arize 8.0.0a2__tar.gz → 8.0.0a4__tar.gz

{arize-8.0.0a2 → arize-8.0.0a4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arize
-Version: 8.0.0a2
+Version: 8.0.0a4
 Summary: A helper library to interact with Arize AI APIs
 Project-URL: Homepage, https://arize.com
 Project-URL: Documentation, https://docs.arize.com/arize
@@ -26,11 +26,19 @@ Classifier: Topic :: System :: Logging
 Classifier: Topic :: System :: Monitoring
 Requires-Python: >=3.10
 Requires-Dist: lazy-imports
+Requires-Dist: numpy>=2.0.0
 Provides-Extra: dev
 Requires-Dist: pytest==8.4.2; extra == 'dev'
 Requires-Dist: ruff==0.13.2; extra == 'dev'
+Provides-Extra: ml-batch
+Requires-Dist: pandas<3,>=1.0.0; extra == 'ml-batch'
+Requires-Dist: protobuf<6,>=4.21.0; extra == 'ml-batch'
+Requires-Dist: pyarrow>=0.15.0; extra == 'ml-batch'
+Requires-Dist: tqdm; extra == 'ml-batch'
+Provides-Extra: ml-stream
+Requires-Dist: protobuf<6,>=4.21.0; extra == 'ml-stream'
+Requires-Dist: requests-futures<2,>=1.0.0; extra == 'ml-stream'
 Provides-Extra: spans
-Requires-Dist: numpy>=2.0.0; extra == 'spans'
 Requires-Dist: openinference-semantic-conventions<1,>=0.1.21; extra == 'spans'
 Requires-Dist: opentelemetry-semantic-conventions<1,>=0.43b0; extra == 'spans'
 Requires-Dist: pandas<3,>=1.0.0; extra == 'spans'
@@ -112,13 +120,14 @@ tracer_provider = register(
 OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
 ```
 
-
-### Logging Spans, Evaluations, and Annotations
+### Operations on Spans
 
 Use `arize.spans` to interact with spans: log spans into Arize, update the span's evaluations, annotations and metadata in bulk. 
 
 > **WARNING**: This is currently under an alpha release. Install with `pip install arize==8.0.0ax` where the `x` denotes the specific alpha version. Check the [pre-releases](https://pypi.org/project/arize/#history) page in PyPI.
 
+#### Logging spans
+
 ```python
 from arize import ArizeClient
 
@@ -130,22 +139,169 @@ client.spans.log(
     space_id=SPACE_ID,
     project_name=PROJECT_NAME,
     dataframe=spans_df,
-    evals_df=evals_df, # Optionally pass the evaluations together with the spans
+    # evals_df=evals_df, # Optionally pass the evaluations together with the spans
 )
+```
+
+#### Update spans Evaluations, Annotations, and Metadata
+
+```python
+from arize import ArizeClient
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+PROJECT_NAME = "<your-project-name>"
 
 client.spans.update_evaluations(
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
     dataframe=evals_df,
-    project_name="your-llm-project",
+    # force_http=... # Optionally pass force_http to update evaluations via HTTP instead of gRPC, defaults to False
 )
 
 client.spans.update_annotations(
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
     dataframe=annotations_df,
-    project_name="your-llm-project",
 )
 
