arize 8.0.0a13__py3-none-any.whl → 8.0.0a14__py3-none-any.whl

arize/{utils → models}/proto.py

@@ -1,21 +1,17 @@
 # type: ignore[pb2]
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Tuple
+from typing import Tuple
 
-from google.protobuf import json_format, message
 from google.protobuf.timestamp_pb2 import Timestamp
 from google.protobuf.wrappers_pb2 import DoubleValue, StringValue
 
-from arize._generated.protocol.flight import export_pb2 as flight_exp_pb2
 from arize._generated.protocol.rec import public_pb2 as pb2
 from arize.exceptions.parameters import InvalidValueType
 from arize.types import (
     CATEGORICAL_MODEL_TYPES,
     NUMERIC_MODEL_TYPES,
-    CorpusSchema,
     Embedding,
-    Environments,
     InstanceSegmentationActualLabel,
     InstanceSegmentationPredictionLabel,
     ModelTypes,
@@ -25,374 +21,10 @@ from arize.types import (
     RankingActualLabel,
     RankingPredictionLabel,
     SemanticSegmentationLabel,
-    SimilaritySearchParams,
     convert_element,
     is_list_of,
 )
 
-if TYPE_CHECKING:
-    from arize.types import (
-        EmbeddingColumnNames,
-        Schema,
-    )
-
-
-def get_pb_schema(
-    schema: Schema,
-    model_id: str,
-    model_version: str | None,
-    model_type: ModelTypes,
-    environment: Environments,
-    batch_id: str,
-):
-    s = pb2.Schema()
-    s.constants.model_id = model_id
-
-    if model_version is not None:
-        s.constants.model_version = model_version
-
-    if environment == Environments.PRODUCTION:
-        s.constants.environment = pb2.Schema.Environment.PRODUCTION
-    elif environment == Environments.VALIDATION:
-        s.constants.environment = pb2.Schema.Environment.VALIDATION
-    elif environment == Environments.TRAINING:
-        s.constants.environment = pb2.Schema.Environment.TRAINING
-    else:
-        raise ValueError(f"unexpected environment: {environment}")
-
-    # Map user-friendly external model types -> internal model types when sending to Arize
-    if model_type in NUMERIC_MODEL_TYPES:
-        s.constants.model_type = pb2.Schema.ModelType.NUMERIC
-    elif model_type in CATEGORICAL_MODEL_TYPES:
-        s.constants.model_type = pb2.Schema.ModelType.SCORE_CATEGORICAL
-    elif model_type == ModelTypes.RANKING:
-        s.constants.model_type = pb2.Schema.ModelType.RANKING
-    elif model_type == ModelTypes.OBJECT_DETECTION:
-        s.constants.model_type = pb2.Schema.ModelType.OBJECT_DETECTION
-    elif model_type == ModelTypes.GENERATIVE_LLM:
-        s.constants.model_type = pb2.Schema.ModelType.GENERATIVE_LLM
-    elif model_type == ModelTypes.MULTI_CLASS:
-        s.constants.model_type = pb2.Schema.ModelType.MULTI_CLASS
-
-    if batch_id is not None:
-        s.constants.batch_id = batch_id
-
-    if schema.prediction_id_column_name is not None:
-        s.arrow_schema.prediction_id_column_name = (
-            schema.prediction_id_column_name
-        )
-
-    if schema.timestamp_column_name is not None:
-        s.arrow_schema.timestamp_column_name = schema.timestamp_column_name
-
-    if schema.prediction_label_column_name is not None:
-        s.arrow_schema.prediction_label_column_name = (
-            schema.prediction_label_column_name
-        )
-
-    if model_type == ModelTypes.OBJECT_DETECTION:
-        if schema.object_detection_prediction_column_names is not None:
-            s.arrow_schema.prediction_object_detection_label_column_names.bboxes_coordinates_column_name = (
-                schema.object_detection_prediction_column_names.bounding_boxes_coordinates_column_name  # noqa: E501
-            )
-            s.arrow_schema.prediction_object_detection_label_column_names.bboxes_categories_column_name = (
-                schema.object_detection_prediction_column_names.categories_column_name  # noqa: E501
-            )
-            if (
-                schema.object_detection_prediction_column_names.scores_column_name
-                is not None
-            ):
-                s.arrow_schema.prediction_object_detection_label_column_names.bboxes_scores_column_name = (
-                    schema.object_detection_prediction_column_names.scores_column_name  # noqa: E501
-                )
-
-        if schema.semantic_segmentation_prediction_column_names is not None:
-            s.arrow_schema.prediction_semantic_segmentation_label_column_names.polygons_coordinates_column_name = (  # noqa: E501
-                schema.semantic_segmentation_prediction_column_names.polygon_coordinates_column_name
