arize-phoenix 3.0.1__py3-none-any.whl → 3.0.2__py3-none-any.whl

{arize_phoenix-3.0.1.dist-info → arize_phoenix-3.0.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: arize-phoenix
-Version: 3.0.1
+Version: 3.0.2
 Summary: ML Observability in your notebook
 Project-URL: Documentation, https://docs.arize.com/phoenix/
 Project-URL: Issues, https://github.com/Arize-ai/phoenix/issues
@@ -50,7 +50,7 @@ Requires-Dist: hatch; extra == 'dev'
 Requires-Dist: jupyter; extra == 'dev'
 Requires-Dist: langchain>=0.0.334; extra == 'dev'
 Requires-Dist: litellm>=1.0.3; extra == 'dev'
-Requires-Dist: llama-index>=0.9.14; extra == 'dev'
+Requires-Dist: llama-index<0.10.0; extra == 'dev'
 Requires-Dist: nbqa; extra == 'dev'
 Requires-Dist: pandas-stubs<=2.0.2.230605; extra == 'dev'
 Requires-Dist: pre-commit; extra == 'dev'

{arize_phoenix-3.0.1.dist-info → arize_phoenix-3.0.2.dist-info}/RECORD

@@ -4,7 +4,7 @@ phoenix/datetime_utils.py,sha256=D955QLrkgrrSdUM6NyqbCeAu2SMsjhR5rHVQEsVUdng,277
 phoenix/exceptions.py,sha256=X5k9ipUDfwSCwZB-H5zFJLas86Gf9tAx0W4l5TZxp5k,108
 phoenix/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 phoenix/services.py,sha256=f6AeyKTuOpy9RCcTCjVH3gx5nYZhbTMFOuv1WSUOB5o,4992
-phoenix/version.py,sha256=E3P6AbnCwaWk6ndR1zNqlOTVebX9z5rv9voltc71dos,22
+phoenix/version.py,sha256=YKXrr5J7dV2n7ZhaRv0tigylRDtfOuvJC9Y4ouFZpzo,22
 phoenix/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 phoenix/core/embedding_dimension.py,sha256=zKGbcvwOXgLf-yrJBpQyKtd-LEOPRKHnUToyAU8Owis,87
 phoenix/core/evals.py,sha256=gJyqQzpud5YjtoY8h4pgXvHDsdubGfqmEewLuZHPPmQ,10224
@@ -23,7 +23,7 @@ phoenix/experimental/evals/__init__.py,sha256=q96YKLMt2GJD9zL8sjugvWx1INfw40Wa7E
 phoenix/experimental/evals/evaluators.py,sha256=r7fXrS-l4gn58SUhLAZSfY3P8lxysouSVJwHddrZJ_Q,15956
 phoenix/experimental/evals/retrievals.py,sha256=o3fqrsYbYZjyGj_jWkN_9VQVyXjLkDKDw5Ws7l8bwdI,3828
 phoenix/experimental/evals/functions/__init__.py,sha256=NNd0-_cmIopdV7vm3rspjfgM726qoQJ4DPq_vqbnaxQ,180
-phoenix/experimental/evals/functions/classify.py,sha256=6yCajPT9i98b4_2qYn9ZxGhdI3CLhfUSrEyUUcqQqmQ,19517
+phoenix/experimental/evals/functions/classify.py,sha256=wqsLtDVPckt4OYuyr1YzaIokqnhzfYf_bMhR5ythWww,18961
 phoenix/experimental/evals/functions/executor.py,sha256=bM7PI2rcPukQQzZ2rWqN_-Kfo_a935YJj0bh1Red8Ps,13406
 phoenix/experimental/evals/functions/generate.py,sha256=8LnnPAjBM9yxitdkaGZ67OabuDTOWBF3fvinJ_uCFRg,5584
 phoenix/experimental/evals/functions/processing.py,sha256=F4xtLsulLV4a8CkuLldRddsCim75dSTIShEJUYN6I6w,1823
@@ -169,8 +169,8 @@ phoenix/trace/v1/evaluation_pb2.pyi,sha256=cCbbx06gwQmaH14s3J1X25TtaARh-k1abbxQd
 phoenix/utilities/__init__.py,sha256=3TVirVnjIGyaCFuJCqeZO4tjlzQ_chZgYM0itIwsEpE,656
 phoenix/utilities/error_handling.py,sha256=7b5rpGFj9EWZ8yrZK1IHvxB89suWk3lggDayUQcvZds,1946
 phoenix/utilities/logging.py,sha256=lDXd6EGaamBNcQxL4vP1au9-i_SXe0OraUDiJOcszSw,222
-arize_phoenix-3.0.1.dist-info/METADATA,sha256=MIwob2psMophui1KBYcjRPTmKinVvD9YIY0aDqRE5V0,28556
-arize_phoenix-3.0.1.dist-info/WHEEL,sha256=TJPnKdtrSue7xZ_AVGkp9YXcvDrobsjBds1du3Nx6dc,87
-arize_phoenix-3.0.1.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
-arize_phoenix-3.0.1.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
-arize_phoenix-3.0.1.dist-info/RECORD,,
+arize_phoenix-3.0.2.dist-info/METADATA,sha256=80fEGOl8VUcS4B1STEVmDITkrkYytJtE6f9d7VmkyhI,28555
+arize_phoenix-3.0.2.dist-info/WHEEL,sha256=TJPnKdtrSue7xZ_AVGkp9YXcvDrobsjBds1du3Nx6dc,87
+arize_phoenix-3.0.2.dist-info/licenses/IP_NOTICE,sha256=JBqyyCYYxGDfzQ0TtsQgjts41IJoa-hiwDrBjCb9gHM,469
+arize_phoenix-3.0.2.dist-info/licenses/LICENSE,sha256=HFkW9REuMOkvKRACuwLPT0hRydHb3zNg-fdFt94td18,3794
+arize_phoenix-3.0.2.dist-info/RECORD,,