 client.spans.update_metadata(
-    dataframe=annotations_df,
-    project_name="your-llm-project",
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
+    dataframe=metadata_df,
+)
+```
+
+#### Exporting spans
+
+Use the `export_to_df` or `export_to_parquet` to export large amounts of spans from Arize.
+
+```python
+from arize import ArizeClient
+from datetime import datetime
+
+FMT  = "%Y-%m-%d"
+start_time = datetime.strptime("2024-01-01",FMT)
+end_time = datetime.strptime("2026-01-01",FMT)
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+PROJECT_NAME = "<your-project-name>"
+
+df = client.spans.export_to_df(
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
+    start_time=start_time,
+    end_time=end_time,
+)
+```
+
+### Operations on ML Models
+
+Use `arize.models` to interact with ML models: log ML data (traininv, validation, production) into Arize, either streaming or in batches.
+
+> **WARNING**: This is currently under an alpha release. Install with `pip install arize==8.0.0ax` where the `x` denotes the specific alpha version. Check the [pre-releases](https://pypi.org/project/arize/#history) page in PyPI.
+
+#### Stream log ML Data for a Classification use-case
+
+```python
+from arize import ArizeClient
+from arize.types import ModelTypes, Environments
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+MODEL_NAME = "<your-model-name>"
+
+features=...
+embedding_features=...
+
+response = client.models.log_stream(
+    space_id=SPACE_ID,
+    model_name=MODEL_NAME,
+    model_type=ModelTypes.SCORE_CATEGORICAL,
+    environment=Environments.PRODUCTION,
+    prediction_label=("not fraud",0.3),
+    actual_label=("fraud",1.0),
+    features=features,
+    embedding_features=embedding_features,
+)
+```
+
+#### Log a batch of ML Data for a Classification use-case
+
+```python
+from arize import ArizeClient
+from arize.types import ModelTypes, Environments
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+MODEL_NAME = "<your-model-name>"
+MODEL_VERSION = "1.0"
+
+from arize.types import Schema, EmbeddingColumnNames, ObjectDetectionColumnNames, ModelTypes, Environments
+
+tags = ["drift_type"]
+embedding_feature_column_names = {
+    "image_embedding": EmbeddingColumnNames(
+        vector_column_name="image_vector", link_to_data_column_name="url"
+    )
+}
+object_detection_prediction_column_names = ObjectDetectionColumnNames(
+    bounding_boxes_coordinates_column_name="prediction_bboxes",
+    categories_column_name="prediction_categories",
+    scores_column_name="prediction_scores",
+)
+object_detection_actual_column_names = ObjectDetectionColumnNames(
+    bounding_boxes_coordinates_column_name="actual_bboxes",
+    categories_column_name="actual_categories",
+)
+
+# Define a Schema() object for Arize to pick up data from the correct columns for logging
+schema = Schema(
+    prediction_id_column_name="prediction_id",
+    timestamp_column_name="prediction_ts",
+    tag_column_names=tags,
+    embedding_feature_column_names=embedding_feature_column_names,
+    object_detection_prediction_column_names=object_detection_prediction_column_names,
+    object_detection_actual_column_names=object_detection_actual_column_names,
+)
+
+# Logging Production DataFrame
+response = client.models.log_batch(
+    space_id=SPACE_ID,
+    model_name=MODEL_NAME,
+    model_type=ModelTypes.OBJECT_DETECTION,
+    dataframe=prod_df,
+    schema=schema,
+    environment=Environments.PRODUCTION,
+    model_version = MODEL_VERSION, # Optionally pass a model version
+)
+```
+
+#### Exporting ML Data
+
+Use the `export_to_df` or `export_to_parquet` to export large amounts of spans from Arize.
+
+```python
+from arize import ArizeClient
+from datetime import datetime
+
+FMT  = "%Y-%m-%d"
+start_time = datetime.strptime("2024-01-01",FMT)
+end_time = datetime.strptime("2026-01-01",FMT)
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+MODEL_NAME = "<your-model-name>"
+MODEL_VERSION = "1.0"
+
+df = client.models.export_to_df(
+    space_id=SPACE_ID,
+    model_name=MODEL_NAME,
+    environment=Environments.TRAINING,
+    model_version=MODEL_VERSION,
+    start_time=start_time,
+    end_time=end_time,
 )
 ```
 

{arize-8.0.0a2 → arize-8.0.0a4}/README.md

@@ -71,13 +71,14 @@ tracer_provider = register(
 OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
 ```
 
-
-### Logging Spans, Evaluations, and Annotations
+### Operations on Spans
 
 Use `arize.spans` to interact with spans: log spans into Arize, update the span's evaluations, annotations and metadata in bulk. 
 
 > **WARNING**: This is currently under an alpha release. Install with `pip install arize==8.0.0ax` where the `x` denotes the specific alpha version. Check the [pre-releases](https://pypi.org/project/arize/#history) page in PyPI.
 