-            )
-            s.arrow_schema.prediction_semantic_segmentation_label_column_names.polygons_categories_column_name = (  # noqa: E501
-                schema.semantic_segmentation_prediction_column_names.categories_column_name
-            )
-
-        if schema.instance_segmentation_prediction_column_names is not None:
-            s.arrow_schema.prediction_instance_segmentation_label_column_names.polygons_coordinates_column_name = (  # noqa: E501
-                schema.instance_segmentation_prediction_column_names.polygon_coordinates_column_name
-            )
-            s.arrow_schema.prediction_instance_segmentation_label_column_names.polygons_categories_column_name = (  # noqa: E501
-                schema.instance_segmentation_prediction_column_names.categories_column_name
-            )
-            if (
-                schema.instance_segmentation_prediction_column_names.scores_column_name
-                is not None
-            ):
-                s.arrow_schema.prediction_instance_segmentation_label_column_names.polygons_scores_column_name = (  # noqa: E501
-                    schema.instance_segmentation_prediction_column_names.scores_column_name
-                )
-            if (
-                schema.instance_segmentation_prediction_column_names.bounding_boxes_coordinates_column_name
-                is not None
-            ):
-                s.arrow_schema.prediction_instance_segmentation_label_column_names.bboxes_coordinates_column_name = (  # noqa: E501
-                    schema.instance_segmentation_prediction_column_names.bounding_boxes_coordinates_column_name
-                )
-
-    if schema.prediction_score_column_name is not None:
-        if model_type in NUMERIC_MODEL_TYPES:
-            # allow numeric prediction to be sent in as either prediction_label (legacy) or
-            # prediction_score.
-            s.arrow_schema.prediction_label_column_name = (
-                schema.prediction_score_column_name
-            )
-        else:
-            s.arrow_schema.prediction_score_column_name = (
-                schema.prediction_score_column_name
-            )
-
-    if schema.feature_column_names is not None:
-        s.arrow_schema.feature_column_names.extend(schema.feature_column_names)
-
-    if schema.embedding_feature_column_names is not None:
-        for (
-            emb_name,
-            emb_col_names,
-        ) in schema.embedding_feature_column_names.items():
-            # emb_name is how it will show in the UI
-            s.arrow_schema.embedding_feature_column_names_map[
-                emb_name
-            ].vector_column_name = emb_col_names.vector_column_name
-            if emb_col_names.data_column_name:
-                s.arrow_schema.embedding_feature_column_names_map[
-                    emb_name
-                ].data_column_name = emb_col_names.data_column_name
-            if emb_col_names.link_to_data_column_name:
-                s.arrow_schema.embedding_feature_column_names_map[
-                    emb_name
-                ].link_to_data_column_name = (
-                    emb_col_names.link_to_data_column_name
-                )
-
-    if schema.prompt_column_names is not None:
-        if isinstance(schema.prompt_column_names, str):
-            s.arrow_schema.embedding_feature_column_names_map[
-                "prompt"
-            ].data_column_name = schema.prompt_column_names
-        elif isinstance(schema.prompt_column_names, EmbeddingColumnNames):
-            col_names = schema.prompt_column_names
-            s.arrow_schema.embedding_feature_column_names_map[
-                "prompt"
-            ].vector_column_name = col_names.vector_column_name
-            if col_names.data_column_name:
-                s.arrow_schema.embedding_feature_column_names_map[
-                    "prompt"
-                ].data_column_name = col_names.data_column_name
-    if schema.response_column_names is not None:
-        if isinstance(schema.response_column_names, str):
-            s.arrow_schema.embedding_feature_column_names_map[
-                "response"
-            ].data_column_name = schema.response_column_names
-        elif isinstance(schema.response_column_names, EmbeddingColumnNames):
-            col_names = schema.response_column_names
-            s.arrow_schema.embedding_feature_column_names_map[
-                "response"
-            ].vector_column_name = col_names.vector_column_name
