_GPT_MODEL
+from copy import copy
 
 
 def push_prompt_scorer(
     name: str,
     prompt: str,
     threshold: float,
+    options: Optional[Dict[str, float]] = None,
     model: str = JUDGMENT_DEFAULT_GPT_MODEL,
+    description: Optional[str] = None,
     judgment_api_key: str = os.getenv("JUDGMENT_API_KEY") or "",
     organization_id: str = os.getenv("JUDGMENT_ORG_ID") or "",
     is_trace: bool = False,
@@ -29,7 +32,9 @@ def push_prompt_scorer(
                 "name": name,
                 "prompt": prompt,
                 "threshold": threshold,
+                "options": options,
                 "model": model,
+                "description": description,
                 "is_trace": is_trace,
             }
         )
@@ -98,6 +103,8 @@ def scorer_exists(
 class BasePromptScorer(ABC, APIScorerConfig):
     score_type: APIScorerType
     prompt: str
+    options: Optional[Dict[str, float]] = None
+    description: Optional[str] = None
     judgment_api_key: str = os.getenv("JUDGMENT_API_KEY") or ""
     organization_id: str = os.getenv("JUDGMENT_ORG_ID") or ""
 
@@ -124,7 +131,9 @@ class BasePromptScorer(ABC, APIScorerConfig):
             name=name,
             prompt=scorer_config["prompt"],
             threshold=scorer_config["threshold"],
+            options=scorer_config.get("options"),
             model=scorer_config.get("model"),
+            description=scorer_config.get("description"),
             judgment_api_key=judgment_api_key,
             organization_id=organization_id,
         )
@@ -135,7 +144,9 @@ class BasePromptScorer(ABC, APIScorerConfig):
         name: str,
         prompt: str,
         threshold: float = 0.5,
+        options: Optional[Dict[str, float]] = None,
         model: str = JUDGMENT_DEFAULT_GPT_MODEL,
+        description: Optional[str] = None,
         judgment_api_key: str = os.getenv("JUDGMENT_API_KEY") or "",
         organization_id: str = os.getenv("JUDGMENT_ORG_ID") or "",
     ):
@@ -150,7 +161,9 @@ class BasePromptScorer(ABC, APIScorerConfig):
                 name,
                 prompt,
                 threshold,
+                options,
                 model,
+                description,
                 judgment_api_key,
                 organization_id,
                 is_trace,
@@ -161,7 +174,9 @@ class BasePromptScorer(ABC, APIScorerConfig):
                 name=name,
                 prompt=prompt,
                 threshold=threshold,
+                options=options,
                 model=model,
+                description=description,
                 judgment_api_key=judgment_api_key,
                 organization_id=organization_id,
             )
@@ -199,6 +214,22 @@ class BasePromptScorer(ABC, APIScorerConfig):
         self.push_prompt_scorer()
         judgeval_logger.info(f"Successfully updated model for {self.name}")
 
+    def set_options(self, options: Optional[Dict[str, float]]):
+        """
+        Updates the options of the scorer.
+        """
+        self.options = options
+        self.push_prompt_scorer()
+        judgeval_logger.info(f"Successfully updated options for {self.name}")
+
+    def set_description(self, description: Optional[str]):
+        """
+        Updates the description of the scorer.
+        """
+        self.description = description
+        self.push_prompt_scorer()
+        judgeval_logger.info(f"Successfully updated description for {self.name}")
+
     def append_to_prompt(self, prompt_addition: str):
         """
         Appends a string to the prompt.
@@ -226,7 +257,19 @@ class BasePromptScorer(ABC, APIScorerConfig):
         """
         return self.model
 
-    def get_name(self) -> str | None:
+    def get_options(self) -> Dict[str, float] | None:
+        """
+        Returns the options of the scorer.
+        """
+        return copy(self.options) if self.options is not None else None
+
+    def get_description(self) -> str | None:
+        """
+        Returns the description of the scorer.
+        """
+        return self.description
+
+    def get_name(self) -> str:
         """
         Returns the name of the scorer.
         """
@@ -241,6 +284,8 @@ class BasePromptScorer(ABC, APIScorerConfig):
             "model": self.model,
             "prompt": self.prompt,
             "threshold": self.threshold,
+            "options": self.options,
+            "description": self.description,
         }
 
     def push_prompt_scorer(self):
@@ -251,14 +296,16 @@ class BasePromptScorer(ABC, APIScorerConfig):
             self.name,
             self.prompt,
             self.threshold,
+            self.options,
             self.model,
+            self.description,
             self.judgment_api_key,
             self.organization_id,
             isinstance(self, TracePromptScorer),
         )
 
     def __str__(self):
-        return f"PromptScorer(name={self.name}, model={self.model}, prompt={self.prompt}, threshold={self.threshold})"
+        return f"PromptScorer(name={self.name}, model={self.model}, prompt={self.prompt}, threshold={self.threshold}, options={self.options}, description={self.description})"
 
     def model_dump(self, *args, **kwargs) -> Dict[str, Any]:
         base = super().model_dump(*args, **kwargs)

judgeval/tracer/__init__.py

@@ -255,6 +255,10 @@ class Tracer(metaclass=SingletonMeta):
     def get_current_agent_context(self):
         return self.agent_context
 