+#### Logging spans
+
 ```python
 from arize import ArizeClient
 
@@ -89,22 +90,169 @@ client.spans.log(
     space_id=SPACE_ID,
     project_name=PROJECT_NAME,
     dataframe=spans_df,
-    evals_df=evals_df, # Optionally pass the evaluations together with the spans
+    # evals_df=evals_df, # Optionally pass the evaluations together with the spans
 )
+```
+
+#### Update spans Evaluations, Annotations, and Metadata
+
+```python
+from arize import ArizeClient
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+PROJECT_NAME = "<your-project-name>"
 
 client.spans.update_evaluations(
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
     dataframe=evals_df,
-    project_name="your-llm-project",
+    # force_http=... # Optionally pass force_http to update evaluations via HTTP instead of gRPC, defaults to False
 )
 
 client.spans.update_annotations(
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
     dataframe=annotations_df,
-    project_name="your-llm-project",
 )
 
 client.spans.update_metadata(
-    dataframe=annotations_df,
-    project_name="your-llm-project",
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
+    dataframe=metadata_df,
+)
+```
+
+#### Exporting spans
+
+Use the `export_to_df` or `export_to_parquet` to export large amounts of spans from Arize.
+
+```python
+from arize import ArizeClient
+from datetime import datetime
+
+FMT  = "%Y-%m-%d"
+start_time = datetime.strptime("2024-01-01",FMT)
+end_time = datetime.strptime("2026-01-01",FMT)
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+PROJECT_NAME = "<your-project-name>"
+
+df = client.spans.export_to_df(
+    space_id=SPACE_ID,
+    project_name=PROJECT_NAME,
+    start_time=start_time,
+    end_time=end_time,
+)
+```
+
+### Operations on ML Models
+
+Use `arize.models` to interact with ML models: log ML data (traininv, validation, production) into Arize, either streaming or in batches.
+
+> **WARNING**: This is currently under an alpha release. Install with `pip install arize==8.0.0ax` where the `x` denotes the specific alpha version. Check the [pre-releases](https://pypi.org/project/arize/#history) page in PyPI.
+
+#### Stream log ML Data for a Classification use-case
+
+```python
+from arize import ArizeClient
+from arize.types import ModelTypes, Environments
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+MODEL_NAME = "<your-model-name>"
+
+features=...
+embedding_features=...
+
+response = client.models.log_stream(
+    space_id=SPACE_ID,
+    model_name=MODEL_NAME,
+    model_type=ModelTypes.SCORE_CATEGORICAL,
+    environment=Environments.PRODUCTION,
+    prediction_label=("not fraud",0.3),
+    actual_label=("fraud",1.0),
+    features=features,
+    embedding_features=embedding_features,
+)
+```
+
+#### Log a batch of ML Data for a Classification use-case
+
+```python
+from arize import ArizeClient
+from arize.types import ModelTypes, Environments
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+MODEL_NAME = "<your-model-name>"
+MODEL_VERSION = "1.0"
+
+from arize.types import Schema, EmbeddingColumnNames, ObjectDetectionColumnNames, ModelTypes, Environments
+
+tags = ["drift_type"]
+embedding_feature_column_names = {
+    "image_embedding": EmbeddingColumnNames(
+        vector_column_name="image_vector", link_to_data_column_name="url"
+    )
+}
+object_detection_prediction_column_names = ObjectDetectionColumnNames(
+    bounding_boxes_coordinates_column_name="prediction_bboxes",
+    categories_column_name="prediction_categories",
+    scores_column_name="prediction_scores",
+)
+object_detection_actual_column_names = ObjectDetectionColumnNames(
+    bounding_boxes_coordinates_column_name="actual_bboxes",
+    categories_column_name="actual_categories",
+)
+
+# Define a Schema() object for Arize to pick up data from the correct columns for logging
+schema = Schema(
+    prediction_id_column_name="prediction_id",
+    timestamp_column_name="prediction_ts",
+    tag_column_names=tags,
+    embedding_feature_column_names=embedding_feature_column_names,
+    object_detection_prediction_column_names=object_detection_prediction_column_names,
+    object_detection_actual_column_names=object_detection_actual_column_names,
+)
+
+# Logging Production DataFrame
+response = client.models.log_batch(
+    space_id=SPACE_ID,
+    model_name=MODEL_NAME,
+    model_type=ModelTypes.OBJECT_DETECTION,
+    dataframe=prod_df,
+    schema=schema,
+    environment=Environments.PRODUCTION,
+    model_version = MODEL_VERSION, # Optionally pass a model version
+)
+```
+
+#### Exporting ML Data
+
+Use the `export_to_df` or `export_to_parquet` to export large amounts of spans from Arize.
+
+```python
+from arize import ArizeClient
+from datetime import datetime
+
+FMT  = "%Y-%m-%d"
+start_time = datetime.strptime("2024-01-01",FMT)
+end_time = datetime.strptime("2026-01-01",FMT)
+
+client = ArizeClient(api_key=API_KEY)
+SPACE_ID = "<your-space-id>"
+MODEL_NAME = "<your-model-name>"
+MODEL_VERSION = "1.0"
+
+df = client.models.export_to_df(
+    space_id=SPACE_ID,
+    model_name=MODEL_NAME,
+    environment=Environments.TRAINING,
+    model_version=MODEL_VERSION,
+    start_time=start_time,
+    end_time=end_time,
 )
 ```
 

