arize 8.0.0a12__py3-none-any.whl → 8.0.0a13__py3-none-any.whl

arize/datasets/client.py

@@ -1,4 +1,18 @@
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List
+
+import pandas as pd
+import pyarrow as pa
+
+from arize._flight.client import ArizeFlightClient
 from arize.config import SDKConfiguration
+from arize.exceptions.base import INVALID_ARROW_CONVERSION_MSG
+
+logger = logging.getLogger(__name__)
+
+REST_LIMIT_DATASET_EXAMPLES = 3
 
 
 class DatasetsClient:
@@ -14,6 +28,110 @@ class DatasetsClient:
         # Forward methods to preserve exact runtime signatures/docs
         self.list = self._api.datasets_list
         self.get = self._api.datasets_get
-        self.create = self._api.datasets_create
         self.delete = self._api.datasets_delete
         self.list_examples = self._api.datasets_list_examples
+
+        # Custom methods
+        self.create = self._create_dataset
+
+    def _create_dataset(
+        self,
+        name: str,
+        space_id: str,
+        examples: List[Dict[str, Any]] | pd.DataFrame,
+    ):
+        if (
+            isinstance(examples, list)
+            and len(examples) > REST_LIMIT_DATASET_EXAMPLES
+        ):
+            logger.info(
+                f"Uploading {len(examples)} examples via REST may be slow. "
+                "Trying to convert to DataFrame for more efficient upload."
+            )
+            # If we have too many examples, try to convert to a dataframe
+            try:
+                data = pd.DataFrame(examples)
+            except Exception as e:
+                logger.warning(
+                    f"Could not convert examples to DataFrame: {e}. "
+                    "Falling back to list upload, which may be less performant."
+                )
+                # If we can’t convert to a dataframe, just use the list
+                data = examples
+        else:
+            # If we have a dataframe or a small list, just use it directly
+            data = examples
+
+        if isinstance(data, list):
+            # If the data is in list format, use the REST endpoint
+            from arize._generated import api_client as gen
+
+            body = gen.DatasetsCreateRequest(
+                name=name,
+                spaceId=space_id,
+                examples=data,
+            )
+            return self._api.datasets_create(datasets_create_request=body)
+        elif isinstance(data, pd.DataFrame):
+            # Convert datetime columns to int64 (ms since epoch)
+            # TODO(Kiko): Missing validation block
+            # data = _convert_datetime_columns_to_int(data)
+            # df = self._set_default_columns_for_dataset(data)
+            # if convert_dict_to_json:
+            #     df = _convert_default_columns_to_json_str(df)
+            # df = _convert_boolean_columns_to_str(df)
+            # validation_errors = Validator.validate(df)
+            # validation_errors.extend(
+            #     Validator.validate_max_chunk_size(max_chunk_size)
+            # )
+            # if validation_errors:
+            #     raise RuntimeError(
+            #         [e.error_message() for e in validation_errors]
+            #     )
+
+            # Convert to Arrow table
+            try:
+                logger.debug("Converting data to Arrow format")
+                pa_table = pa.Table.from_pandas(data)
+            except pa.ArrowInvalid as e:
+                logger.error(f"{INVALID_ARROW_CONVERSION_MSG}: {str(e)}")
+                raise pa.ArrowInvalid(
+                    f"Error converting to Arrow format: {str(e)}"
+                ) from e
+            except Exception as e:
+                logger.error(f"Unexpected error creating Arrow table: {str(e)}")
+                raise
+
+            response = None
+            with ArizeFlightClient(
+                api_key=self._sdk_config.api_key,
+                host=self._sdk_config.flight_server_host,
+                port=self._sdk_config.flight_server_port,
+                scheme=self._sdk_config.flight_scheme,
+                request_verify=self._sdk_config.request_verify,
+            ) as flight_client:
+                try:
+                    response = flight_client.create_dataset(
+                        space_id=space_id,
+                        dataset_name=name,
+                        pa_table=pa_table,
+                    )
+                except Exception as e:
+                    msg = f"Error during update request: {str(e)}"
+                    logger.error(msg)
+                    raise RuntimeError(msg) from e