+    def get_span_processor(self) -> JudgmentSpanProcessor:
+        """Get the internal span processor of this tracer instance."""
+        return self.judgment_processor
+
     def set_customer_id(self, customer_id: str) -> None:
         span = self.get_current_span()
         if span and span.is_recording():

judgeval/version.py

@@ -1,4 +1,4 @@
-__version__ = "0.14.0"
+__version__ = "0.15.0"
 
 
 def get_version() -> str:

{judgeval-0.14.0.dist-info → judgeval-0.15.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: judgeval
-Version: 0.14.0
+Version: 0.15.0
 Summary: Judgeval Package
 Project-URL: Homepage, https://github.com/JudgmentLabs/judgeval
 Project-URL: Issues, https://github.com/JudgmentLabs/judgeval/issues

{judgeval-0.14.0.dist-info → judgeval-0.15.0.dist-info}/RECORD

@@ -4,22 +4,23 @@ judgeval/constants.py,sha256=JZZJ1MqzZZDVk-5PRPRbmLnM8mXI-RDL5vxa1JFuscs,3408
 judgeval/env.py,sha256=37Mn4g0OkpFxXCZGlO_CLqKJnyX-jx_R24tC28XJzig,2112
 judgeval/exceptions.py,sha256=tTbfe4yoOtPXmn22UQz9-6a-5PT9uOko85xaRRwr0Sw,621
 judgeval/logger.py,sha256=ZWbp0QfT1CJnQIjV-Zle4n489nFCKEmD2-ukx--iiow,1553
-judgeval/version.py,sha256=qFLvC9WMqiLgjMPdAqGbBm-v0rO2ePVeM8dvl-2r7WA,74
+judgeval/version.py,sha256=1a6hS0-ubylneLxq8Pt0EqBRx0hSP1cO9JKaTmHazfo,74
 judgeval/warnings.py,sha256=LbGte14ppiFjrkp-JJYueZ40NWFvMkWRvPXr6r-fUWw,73
-judgeval/api/__init__.py,sha256=3Pm0qQ4ZQj76jUsJVrnuazRnYcqF3pzM_Wv_Z6lOv0w,13216
-judgeval/api/api_types.py,sha256=w45Rh2I31JaqWoUsxCK5_rr_wJ1QkWYxDLjRppXkruE,8785
+judgeval/api/__init__.py,sha256=_oDuEDBDmyPQkdfvWebvBSvrnlzg4vreETpt16frXEA,12468
+judgeval/api/api_types.py,sha256=hpUpVRCLIGF-lHHg1gIgdTaRfwS94Vh1E23vU9Z34js,8555
 judgeval/data/__init__.py,sha256=1tU0EN0ThIfQ1fad5I3dKxAfTcZ5U8cvTLcQ6qLVLU0,407
 judgeval/data/evaluation_run.py,sha256=O41p99wNAuCAf6lsLNKzkZ6W-kL9LlzCYxVls7IcKkA,4727
 judgeval/data/example.py,sha256=eGJpF-lyUH734Cg90B7WtU9f8iKoS3VFGeV6R-GVCCc,1039
-judgeval/data/judgment_types.py,sha256=rZ4Uq6Va94bHF0Obn3wKB7E5n77R5N5WTkK5o02EAzg,16285
+judgeval/data/judgment_types.py,sha256=u45rfHEtUNzXSQstJ4TcOo-yX9cZymma5W0hTtb5u34,15965
 judgeval/data/result.py,sha256=XufFGSAkBDfevPUmzSgsR9HEqytISkM0U5HkhJmsjpY,2102
 judgeval/data/scorer_data.py,sha256=HeP15ZgftFTJCF8JmDJCLWXRnZJIaGDJCzl7Hg6gWwE,2006
 judgeval/data/trace.py,sha256=zSiR3o6xt8Z46XA3M9fJBtViF0BsPO6yKp9jxdscOSc,3881
 judgeval/data/scripts/fix_default_factory.py,sha256=lvp2JwYZqz-XpD9LZNa3mANZVP-jJSZoNzolI6JWERM,591
 judgeval/data/scripts/openapi_transform.py,sha256=Sm04JClzyP1ga8KA3gkIdsae8Hlx-XU7-x0gHCQYOhg,3877
-judgeval/dataset/__init__.py,sha256=4CiV7jQUiJ8_IXnD_E-vS5OfoEr0hghBe3-OSuVoBwE,8277
-judgeval/evaluation/__init__.py,sha256=6bSC1Sw-fpJN6OkZTv4UtAoYZqkjUy7OG17lxiRX5qE,13321
+judgeval/dataset/__init__.py,sha256=kL0_tIMP3qV6t4W17HQU91ybdXMZ5iDZzyUKzyfRdyY,8269
