arize 8.0.0a3__tar.gz → 8.0.0a4__tar.gz

{arize-8.0.0a3 → arize-8.0.0a4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arize
-Version: 8.0.0a3
+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
@@ -120,13 +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
 
@@ -138,22 +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-8.0.0a3 → 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-8.0.0a4/src/arize/version.py

@@ -0,0 +1 @@
+__version__ = "8.0.0a4"

arize-8.0.0a3/src/arize/version.py

@@ -1 +0,0 @@
-__version__ = "8.0.0a3"