-            if col_names.data_column_name:
-                s.arrow_schema.embedding_feature_column_names_map[
-                    "response"
-                ].data_column_name = col_names.data_column_name
-
-    if schema.tag_column_names is not None:
-        s.arrow_schema.tag_column_names.extend(schema.tag_column_names)
-
-    if (
-        model_type == ModelTypes.RANKING
-        and schema.relevance_labels_column_name is not None
-    ):
-        s.arrow_schema.actual_label_column_name = (
-            schema.relevance_labels_column_name
-        )
-    elif (
-        model_type == ModelTypes.RANKING
-        and schema.attributions_column_name is not None
-    ):
-        s.arrow_schema.actual_label_column_name = (
-            schema.attributions_column_name
-        )
-    elif schema.actual_label_column_name is not None:
-        s.arrow_schema.actual_label_column_name = (
-            schema.actual_label_column_name
-        )
-
-    if (
-        model_type == ModelTypes.RANKING
-        and schema.relevance_score_column_name is not None
-    ):
-        s.arrow_schema.actual_score_column_name = (
-            schema.relevance_score_column_name
-        )
-    elif schema.actual_score_column_name is not None:
-        if model_type in NUMERIC_MODEL_TYPES:
-            # allow numeric prediction to be sent in as either prediction_label (legacy) or
-            # prediction_score.
-            s.arrow_schema.actual_label_column_name = (
-                schema.actual_score_column_name
-            )
-        else:
-            s.arrow_schema.actual_score_column_name = (
-                schema.actual_score_column_name
-            )
-
-    if schema.shap_values_column_names is not None:
-        s.arrow_schema.shap_values_column_names.update(
-            schema.shap_values_column_names
-        )
-
-    if schema.prediction_group_id_column_name is not None:
-        s.arrow_schema.prediction_group_id_column_name = (
-            schema.prediction_group_id_column_name
-        )
-
-    if schema.rank_column_name is not None:
-        s.arrow_schema.rank_column_name = schema.rank_column_name
-
-    if model_type == ModelTypes.OBJECT_DETECTION:
-        if schema.object_detection_actual_column_names is not None:
-            s.arrow_schema.actual_object_detection_label_column_names.bboxes_coordinates_column_name = (  # noqa: E501
-                schema.object_detection_actual_column_names.bounding_boxes_coordinates_column_name
-            )
-            s.arrow_schema.actual_object_detection_label_column_names.bboxes_categories_column_name = (  # noqa: E501
-                schema.object_detection_actual_column_names.categories_column_name
-            )
-            if (
-                schema.object_detection_actual_column_names.scores_column_name
-                is not None
-            ):
-                s.arrow_schema.actual_object_detection_label_column_names.bboxes_scores_column_name = (  # noqa: E501
-                    schema.object_detection_actual_column_names.scores_column_name
-                )
-
-        if schema.semantic_segmentation_actual_column_names is not None:
-            s.arrow_schema.actual_semantic_segmentation_label_column_names.polygons_coordinates_column_name = (  # noqa: E501
-                schema.semantic_segmentation_actual_column_names.polygon_coordinates_column_name
-            )
-            s.arrow_schema.actual_semantic_segmentation_label_column_names.polygons_categories_column_name = (  # noqa: E501
-                schema.semantic_segmentation_actual_column_names.categories_column_name
-            )
-
-        if schema.instance_segmentation_actual_column_names is not None:
-            s.arrow_schema.actual_instance_segmentation_label_column_names.polygons_coordinates_column_name = (  # noqa: E501
-                schema.instance_segmentation_actual_column_names.polygon_coordinates_column_name
-            )
-            s.arrow_schema.actual_instance_segmentation_label_column_names.polygons_categories_column_name = (  # noqa: E501
-                schema.instance_segmentation_actual_column_names.categories_column_name
-            )
-            if (
-                schema.instance_segmentation_actual_column_names.bounding_boxes_coordinates_column_name
-                is not None
-            ):
-                s.arrow_schema.actual_instance_segmentation_label_column_names.bboxes_coordinates_column_name = (  # noqa: E501