+judgeval/evaluation/__init__.py,sha256=WcqOgQdwgtc_BwEwDz6RDlF2RczyLrNjjIevQp-_NKE,12788
 judgeval/integrations/langgraph/__init__.py,sha256=HwXmtDxaO75Kn4KPErnMb6Ne6FcpRxV_SCYVuwFsve0,332
+judgeval/integrations/openlit/__init__.py,sha256=-8D4D6-fGsWPwoOojw82OaE9X5sUbmb16x1bF-WfOmg,1571
 judgeval/judges/__init__.py,sha256=e7JnTc1TG_SwqydDHTXHIP0EBazQxt-ydMQG7ghSU5A,228
 judgeval/judges/base_judge.py,sha256=_dz0qWsKRxzXxpRY9l6mrxTRYPSF2FE4ZXkrzhZ4gbY,986
 judgeval/judges/litellm_judge.py,sha256=5vEF0IUo7HVWnOF2ww-DMke8Xkarnz32B_qbgKjc0-I,4182
@@ -39,8 +40,8 @@ judgeval/scorers/judgeval_scorers/api_scorers/answer_correctness.py,sha256=WUeFy
 judgeval/scorers/judgeval_scorers/api_scorers/answer_relevancy.py,sha256=ciiFBQQC4UDsk9qou9OiKbAR31s82eRUY1ZTt1gdM-0,407
 judgeval/scorers/judgeval_scorers/api_scorers/faithfulness.py,sha256=ucYOI6ztAjfoYmcgTDzN8u5RrehlVqrkeLEfss9b1fk,441
 judgeval/scorers/judgeval_scorers/api_scorers/instruction_adherence.py,sha256=V3RdrWhnR_vLBrtWw7QbgN9K_A-Och7-v9I2fN4z8gY,506
-judgeval/scorers/judgeval_scorers/api_scorers/prompt_scorer.py,sha256=UiX-qUVokx8W3EIr5i4_H6CGQT2pNBEYWSCtTUx1wLE,9196
-judgeval/tracer/__init__.py,sha256=iqFvWok4QBW-1bs2zCmkhw4Y_o2d2mVeiPUtQbG9Nvc,35995
+judgeval/scorers/judgeval_scorers/api_scorers/prompt_scorer.py,sha256=zJ0n3HyZ1FFBnMnTYxBi37m_3Er7ENd4HpqLjNi5Eag,10902
+judgeval/tracer/__init__.py,sha256=uIOx-2P_FVwBKhwVkkIOyEQCv3gouCZ2I8-eApocnKU,36165
 judgeval/tracer/constants.py,sha256=ae8tivAW97awJQxdRB9OMqX50wOLX3zqChT_AGkPBu0,85
 judgeval/tracer/keys.py,sha256=ho4-_w4ngTVejdSKUH80sG6vtYt4c7FEKrYpFrDfPLs,2105
 judgeval/tracer/local_eval_queue.py,sha256=KZKvSSli7B-EVzdHa4-CmXUpv0uOjGLLRa2KTPg8lRc,7320
@@ -72,8 +73,8 @@ judgeval/utils/serialize.py,sha256=QXR-8Nj5rqOrI9zLx0oRLdk6DW6Bc7j8eyF4zQ7PLxA,6
 judgeval/utils/testing.py,sha256=m5Nexv65tmfSj1XvAPK5Ear7aJ7w5xjDtZN0tLZ_RBk,2939
 judgeval/utils/url.py,sha256=Shf0v3XcbaWpL0m1eGJEEO_z4TsQCnDB2Rl25OTUmiI,195
 judgeval/utils/version_check.py,sha256=ylZQSqV7kLzEOChxvav9SCHUU4OnaCp36tXHLjdzmw0,1072
-judgeval-0.14.0.dist-info/METADATA,sha256=PN_KgV2HavJDSdkoMAnusgLD1kiKNOfXMyWEVFyYx2s,8564
-judgeval-0.14.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-judgeval-0.14.0.dist-info/entry_points.txt,sha256=-eoeD-oDLn4A7MSgeBS9Akwanf3_0r0cgEleBcIOjg0,46
-judgeval-0.14.0.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
-judgeval-0.14.0.dist-info/RECORD,,
+judgeval-0.15.0.dist-info/METADATA,sha256=MT857VBF8qoWXiCu_NyK_JCBcrddN1kCSWxDd58D3g0,8564
+judgeval-0.15.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+judgeval-0.15.0.dist-info/entry_points.txt,sha256=-eoeD-oDLn4A7MSgeBS9Akwanf3_0r0cgEleBcIOjg0,46
+judgeval-0.15.0.dist-info/licenses/LICENSE.md,sha256=tKmCg7k5QOmxPK19XMfzim04QiQJPmgIm0pAn55IJwk,11352
+judgeval-0.15.0.dist-info/RECORD,,