+            if response is None:
+                # This should not happen with proper Flight client implementation,
+                # but we handle it defensively
+                msg = "No response received from flight server during update"
+                logger.error(msg)
+                raise RuntimeError(msg)
+            # The response from flightserver is the dataset ID. To return the dataset
+            # object we make a GET query
+            dataset = self.get(dataset_id=response)
+            return dataset
+
+        else:
+            raise TypeError(
+                "Examples must be a list of dicts or a pandas DataFrame"
+            )

arize/utils/proto.py

@@ -7,9 +7,7 @@ from google.protobuf import json_format, message
 from google.protobuf.timestamp_pb2 import Timestamp
 from google.protobuf.wrappers_pb2 import DoubleValue, StringValue
 
-from arize._flight.types import FlightRequestType
 from arize._generated.protocol.flight import export_pb2 as flight_exp_pb2
-from arize._generated.protocol.flight import ingest_pb2 as flight_ing_pb2
 from arize._generated.protocol.rec import public_pb2 as pb2
 from arize.exceptions.parameters import InvalidValueType
 from arize.types import (
@@ -368,40 +366,6 @@ def get_pb_schema_tracing(
     return s
 
 
-def get_pb_flight_doput_request(
-    space_id,
-    model_id: str,
-    request_type: FlightRequestType,
-) -> flight_ing_pb2.DoPutRequest:
-    """Return a DoPutRequest for the given request_type."""
-    common_args: dict[str, str] = {
-        "space_id": space_id,
-        "external_model_id": model_id,
-    }
-
-    match request_type:
-        case FlightRequestType.EVALUATION:
-            return flight_ing_pb2.DoPutRequest(
-                write_span_evaluation_request=flight_ing_pb2.WriteSpanEvaluationRequest(
-                    **common_args
-                )
-            )
-        case FlightRequestType.ANNOTATION:
-            return flight_ing_pb2.DoPutRequest(
-                write_span_annotation_request=flight_ing_pb2.WriteSpanAnnotationRequest(
-                    **common_args
-                )
-            )
-        case FlightRequestType.METADATA:
-            return flight_ing_pb2.DoPutRequest(
-                write_span_attributes_metadata_request=flight_ing_pb2.WriteSpanAttributesMetadataRequest(
-                    **common_args
-                )
-            )
-        case _:
-            raise ValueError(f"Unsupported request_type: {request_type}")
-
-
 def message_to_dict(
     msg: message.Message,
     preserve_names: bool = True,

arize/version.py

@@ -1 +1 @@
-__version__ = "8.0.0a12"
+__version__ = "8.0.0a13"

{arize-8.0.0a12.dist-info → arize-8.0.0a13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arize
-Version: 8.0.0a12
+Version: 8.0.0a13
 Summary: A helper library to interact with Arize AI APIs
 Project-URL: Homepage, https://arize.com
 Project-URL: Documentation, https://docs.arize.com/arize
@@ -34,6 +34,8 @@ Requires-Dist: pillow<11,>=8.4.0; extra == 'auto-embeddings'
 Requires-Dist: tokenizers<1,>=0.13; extra == 'auto-embeddings'
 Requires-Dist: torch<3,>=1.13; extra == 'auto-embeddings'
 Requires-Dist: transformers<5,>=4.25; extra == 'auto-embeddings'
+Provides-Extra: datasets-experiments
+Requires-Dist: pydantic; extra == 'datasets-experiments'
 Provides-Extra: dev
 Requires-Dist: pytest==8.4.2; extra == 'dev'
 Requires-Dist: ruff==0.13.2; extra == 'dev'
@@ -92,6 +94,11 @@ Description-Content-Type: text/markdown
     - [Log a batch of ML Data for a Object Detection use-case](#log-a-batch-of-ml-data-for-a-object-detection-use-case)
     - [Exporting ML Data](#exporting-ml-data)
   - [Generate embeddings for your data](#generate-embeddings-for-your-data)
+  - [Operations on Datasets](#operations-on-datasets)
+    - [List Datasets](#list-datasets)
+    - [Create a Dataset](#create-a-dataset)
+    - [Get Dataset by ID](#get-dataset-by-id)
+    - [Delete a Dataset](#delete-a-dataset)
 - [Configure Logging](#configure-logging)
   - [In Code](#in-code)
   - [Via Environment Variables](#via-environment-variables)
@@ -368,6 +375,88 @@ generator = EmbeddingGenerator.from_use_case(
 df["text_vector"] = generator.generate_embeddings(text_col=df["text"])
 ```
 
+## Operations on Datasets
+
+### List Datasets
+
+You can list all datasets that the user has access to using `client.datasets.list()`. You can use the `limit` parameter to specify the maximum number of datasets desired in the response and you can specify the `space_id` to target the list operation to a particular space.
