arize-phoenix 3.16.1__py3-none-any.whl → 7.7.0__py3-none-any.whl

phoenix/session/data_extractor.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from datetime import datetime
-from typing import List, Optional, Union, cast
+from typing import Optional, Union, cast
 
 import pandas as pd
 
@@ -8,6 +8,9 @@ from phoenix.trace import Evaluations
 from phoenix.trace.dsl import SpanQuery
 from phoenix.trace.trace_dataset import TraceDataset
 
+DEFAULT_SPAN_LIMIT = 1000
+DEFAULT_TIMEOUT_IN_SECONDS = 5
+
 
 class TraceDataExtractor(ABC):
     """
@@ -20,28 +23,34 @@ class TraceDataExtractor(ABC):
         self,
         *queries: SpanQuery,
         start_time: Optional[datetime] = None,
-        stop_time: Optional[datetime] = None,
+        end_time: Optional[datetime] = None,
+        limit: Optional[int] = DEFAULT_SPAN_LIMIT,
         root_spans_only: Optional[bool] = None,
         project_name: Optional[str] = None,
-    ) -> Optional[Union[pd.DataFrame, List[pd.DataFrame]]]: ...
+        timeout: Optional[int] = DEFAULT_TIMEOUT_IN_SECONDS,
+    ) -> Optional[Union[pd.DataFrame, list[pd.DataFrame]]]: ...
 
     def get_spans_dataframe(
         self,
         filter_condition: Optional[str] = None,
         *,
         start_time: Optional[datetime] = None,
-        stop_time: Optional[datetime] = None,
+        end_time: Optional[datetime] = None,
+        limit: Optional[int] = DEFAULT_SPAN_LIMIT,
         root_spans_only: Optional[bool] = None,
         project_name: Optional[str] = None,
+        timeout: Optional[int] = DEFAULT_TIMEOUT_IN_SECONDS,
     ) -> Optional[pd.DataFrame]:
         return cast(
             Optional[pd.DataFrame],
             self.query_spans(
                 SpanQuery().where(filter_condition or ""),
                 start_time=start_time,
-                stop_time=stop_time,
+                end_time=end_time,
+                limit=limit,
                 root_spans_only=root_spans_only,
                 project_name=project_name,
+                timeout=timeout,
             ),
         )
 
@@ -49,13 +58,28 @@ class TraceDataExtractor(ABC):
     def get_evaluations(
         self,
         project_name: Optional[str] = None,
-    ) -> List[Evaluations]: ...
+    ) -> list[Evaluations]: ...
 
     def get_trace_dataset(
         self,
         project_name: Optional[str] = None,
+        *,
+        start_time: Optional[datetime] = None,
+        end_time: Optional[datetime] = None,
+        limit: Optional[int] = DEFAULT_SPAN_LIMIT,
+        root_spans_only: Optional[bool] = None,
+        timeout: Optional[int] = DEFAULT_TIMEOUT_IN_SECONDS,
     ) -> Optional[TraceDataset]:
-        if (dataframe := self.get_spans_dataframe(project_name=project_name)) is None:
+        if (
+            dataframe := self.get_spans_dataframe(
+                project_name=project_name,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                root_spans_only=root_spans_only,
+                timeout=timeout,
+            )
+        ) is None:
             return None
         evaluations = self.get_evaluations(project_name=project_name)
         return TraceDataset(dataframe=dataframe, evaluations=evaluations)

phoenix/session/evaluation.py

@@ -1,5 +1,5 @@
 """
-A set of **highly experimental** helper functions to
+A set of helper functions to
   - extract spans from Phoenix for evaluation
     - explode retrieved documents from (horizontal) lists to a (vertical) series
       indexed by `context.span_id` and `document_position`
@@ -13,11 +13,9 @@ from typing import (
     Iterator,
     Optional,
     Sequence,
-    Tuple,
     Union,
     cast,
 )
-from urllib.parse import urljoin
 
 import pandas as pd
 from google.protobuf.wrappers_pb2 import DoubleValue, StringValue
@@ -45,7 +43,7 @@ def encode_evaluations(evaluations: Evaluations) -> Iterator[pb.Evaluation]:
     for index, row in dataframe.iterrows():
         subject_id = _extract_subject_id_from_index(
             index_names,
-            cast(Union[str, Tuple[Any]], index),
+            cast(Union[str, tuple[Any]], index),
         )
         if (result := _extract_result(row)) is None:
             continue
@@ -73,7 +71,6 @@ def _extract_subject_id_from_index(
     value: Union[str, Sequence[Any]],
 ) -> pb.Evaluation.SubjectId:
     """
-    (**Highly Experimental**)
     Returns `SubjectId` given the format of `index_names`. Allowed formats are:
         - DocumentRetrievalId
             - index_names=["context.span_id", "document_position"]
@@ -148,8 +145,5 @@ def log_evaluations(
     if host == "0.0.0.0":
         host = "127.0.0.1"
     port = port or get_env_port()
-    endpoint = endpoint or urljoin(
-        get_env_collector_endpoint() or f"http://{host}:{port}",
-        "/v1/traces",
-    )
+    endpoint = endpoint or get_env_collector_endpoint() or f"http://{host}:{port}"
     Client(endpoint=endpoint).log_evaluations(*evals)