-                    schema.instance_segmentation_actual_column_names.bounding_boxes_coordinates_column_name
-                )
-
-    if model_type == ModelTypes.GENERATIVE_LLM:
-        if schema.prompt_template_column_names is not None:
-            s.arrow_schema.prompt_template_column_names.template_column_name = (
-                schema.prompt_template_column_names.template_column_name
-            )
-            s.arrow_schema.prompt_template_column_names.template_version_column_name = (  # noqa: E501
-                schema.prompt_template_column_names.template_version_column_name
-            )
-        if schema.llm_config_column_names is not None:
-            s.arrow_schema.llm_config_column_names.model_column_name = (
-                schema.llm_config_column_names.model_column_name
-            )
-            s.arrow_schema.llm_config_column_names.params_map_column_name = (
-                schema.llm_config_column_names.params_column_name
-            )
-        if schema.retrieved_document_ids_column_name is not None:
-            s.arrow_schema.retrieved_document_ids_column_name = (
-                schema.retrieved_document_ids_column_name
-            )
-    if model_type == ModelTypes.MULTI_CLASS:
-        if schema.prediction_score_column_name is not None:
-            s.arrow_schema.prediction_score_column_name = (
-                schema.prediction_score_column_name
-            )
-        if schema.multi_class_threshold_scores_column_name is not None:
-            s.arrow_schema.multi_class_threshold_scores_column_name = (
-                schema.multi_class_threshold_scores_column_name
-            )
-        if schema.actual_score_column_name is not None:
-            s.arrow_schema.actual_score_column_name = (
-                schema.actual_score_column_name
-            )
-    return s
-
-
-def get_pb_schema_corpus(
-    schema: CorpusSchema,
-    model_id: str,
-) -> pb2.Schema:
-    s = pb2.Schema()
-    s.constants.model_id = model_id
-    s.constants.environment = pb2.Schema.Environment.CORPUS
-    s.constants.model_type = pb2.Schema.ModelType.GENERATIVE_LLM
-    if schema.document_id_column_name is not None:
-        s.arrow_schema.document_column_names.id_column_name = (
-            schema.document_id_column_name
-        )
-    if schema.document_version_column_name is not None:
-        s.arrow_schema.document_column_names.version_column_name = (
-            schema.document_version_column_name
-        )
-    if schema.document_text_embedding_column_names is not None:
-        s.arrow_schema.document_column_names.text_column_name.vector_column_name = schema.document_text_embedding_column_names.vector_column_name  # noqa: E501
-        s.arrow_schema.document_column_names.text_column_name.data_column_name = schema.document_text_embedding_column_names.data_column_name  # noqa: E501
-        if (
-            schema.document_text_embedding_column_names.link_to_data_column_name
-            is not None
-        ):
-            s.arrow_schema.document_column_names.text_column_name.link_to_data_column_name = schema.document_text_embedding_column_names.link_to_data_column_name  # noqa: E501
-    return s
-
-
-def get_pb_schema_tracing(
-    project_name: str,
-) -> pb2.Schema:
-    s = pb2.Schema()
-    s.constants.model_id = project_name
-    s.constants.environment = pb2.Schema.Environment.TRACING
-    s.constants.model_type = pb2.Schema.ModelType.GENERATIVE_LLM
-    s.arize_spans.SetInParent()
-    return s
-
-
-def message_to_dict(
-    msg: message.Message,
-    preserve_names: bool = True,
-    use_int_enums: bool = False,
-):
-    return json_format.MessageToDict(
-        msg,
-        preserving_proto_field_name=preserve_names,
-        use_integers_for_enums=use_int_enums,
-    )
-
-
-def get_pb_similarity_search_params(
-    similarity_params: SimilaritySearchParams,
-) -> flight_exp_pb2.SimilaritySearchParams:
-    proto_params = flight_exp_pb2.SimilaritySearchParams()
-    proto_params.search_column_name = similarity_params.search_column_name
-    proto_params.threshold = similarity_params.threshold
-    for ref in similarity_params.references:
-        new_ref = proto_params.references.add()
-        new_ref.prediction_id = ref.prediction_id
-        new_ref.reference_column_name = ref.reference_column_name
-        if ref.prediction_timestamp:
-            new_ref.prediction_timestamp.FromDatetime(ref.prediction_timestamp)
-
-    return proto_params
-
 