+
+```python
+resp = client.datasets.list(
+    limit=... # Optional
+    space_id=... # Optional
+)
+```
+
+The response is an object of type `DatasetsList200Response`, and you can access the list of datasets via its `datasets` attribute. In addition, you can transform the response object to a dictionary, to JSON format, or a pandas dataframe.
+
+```python
+# Get the list of datasets from the response
+dataset_list = resp.datasets 
+# Get the response as a dictionary
+resp_dict = resp.to_dict()
+# Get the response in JSON format
+resp_dict = resp.to_json()
+# Get the response as a pandas dataframe
+resp_dict = resp.to_df()
+```
+
+### Create a Dataset
+
+You can create a dataset using `client.datasets.create()`. You must pass examples, we currently don't support creating an empty dataset, for instance, these are 2 rows of examples, as a list of dictionaries. You can also pass a pandas dataframe for the examples.
+
+```python
+examples = [
+    {
+        "eval.Correctness Basic.explanation": "The query indicates that the user is having trouble accessing their account on their laptop, while access on their phone is still working. This suggests a potential issue with the login process on the laptop, which aligns with the 'Login Issues' queue. The mention of a possible change in the account could relate to login credentials or settings affecting the laptop specifically, but it still falls under the broader category of login issues.",
+        "eval.Correctness Basic.label": "correct",
+        "eval.Correctness Basic.score": 1,
+        "llm output": "Login Issues",
+        "query": "I can't get in on my laptop anymore, but my phone still works fine — could this be because I changed something in my account?"
+    },
+    {
+        "eval.Correctness Basic.explanation": "The query is about a user who signed up but is unable to log in because the system says no account is found. This issue is related to the login process, as the user is trying to access their account and is facing a problem with the login system recognizing their account. Therefore, assigning this query to the 'Login Issues' queue is appropriate.",
+        "eval.Correctness Basic.label": "correct",
+        "eval.Correctness Basic.score": 1,
+        "llm output": "Login Issues",
+        "query": "Signed up ages ago but never got around to logging in — now it says no account found. Do I start over?"
+    }
+]
+```
+
+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.
+
+```python
+created_dataset = client.datasets.create(
+    space_i="<target-space-id>",
+    name="<your-dataset-name>", # Name must be unique within a space
+    examples=..., # List of dictionaries or pandas dataframe
+)
+```
+
+
+
+### 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.
+
+```python
+dataset = client.datasets.get(
+    dataset_id=... # The unique identifier of the dataset
+    dataset_version_id=... # The unique identifier of the dataset version
+)
+```
+
+### Delete a Dataset
+
+To delete a dataset by its ID use `client.datasets.delete()`. The call returns `None` if successful deletion took place, error otherwise.