{arize-8.0.0a2 → arize-8.0.0a4}/pyproject.toml

@@ -35,6 +35,7 @@ classifiers = [
 ]
 dependencies = [
     "lazy-imports",
+    "numpy>=2.0.0",
     # "requests_futures==1.0.0",
     # "googleapis_common_protos>=1.51.0,<2",
     # "protobuf>=4.21.0,<6",
@@ -51,7 +52,6 @@ dev = [
     "ruff==0.13.2",
 ]
 spans = [
-    "numpy>=2.0.0",
     "openinference-semantic-conventions>=0.1.21, <1",
     "opentelemetry-semantic-conventions>=0.43b0, <1",
     "pandas>=1.0.0,<3",
@@ -59,6 +59,16 @@ spans = [
     "pyarrow>=0.15.0",
     "tqdm",
 ]
+ml-stream = [
+    "requests_futures>=1.0.0, <2",
+    "protobuf>=4.21.0,<6",
+]
+ml-batch = [
+    "pandas>=1.0.0,<3",
+    "pyarrow>=0.15.0",
+    "protobuf>=4.21.0,<6",
+    "tqdm",
+]
 # datasets-experiments = [
 #     "pydantic",
 # ]

{arize-8.0.0a2 → arize-8.0.0a4}/src/arize/_exporter/client.py

@@ -1,6 +1,4 @@
 # type: ignore[pb2]
-from __future__ import annotations
-
 import logging
 from dataclasses import dataclass
 from datetime import datetime
@@ -14,17 +12,14 @@ from google.protobuf.wrappers_pb2 import Int64Value
 from pyarrow import flight
 from tqdm import tqdm
 
-from arize._exporter.parsers.tracing_data_parser import (
-    OtelTracingDataTransformer,
-)
 from arize._exporter.validation import (
     validate_input_type,
-    validate_input_value,
     validate_start_end_time,
 )
 from arize._generated.protocol.flight import export_pb2
+from arize.logging import CtxAdapter
 from arize.types import Environments, SimilaritySearchParams
-from arize.utils.pandas import reset_dataframe_index
+from arize.utils.dataframe import reset_dataframe_index
 from arize.utils.proto import get_pb_flight_doput_request
 
 logger = logging.getLogger(__name__)
@@ -124,6 +119,10 @@ class ArizeExportClient:
         df.drop(null_columns, axis=1, inplace=True)
 
         if environment == Environments.TRACING:
+            from arize._exporter.parsers.tracing_data_parser import (
+                OtelTracingDataTransformer,
+            )
+
             # by default, transform the exported tracing data so that it's
             # easier to work with in Python
             df = OtelTracingDataTransformer().transform(df)
@@ -238,6 +237,27 @@ class ArizeExportClient:
         columns: List | None = None,
         stream_chunk_size: int | None = None,
     ) -> Tuple[flight.FlightStreamReader, int]:
+        # Bind common context for this operation
+        log = CtxAdapter(
+            logger,
+            {
+                "component": "exporter",
+                "operation": "export_to_df",
+                "space_id": space_id,
+                "model_id": model_id,
+                "environment": environment.name,
+                "model_version": model_version,
+                "batch_id": batch_id,
+                "include_actuals": include_actuals,
+                "where": where,
+                "columns": columns,
+                "similarity_search_params": similarity_search_params,
+                "stream_chunk_size": stream_chunk_size,
+                "start_time": start_time,
+                "end_time": end_time,
+            },
+        )
+        log.debug("Getting stream reader...")
         validate_input_type(space_id, "space_id", str)
         validate_input_type(model_id, "model_id", str)
         validate_input_type(environment, "environment", Environments)
@@ -281,7 +301,7 @@ class ArizeExportClient:
                     json_format.MessageToJson(query_descriptor)  # type: ignore
                 ),
             )
-            logger.debug("Fetching data...")
+            logger.info("Fetching data...")
 