 def get_pb_dictionary(d):
     if d is None:

arize/spans/client.py

@@ -11,6 +11,7 @@ from typing import TYPE_CHECKING, Any, Dict, List
 import numpy as np
 import pandas as pd
 import pyarrow as pa
+from google.protobuf import json_format, message
 
 from arize._exporter.client import ArizeExportClient
 from arize._flight.client import ArizeFlightClient, WriteSpanResponse
@@ -19,6 +20,7 @@ from arize._generated.protocol.flight.ingest_pb2 import (
     WriteSpanAnnotationResponse,
     WriteSpanEvaluationResponse,
 )
+from arize._generated.protocol.rec import public_pb2 as pb2
 from arize.constants.spans import DEFAULT_DATETIME_FMT
 from arize.exceptions.base import (
     INVALID_ARROW_CONVERSION_MSG,
@@ -35,7 +37,6 @@ from arize.utils.dataframe import (
     remove_extraneous_columns,
     reset_dataframe_index,
 )
-from arize.utils.proto import get_pb_schema_tracing, message_to_dict
 
 if TYPE_CHECKING:
     import requests
@@ -226,7 +227,7 @@ class SpansClient:
             log.error(f"Unexpected error creating Arrow table: {str(e)}")
             raise
 
-        proto_schema = get_pb_schema_tracing(project_name=project_name)
+        proto_schema = _get_pb_schema_tracing(project_name=project_name)
         # Create headers copy for the spans client
         # Safe to mutate, returns a deep copy
         headers = self._sdk_config.headers
@@ -363,7 +364,7 @@ class SpansClient:
             raise
 
         if force_http:
-            proto_schema = get_pb_schema_tracing(project_name=project_name)
+            proto_schema = _get_pb_schema_tracing(project_name=project_name)
             # Create headers copy for the spans client
             # Safe to mutate, returns a deep copy
             headers = self._sdk_config.headers
@@ -422,7 +423,7 @@ class SpansClient:
         )
 
         # Convert Protocol Buffer SpanError objects to dictionaries for easier access
-        return message_to_dict(response)
+        return _message_to_dict(response)
 
     def update_annotations(
         self,
@@ -636,7 +637,7 @@ class SpansClient:
         )
 
         # Convert Protocol Buffer SpanError objects to dictionaries for easier access
-        return message_to_dict(response)
+        return _message_to_dict(response)
 
     def update_metadata(
         self,
@@ -967,7 +968,7 @@ class SpansClient:
         )
 