+
+```python
+client.datasets.delete(
+    dataset_id=... # The unique identifier of the dataset
+)
+```
+
 # Configure Logging
 
 ## In Code

{arize-8.0.0a12.dist-info → arize-8.0.0a13.dist-info}/RECORD

@@ -1,54 +1,52 @@
 arize/__init__.py,sha256=-4bbbZwcjGS9OfAunsB-lmKRCzccPdFvZmvJQJEky3E,534
-arize/_lazy.py,sha256=MVep6D93sJWvArg4pgm4CVNGc6tu-XRK_Z7EDMuc76I,2358
-arize/client.py,sha256=kDdOWC1rwYgPPExO3wT3-KU3qpMwQ0ogrAdjvf7Ls3M,5860
-arize/config.py,sha256=iynVEZhrOPdTNJTQ_KQmwKOPiwL0LfEP8AUIDYW86Xw,5801
+arize/_lazy.py,sha256=1Lnm4l42t7W-m2JYCYD-S7ASBOIl0XJkBuli3Ei1VXA,2474
+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=pIYyrrKVIV-mJxlHLm5Y4gHaueX3_4oWwSPkGBkbmdI,25
+arize/version.py,sha256=1g3Ne_YSIwt3dSGmtEtvWJDZ7TJpxNJ6t6cItY3e-YY,25
 arize/_exporter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/_exporter/client.py,sha256=eAxJX1sUfdpLrtaQ0ynMTd5jI37JOp9fbl3NWp4WFEA,15216
 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
 arize/_flight/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize/_flight/client.py,sha256=OCqMf0SEclc2TLzMqu3wgORuLHHGkZOODDZsUu8F8a0,6895
+arize/_flight/client.py,sha256=5nH5F-jmtVOK9wklyGW6sBDJHxhTKdq0t1LaEijpggw,9781
 arize/_flight/types.py,sha256=OuLupzkGYt7r0PEzsX4NmXV9uq3lD11AeRaHHI5NsSw,146
 arize/_generated/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize/_generated/api_client_README.md,sha256=AM6a2RwMFfDPPt1nCFC-SYW0T4vNAwNfId9FYcPFjMM,4844
-arize/_generated/api_client/__init__.py,sha256=nwOsLqmUBDWbfo3w8DRiEoWL1rD2v8XrW8hFNNzlz4g,5367
-arize/_generated/api_client/api_client.py,sha256=Wo2j_q09pQQNF19QJZ_lxSui-jrVyBXLmCsg9wXuvRc,27990
+arize/_generated/api_client_README.md,sha256=Ww8o5NA3M07uLm8_SI51HDC8cPJO1tLTOqTU1Pnwo5s,4942
+arize/_generated/api_client/__init__.py,sha256=8Gwd24UqBYZXEAscsVIwcxpJ7z1f-MFtu9yJxqbVE9E,2792
+arize/_generated/api_client/api_client.py,sha256=dsM3yuWYR6O_OHPry5R5S8HVsMvibksjpHm7IWIGwXw,27990
 arize/_generated/api_client/api_response.py,sha256=eMxw1mpmJcoGZ3gs9z6jM4oYoZ10Gjk333s9sKxGv7s,652
 arize/_generated/api_client/configuration.py,sha256=M4-qSDv2FwLqjyl8uRfIGu48JCRrk1eWMHALBlKkqEg,18994
 arize/_generated/api_client/exceptions.py,sha256=5Vnmr2HaL2cbZrqT2Zm44q0VPCFimQS28qszUpsPfYs,6593
 arize/_generated/api_client/rest.py,sha256=oBXdZdxKrAW3xr9HImyyNK3F3JOdxSFIbHNFN0tvbyo,9603
-arize/_generated/api_client/api/__init__.py,sha256=hCjRIZx6rAgRGdjUNjbPHl3XJDoCEOsZn3uXNoKnLh0,641
-arize/_generated/api_client/api/datasets_api.py,sha256=tSXL2Uki6P8A9eMMyMF9si3VWrv6kuF5zxExmI_4-ho,58987
-arize/_generated/api_client/api/experiments_api.py,sha256=kCSDbA04W7qWzhys2pHhMIVNRV0bv2tPCLT9g8_2ZVI,12719
-arize/_generated/api_client/models/__init__.py,sha256=XfFle5pGefZfuzYOencNoUMxHelO-ZDVs5YpqOr8KlQ,2382
-arize/_generated/api_client/models/dataset.py,sha256=K0Q6KmzI9TZY-CLz9d5OZN6WnSPWvio8ESYyn6zcN8Q,4650