             if flight_info.total_records == 0:
                 logger.warning("Query returns no data")

{arize-8.0.0a2 → arize-8.0.0a4}/src/arize/_exporter/parsers/tracing_data_parser.py

@@ -1,9 +1,8 @@
+from __future__ import annotations
+
 import json
 import logging
-from typing import List
-
-import numpy as np
-import pandas as pd
+from typing import TYPE_CHECKING, List
 
 from arize.spans.columns import (
     SPAN_ATTRIBUTES_EMBEDDING_EMBEDDINGS_COL,
@@ -19,6 +18,10 @@ from arize.spans.columns import (
     SPAN_START_TIME_COL,
 )
 
+if TYPE_CHECKING:
+    import numpy as np
+    import pandas as pd
+
 logger = logging.getLogger(__name__)
 
 

{arize-8.0.0a2 → arize-8.0.0a4}/src/arize/_exporter/validation.py

@@ -1,5 +1,9 @@
-from datetime import datetime
-from typing import Any
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from datetime import datetime
 
 
 def validate_input_type(
@@ -35,6 +39,6 @@ def validate_input_value(
     )
 
 
-def validate_start_end_time(start_time, end_time: datetime) -> None:
+def validate_start_end_time(start_time: datetime, end_time: datetime) -> None:
     if start_time >= end_time:
         raise ValueError("start_time must be before end_time")

{arize-8.0.0a2 → arize-8.0.0a4}/src/arize/_flight/client.py

@@ -2,29 +2,28 @@
 from __future__ import annotations
 
 import base64
+import logging
 from dataclasses import dataclass, field
-from typing import Any, Dict, List, Tuple
+from typing import TYPE_CHECKING, Any, Dict, List, Tuple
 
-import pyarrow as pa
 from google.protobuf import json_format
 from pyarrow import flight
 
-from arize._flight.types import FlightRequestType
 from arize._generated.protocol.flight.ingest_pb2 import (
     WriteSpanAnnotationResponse,
     WriteSpanAttributesMetadataResponse,
     WriteSpanEvaluationResponse,
 )
 from arize.config import get_python_version
-from arize.constants.config import (
-    DEFAULT_FLIGHT_HOST,
-    DEFAULT_FLIGHT_PORT,
-    DEFAULT_FLIGHT_TRANSPORT_SCHEME,
-)
 from arize.logging import log_a_list
 from arize.utils.proto import get_pb_flight_doput_request, get_pb_schema_tracing
 from arize.version import __version__
 
+if TYPE_CHECKING:
+    import pyarrow as pa
+
+    from arize._flight.client import FlightRequestType
+
 BytesPair = Tuple[bytes, bytes]
 Headers = List[BytesPair]
 WriteSpanResponse = (
@@ -32,7 +31,6 @@ WriteSpanResponse = (
     | WriteSpanAnnotationResponse
     | WriteSpanAttributesMetadataResponse
 )
-import logging
 
 logger = logging.getLogger(__name__)
 
@@ -40,10 +38,10 @@ logger = logging.getLogger(__name__)
 @dataclass(frozen=True)
 class ArizeFlightClient:
     api_key: str = field(repr=False)
-    host: str = DEFAULT_FLIGHT_HOST
-    port: int = DEFAULT_FLIGHT_PORT
-    scheme: str = DEFAULT_FLIGHT_TRANSPORT_SCHEME
-    request_verify: bool = True
+    host: str
+    port: int
+    scheme: str
+    request_verify: bool
 
     # internal cache for the underlying FlightClient
     _client: flight.FlightClient | None = field(
@@ -54,7 +52,6 @@ class ArizeFlightClient:
 
     @property
     def headers(self) -> Headers:
-        # Keep the typing simple: (bytes, bytes)
         return [
             (b"origin", b"arize-logging-client"),
             (b"auth-token-bin", str(self.api_key).encode("utf-8")),