         # Convert Protocol Buffer SpanError objects to dictionaries for easier access
-        return message_to_dict(response)
+        return _message_to_dict(response)
 
     def export_to_df(
         self,
@@ -1226,3 +1227,26 @@ def _log_flight_update_summary(
                 **err,
             },
         )
+
+
+def _get_pb_schema_tracing(
+    project_name: str,
+) -> pb2.Schema:
+    s = pb2.Schema()
+    s.constants.model_id = project_name
+    s.constants.environment = pb2.Schema.Environment.TRACING
+    s.constants.model_type = pb2.Schema.ModelType.GENERATIVE_LLM
+    s.arize_spans.SetInParent()
+    return s
+
+
+def _message_to_dict(
+    msg: message.Message,
+    preserve_names: bool = True,
+    use_int_enums: bool = False,
+):
+    return json_format.MessageToDict(
+        msg,
+        preserving_proto_field_name=preserve_names,
+        use_integers_for_enums=use_int_enums,
+    )

arize/utils/arrow.py

@@ -39,7 +39,7 @@ def post_arrow_table(
 
     logger.debug("Serializing schema")
     base64_schema = base64.b64encode(proto_schema.SerializeToString())
-    pa_schema = append_to_pyarrow_metadata(
+    pa_schema = _append_to_pyarrow_metadata(
         pa_table.schema, {"arize-schema": base64_schema}
     )
 
@@ -68,7 +68,7 @@ def post_arrow_table(
     try:
         # Write arrow file
         logger.debug(f"Writing table to temporary file: {outfile}")
-        write_arrow_file(outfile, pa_table, pa_schema)
+        _write_arrow_file(outfile, pa_table, pa_schema)
 
         # Send to Arize
         logger.debug(
@@ -104,7 +104,7 @@ def post_arrow_table(
                 )
 
 
-def append_to_pyarrow_metadata(
+def _append_to_pyarrow_metadata(
     pa_schema: pa.Schema, new_metadata: Dict[str, Any]
 ):
     # Ensure metadata is handled correctly, even if initially None.
@@ -125,7 +125,7 @@ def append_to_pyarrow_metadata(
     return pa_schema.with_metadata(updated_metadata)
 
 
-def write_arrow_file(
+def _write_arrow_file(
     path: str, pa_table: pa.Table, pa_schema: pa.Schema
 ) -> None:
     with pa.OSFile(path, mode="wb") as sink, pa.ipc.RecordBatchStreamWriter(

arize/version.py

@@ -1 +1 @@
-__version__ = "8.0.0a13"
+__version__ = "8.0.0a14"

{arize-8.0.0a13.dist-info → arize-8.0.0a14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arize
-Version: 8.0.0a13
+Version: 8.0.0a14
 Summary: A helper library to interact with Arize AI APIs
 Project-URL: Homepage, https://arize.com
 Project-URL: Documentation, https://docs.arize.com/arize
@@ -424,7 +424,7 @@ examples = [
 ]
 ```
 
-If the number of examples (rows in dataframe, items in list) is too large, the client SDK will try to send the data via Arrow Flight via gRPC for better performance. If you want to force the data transfer to HTTP you can use the `force_http` flag. The response is always a `Dataset` object.
+If the number of examples (rows in dataframe, items in list) is too large, the client SDK will try to send the data via Arrow Flight via gRPC for better performance. If you want to force the data transfer to HTTP you can use the `force_http` flag. The response is a `Dataset` object.
 
 ```python
 created_dataset = client.datasets.create(
@@ -434,11 +434,19 @@ created_dataset = client.datasets.create(
 )
 ```
 
+The `Dataset` object also counts with convenience method similar to `List***` objects:
+
+```python
+# Get the response as a dictionary
+dataset_dict = create_dataset.to_dict()
+# Get the response in JSON format
+dataset_dict = create_dataset.to_json()
+```
 
 
 ### Get Dataset by ID
 
-To get a dataset by its ID use `client.datasets.get()`, you can optionally also pass the version ID of a particular version of interest of the dataset.
+To get a dataset by its ID use `client.datasets.get()`, you can optionally also pass the version ID of a particular version of interest of the dataset. The returned type is `Dataset`.
 