-arize/_generated/api_client/models/dataset_version.py,sha256=DOid8M0AdvjIC62ndAAw0Y2vEFgPCVQGAXcyykXYhUI,4073
-arize/_generated/api_client/models/datasets_create201_response.py,sha256=AZ5f7PbbZCPOSrdFE5pj2itaqvuOEqfbj7FDNHop2gk,2716
-arize/_generated/api_client/models/datasets_create_request.py,sha256=FJMO2LW398S2_FzKA33nGXCWXeyYAR2sJ8yTjUsPOw0,3453
-arize/_generated/api_client/models/datasets_list200_response.py,sha256=NblZnqa7DBIFtZKFDNK6XU3uhuV4k8B-pJdQ2FLEpro,3168
-arize/_generated/api_client/models/datasets_list_examples200_response.py,sha256=uAAcFlGMVoPqa-emVqZsMlrAUa3rVr_pdPKe8Wy5IDw,2734
-arize/_generated/api_client/models/error.py,sha256=Q54b32Cio6llepX22rzsZ3uib6C-IEcOPN3GBPsYaUA,3192
-arize/_generated/api_client/models/experiment.py,sha256=tJVqnROy8U6gDnPiZRr2-nk4vRSgWH-60KeC4bn4tjU,4798
-arize/_generated/api_client/models/experiments_list200_response.py,sha256=4AXkHBq8IFTLgDdqzonIIMAF5MaN19qn2cGcRd77aK8,3147
+arize/_generated/api_client/api/__init__.py,sha256=mi-qaCL6KBckrbJtN8ZwPHcc2M8GSDKjCOngIGOWVyw,192
+arize/_generated/api_client/api/datasets_api.py,sha256=we4_t-2f9xIvXLCg3CR2dsyMWg_Z6OL-0aeEOipyA9M,58685
+arize/_generated/api_client/api/experiments_api.py,sha256=p0U5Miilw7k9e9paUA4j5PrNQeN3OP6MGK-BBhe69KI,23293
+arize/_generated/api_client/models/__init__.py,sha256=ME1bwtOgn2VVJnCruOWucVxSMYPNXZcYDvkSqJe3rac,1166
+arize/_generated/api_client/models/dataset.py,sha256=7AdN40sZYQbmvkbXefam0aQz9mBk0UoNuTT8HIOMKNQ,4305
+arize/_generated/api_client/models/dataset_version.py,sha256=JFWJWH05ED4UX32MfIa1zoPD4Sr0nPvODEdppgvRDoU,3735
+arize/_generated/api_client/models/datasets_create_request.py,sha256=EGafmuzsr0KvlkTMdZ6cA-hdsNRTj9gBf-ZwK9dg8AQ,3122
+arize/_generated/api_client/models/datasets_list200_response.py,sha256=nFq4dEzsDM9gTNafyN95dBY6rJJEZGHxpkFcugxzZ24,3434
+arize/_generated/api_client/models/datasets_list_examples200_response.py,sha256=7kbFCb1pn6sSSs4YeY4vEvf5s0HugK1d9VUIj9WY2wE,3024
+arize/_generated/api_client/models/error.py,sha256=nlrEYG7t0Vag4HF7EaongORASK09hm8wumwDKrPO1aM,2845
+arize/_generated/api_client/models/experiment.py,sha256=fYHNJacVEMpbr4gIw1j3Nf8Qx6_90EQ41SM5LBKD4Y0,4456
+arize/_generated/api_client/models/experiments_list200_response.py,sha256=5M7FkJV4cRILLHBw1n5fui7A3WCnwqN7zzxdFOgsrS8,3500
 arize/_generated/api_client/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/_generated/api_client/test/test_dataset.py,sha256=SBCRDWfkVpjW4KpvPQYewQ6B-dkZNQ7aUat-6kNuoms,2237
 arize/_generated/api_client/test/test_dataset_version.py,sha256=GF7kNg9icnRm9D8NxOaaVh1YDl_IMEOwfxtSDxB-2gA,1788
 arize/_generated/api_client/test/test_datasets_api.py,sha256=87YkU1FQUGMPhlE3Tut7gA8BC7bkywz7323k6wfAs2k,1516
-arize/_generated/api_client/test/test_datasets_create201_response.py,sha256=pXzfp0DCtF-f27OfVvPmLwoHSw20WoHWMGbT7vhYZnk,1688
 arize/_generated/api_client/test/test_datasets_create_request.py,sha256=9YTIb9x33IGen_iuNw-S_KhXCKAZZroEcCwZx-dyAno,1813