phoenix/experimental/evals/functions/classify.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import logging
 import warnings
 from collections import defaultdict
+from itertools import product
 from typing import (
     Any,
     DefaultDict,
@@ -54,8 +55,7 @@ Label: TypeAlias = str
 Score: TypeAlias = Optional[float]
 Explanation: TypeAlias = Optional[str]
 Record: TypeAlias = Mapping[str, Any]
-EvaluatorIndex: TypeAlias = int
-RowIndex: TypeAlias = Any
+Index: TypeAlias = int
 
 # snapped_response, explanation, response
 ParsedLLMResponse: TypeAlias = Tuple[Optional[str], Optional[str], str]
@@ -343,8 +343,6 @@ def _get_contents_from_openinference_documents(documents: Iterable[Any]) -> List
 
 
 class RunEvalsPayload(NamedTuple):
-    evaluator_index: EvaluatorIndex
-    row_index: RowIndex
     evaluator: LLMEvaluator
     record: Record
 
@@ -404,23 +402,21 @@ def run_evals(
 
     async def _arun_eval(
         payload: RunEvalsPayload,
-    ) -> Tuple[EvaluatorIndex, RowIndex, Label, Score, Explanation]:
-        label, score, explanation = await payload.evaluator.aevaluate(
+    ) -> Tuple[Label, Score, Explanation]:
+        return await payload.evaluator.aevaluate(
             payload.record,
             provide_explanation=provide_explanation,
             use_function_calling_if_available=use_function_calling_if_available,
         )
-        return payload.evaluator_index, payload.row_index, label, score, explanation
 
     def _run_eval(
         payload: RunEvalsPayload,
-    ) -> Tuple[EvaluatorIndex, RowIndex, Label, Score, Explanation]:
-        label, score, explanation = payload.evaluator.evaluate(
+    ) -> Tuple[Label, Score, Explanation]:
+        return payload.evaluator.evaluate(
             payload.record,
             provide_explanation=provide_explanation,
             use_function_calling_if_available=use_function_calling_if_available,
         )
-        return payload.evaluator_index, payload.row_index, label, score, explanation
 
     executor = get_executor_on_sync_context(
         _run_eval,
@@ -428,24 +424,20 @@ def run_evals(
         concurrency=concurrency,
         tqdm_bar_format=get_tqdm_progress_bar_formatter("run_evals"),
         exit_on_error=True,
-        fallback_return_value=(None, None),
+        fallback_return_value=(None, None, None),
     )
+
+    total_records = len(dataframe)
     payloads = [
-        RunEvalsPayload(
-            evaluator_index=evaluator_index,
-            row_index=row_index,
-            evaluator=evaluator,
-            record=row.to_dict(),
-        )
-        # use the position of the row rather than the dataframe index, which is used
-        # to ensure the output dataframe has the same row order as the input dataframe
-        for row_index, (_, row) in enumerate(dataframe.iterrows())
-        for evaluator_index, evaluator in enumerate(evaluators)
+        RunEvalsPayload(evaluator=evaluator, record=row)
+        for evaluator, (_, row) in product(evaluators, dataframe.iterrows())
     ]
-    eval_results: List[DefaultDict[RowIndex, Dict[ColumnName, Union[Label, Explanation]]]] = [
+    eval_results: List[DefaultDict[Index, Dict[ColumnName, Union[Label, Explanation]]]] = [
         defaultdict(dict) for _ in range(len(evaluators))
     ]
-    for evaluator_index, row_index, label, score, explanation in executor.run(payloads):
+    for index, (label, score, explanation) in enumerate(executor.run(payloads)):
+        evaluator_index = index // total_records
+        row_index = index % total_records
         eval_results[evaluator_index][row_index]["label"] = label
         eval_results[evaluator_index][row_index]["score"] = score
         if provide_explanation:

phoenix/version.py

@@ -1 +1 @@
-__version__ = "3.0.1"
+__version__ = "3.0.2"