 ```python
 dataset = client.datasets.get(

{arize-8.0.0a13.dist-info → arize-8.0.0a14.dist-info}/RECORD

@@ -4,9 +4,9 @@ arize/client.py,sha256=H1VdHwtruq9koc37LPP1eSZEax32iQR0porczhCOLYg,6070
 arize/config.py,sha256=_EucdoM6k-6DZSurwX_6_n7VIePcKcUccil-Iwk4JH0,6015
 arize/logging.py,sha256=OahBaJRG-z5DPqWrj2_rbe2n0r4fMGOrXpxN_4M_i_w,7244
 arize/types.py,sha256=z1yg5-brmTD4kVHDmmTVkYke53JpusXXeOOpdQw7rYg,69508
-arize/version.py,sha256=1g3Ne_YSIwt3dSGmtEtvWJDZ7TJpxNJ6t6cItY3e-YY,25
+arize/version.py,sha256=fUXlzvO9it_R2HsYwSkRT1nJGpumTpSybxg2EoP8byU,25
 arize/_exporter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize/_exporter/client.py,sha256=eAxJX1sUfdpLrtaQ0ynMTd5jI37JOp9fbl3NWp4WFEA,15216
+arize/_exporter/client.py,sha256=k3xS-2wx_UlB5toI5RKBoy1bi3ONIxh4KQy4A4a2Omc,15822
 arize/_exporter/validation.py,sha256=6ROu5p7uaolxQ93lO_Eiwv9NVw_uyi3E5T--C5Klo5Q,1021
 arize/_exporter/parsers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/_exporter/parsers/tracing_data_parser.py,sha256=zVS-w8t1HJkz-AIC_JCdjPJ7gJXgFpfELfqNM_vK42E,5395
@@ -56,7 +56,7 @@ arize/constants/ml.py,sha256=X_vtKpt1AdhLoT2DWEyKDSXAVEuzjwGFacIbgUOpB3M,2358
 arize/constants/model_mapping.json,sha256=OPE54rBATzmwRhx0tycsxnGae1jBhtqEmQqQvzleTSc,5725
 arize/constants/spans.py,sha256=EfMgbEIK_2EUcvUY5BGnNAbS7bupBKePlI3j2L5T5CE,2532
 arize/datasets/__init__.py,sha256=GVNsjaqzQt4x-nILE41BvWyZqfYAxPQB0oHZgIDW7ws,2289
-arize/datasets/client.py,sha256=HBzxSQ_SmCtda3nkEnunztiuxmAQOqtR4vNn5BaqXEs,5327
+arize/datasets/client.py,sha256=ykGa60Ms6mXGCegW4Oq5plEJgX_9rJjd6Nu8nEDBnwU,5065
 arize/embeddings/__init__.py,sha256=6_C8908W_qDixkoBJl1wapgmQCzI8TPLH207kzbYsFA,156
 arize/embeddings/auto_generator.py,sha256=ukZUJWRkiG9HFgSHXhr44rt2tdVHn1phb7_nOxYXWEg,4111
 arize/embeddings/base_generators.py,sha256=HybEUAzeESswEDmkmvPayzFab1y8deg5X20HSphGp8Q,8855
@@ -78,7 +78,9 @@ arize/experiments/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 arize/experiments/client.py,sha256=2fDq0fr_h6Knn_9zgDAlAhSUCKUrKozGLOQRTInCr4c,344
 arize/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/models/bounded_executor.py,sha256=o-PJsDAXQdiJ9dc-jzGCHMhT0-QBY9bvl4Ckn1017Eo,1131
-arize/models/client.py,sha256=ZHxGYmCKP5ZX001qVNQc96QoclP4jvYVkLW11Xfqo2M,31199
+arize/models/casting.py,sha256=YVnN0UiddLUVJDnOiXe2YyAzC1THBKbnm_V0qKYORJo,12480
+arize/models/client.py,sha256=xnOC6ViF2NJjgXc0AL5w0wy8HlNevEGVZO6SAk0vVKs,46500
+arize/models/proto.py,sha256=9YkXn5Q6DuQP641fvBu-dlTx1ULQWMtH2wV7gCFDta8,17412