 arize/_generated/api_client/test/test_datasets_list200_response.py,sha256=9Zc_ZNaqhrCFvnQ_VL05G1ZG2DEb-bQNwLk5nA6i7L4,3630
-arize/_generated/api_client/test/test_datasets_list_examples200_response.py,sha256=Urj8Qx185a1KkBww1Rv9sa9qUHRyLOwwy6Flo9pDSjA,1841
+arize/_generated/api_client/test/test_datasets_list_examples200_response.py,sha256=TQKmd1MtRhi-jQTY2BV7Pm--mf1GZfGcWoOhpUapx8M,1849
 arize/_generated/api_client/test/test_error.py,sha256=0XtZ4I6Q6cvaV22W_gmTzvFNFhFSj3Kv7muJVMoQywc,1410
 arize/_generated/api_client/test/test_experiment.py,sha256=PV415RGPEAjz5zNIZGDoaXyS6N3JXFjBTALdF8n5JKE,1916
-arize/_generated/api_client/test/test_experiments_api.py,sha256=Mu9AekLnYX5U7O1nM9c5BtKAOMIrnrDdzlPFf5flTok,940
-arize/_generated/api_client/test/test_experiments_list200_response.py,sha256=xqkh0dbFjqLMlUiK5fhMw4qIZKfiaDDjQQAQDrA1yMU,2880
+arize/_generated/api_client/test/test_experiments_api.py,sha256=NZ0Dy3-ygmmrit3LJFnd7g2TkMhYUa2QhtJLV0EYS0k,1093
+arize/_generated/api_client/test/test_experiments_list200_response.py,sha256=BetH2525aeMCBYYoxx0a-5gBbb-mzRC7QKpt4QIGSJ4,2894
 arize/_generated/protocol/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/_generated/protocol/flight/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize/_generated/protocol/flight/export_pb2.py,sha256=yhmOUp6XVbpAJnED6V-jCAWmpwtp7AZZDuU4BEfyj4k,4237
+arize/_generated/protocol/flight/export_pb2.py,sha256=fF5-2ygRwyLgPD_of_cDrqyi5He9ajXEcarJWivg8ZU,4320
 arize/_generated/protocol/flight/ingest_pb2.py,sha256=-wC5rbLK4yjROQuXOU9c_gPwA4aHKBCN86u6IeivUZo,24302
 arize/_generated/protocol/rec/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 arize/_generated/protocol/rec/public_pb2.py,sha256=vgP-yTSZLeomVwfIzcOo6t3i1mPCCNJGgd41ZkfLNng,79898
@@ -57,8 +55,8 @@ arize/constants/config.py,sha256=wDoptoadZviB0_7GgwqwkIWeyZFpLJdBy-SfaiGfwdE,107
 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=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-arize/datasets/client.py,sha256=Rk3TQF2IzJwi3JqF1GYt1tUs68gPIiVFRgKjEmY7igE,743
+arize/datasets/__init__.py,sha256=GVNsjaqzQt4x-nILE41BvWyZqfYAxPQB0oHZgIDW7ws,2289
+arize/datasets/client.py,sha256=HBzxSQ_SmCtda3nkEnunztiuxmAQOqtR4vNn5BaqXEs,5327
 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
@@ -117,10 +115,10 @@ 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/dataframe.py,sha256=I0FloPgNiqlKga32tMOvTE70598QA8Hhrgf-6zjYMAM,1120
-arize/utils/proto.py,sha256=9vLo53INYjdF78ffjm3E48jFwK6LbPD2FfKei7VaDy8,35477
+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-8.0.0a12.dist-info/METADATA,sha256=-1PeD1-Kf8yRY1Nw9PyuRDaOa88Rkg98Jd6l5ruq7Hk,14725
-arize-8.0.0a12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-arize-8.0.0a12.dist-info/licenses/LICENSE.md,sha256=8vLN8Gms62NCBorxIv9MUvuK7myueb6_-dhXHPmm4H0,1479
-arize-8.0.0a12.dist-info/RECORD,,