 arize/models/stream_validation.py,sha256=PtmqWgRdCxVtTNkHHEHIM1S6ECbYLA1vuQQFBw_t3Lw,7118
 arize/models/batch_validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/models/batch_validation/errors.py,sha256=__I8l25zf4kGv6qgiwEm9LzGNgqmMSM8Fb88pBtyMxE,39990
@@ -86,7 +88,7 @@ arize/models/batch_validation/validator.py,sha256=acnGcMt-pETmPJUfYj5tIzIBvmBhWo
 arize/models/surrogate_explainer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/models/surrogate_explainer/mimic.py,sha256=MsMfhU9IhQJWm0kK6jpFkcTW6kw5IGJE3Kv94oOzMo0,5517
 arize/spans/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize/spans/client.py,sha256=5yODUaSqxH-dLAenjRZBKbpsK7XgewZKwJpXzHWPNf0,47248
+arize/spans/client.py,sha256=xiXKnFtzzulngNVscK4TIwj_JMAckPPzA-yLjrVHR3k,47869
 arize/spans/columns.py,sha256=BbB11jF4YHYfjrKbSd1r3K2F0AGA8KULTj1W3e2rwhM,12912
 arize/spans/conversion.py,sha256=U9elK_znCADOcg5pOmq7srrdZwDSQRFApxN7jFZZ0X4,4038
 arize/spans/validation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -112,13 +114,11 @@ arize/spans/validation/spans/dataframe_form_validation.py,sha256=NqyaOYzZL5_XIHR
 arize/spans/validation/spans/spans_validation.py,sha256=p6IjbQMtOhotGBfw3axj7yMWxb2pC47EAzJSB887nzs,2451
 arize/spans/validation/spans/value_validation.py,sha256=H3qV96w6JQNCed_MxhWDas9Jf6vUj6RFabShcwf4jr4,19102
 arize/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize/utils/arrow.py,sha256=4In1gQc0i4Rb8zuwI0w-Hv-10wiItu5opqqGrJ8tSzo,5277
-arize/utils/casting.py,sha256=KUrPUQN6qJEVe39nxbr0T-0GjAJLHjf4xWuzV71QezI,12468
+arize/utils/arrow.py,sha256=C_UDeTW3ugB3rR--1o0dljEfxT727nMvqZV-c9WJRc8,5281
 arize/utils/dataframe.py,sha256=I0FloPgNiqlKga32tMOvTE70598QA8Hhrgf-6zjYMAM,1120
-arize/utils/proto.py,sha256=7PwggGH7iz1Ldwv0BCIxu9-WBeojNXUcT2pDU502Mto,34175
 arize/utils/online_tasks/__init__.py,sha256=nDuTLUTYnZaWgyJoYR1P7O8ZKA-Nba7X6tJ9OislbWM,144
 arize/utils/online_tasks/dataframe_preprocessor.py,sha256=YyeeeFu_FwCYImbYvBZvQIH_5TK2lHru8KSfqV893ps,8884
-arize-8.0.0a13.dist-info/METADATA,sha256=rtL4iOu2_1BXcOEVhfvzJ8R0l3Ff3QWGbVRaNnbCny8,18881
-arize-8.0.0a13.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-arize-8.0.0a13.dist-info/licenses/LICENSE.md,sha256=8vLN8Gms62NCBorxIv9MUvuK7myueb6_-dhXHPmm4H0,1479
-arize-8.0.0a13.dist-info/RECORD,,
+arize-8.0.0a14.dist-info/METADATA,sha256=uQfN_5isd7SmAPZIwvDlcEniLQvJQFCoHcLouh4Ih1o,19157
+arize-8.0.0a14.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+arize-8.0.0a14.dist-info/licenses/LICENSE.md,sha256=8vLN8Gms62NCBorxIv9MUvuK7myueb6_-dhXHPmm4H0,1479
+arize-8.0.0a14.dist-info/RECORD,,