+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/_generated/api_client/models/datasets_create201_response.py

@@ -1,87 +0,0 @@
-# coding: utf-8
-
-"""
-    Arize REST API
-
-    API specification for the backend data server. The API is hosted globally at https://app.arize.com/api/v1 or in your own environment. You can access the OpenAPI spec for this API at https://app.arize.com/api/v1/spec.yaml 
-
-    The version of the OpenAPI document: 0.0.1
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict
-from typing import Optional, Set
-from typing_extensions import Self
-
-class DatasetsCreate201Response(BaseModel):
-    """
-    DatasetsCreate201Response
-    """ # noqa: E501
-    dataset_id: StrictStr = Field(description="The ID of the created dataset")
-    __properties: ClassVar[List[str]] = ["dataset_id"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of DatasetsCreate201Response from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of DatasetsCreate201Response from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "dataset_id": obj.get("dataset_id")
-        })
-        return _obj
-
-

arize/_generated/api_client/test/test_datasets_create201_response.py

@@ -1,52 +0,0 @@
-# coding: utf-8
-
-"""
-    Arize REST API
-
-    API specification for the backend data server. The API is hosted globally at https://app.arize.com/api/v1 or in your own environment. You can access the OpenAPI spec for this API at https://app.arize.com/api/v1/spec.yaml 
-
-    The version of the OpenAPI document: 0.0.1
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-import unittest
-
-from arize._generated.api_client.models.datasets_create201_response import DatasetsCreate201Response
-
-class TestDatasetsCreate201Response(unittest.TestCase):
-    """DatasetsCreate201Response unit test stubs"""
-
-    def setUp(self):
-        pass
-
-    def tearDown(self):
-        pass
-
-    def make_instance(self, include_optional) -> DatasetsCreate201Response:
-        """Test DatasetsCreate201Response
-            include_optional is a boolean, when False only required
-            params are included, when True both required and
-            optional params are included """
-        # uncomment below to create an instance of `DatasetsCreate201Response`
-        """
-        model = DatasetsCreate201Response()
-        if include_optional:
-            return DatasetsCreate201Response(
-                dataset_id = ''
-            )
-        else:
-            return DatasetsCreate201Response(
-                dataset_id = '',
-        )
-        """
-
-    def testDatasetsCreate201Response(self):
-        """Test DatasetsCreate201Response"""
-        # inst_req_only = self.make_instance(include_optional=False)
-        # inst_req_and_optional = self.make_instance(include_optional=True)
-
-if __name__ == '__main__':
-    unittest.main()