ArizeExportClient, export methods are now integrated directly into the unified ArizeClient via resource-specific methods.
from arize.exporter import ArizeExportClient
client = ArizeExportClient(api_key="your-api-key")
from arize import ArizeClient
# Export methods are integrated into the unified client
client = ArizeClient(api_key="your-api-key")
Exporting Spans/Traces (LLM Data)
In v8, span export methods are available onclient.spans.
export_model_to_df() for Spans
Theexport_model_to_df() method for tracing data migrates to client.spans.export_to_df().
Parameter Reference
| Parameter | v7 | v8 | Changes |
|---|---|---|---|
space_id | Required | Required | — |
model_id | Required | Required | Renamed to project_name |
project_name | N/A | ✅ Required | Renamed from model_id |
environment | Required | ❌ Removed | Always TRACING for spans |
start_time | Required | Required | — |
end_time | Required | Required | — |
include_actuals | Optional | ❌ Removed | Not applicable to spans |
model_version | Optional | ❌ Removed | Not applicable to spans |
batch_id | Optional | ❌ Removed | Not applicable to spans |
where | Optional | Optional | — |
similarity_search_params | Optional | Optional | — |
columns | Optional | Optional | — |
stream_chunk_size | Optional | Optional | — |
parallelize_exports | Optional | ❌ Removed | No longer supported |
Side-by-Side Comparison
from arize.exporter import ArizeExportClient
from arize.utils.types import Environments
from datetime import datetime
# Client initialization
client = ArizeExportClient(api_key="your-api-key")
# Export spans/traces to DataFrame
df = client.export_model_to_df(
space_id="your-space-id",
model_id="my-llm-project",
environment=Environments.TRACING,
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
where="span.name = 'generate'",
columns=["span_id", "parent_span_id", "span.name"],
stream_chunk_size=1000,
parallelize_exports=True
)
from arize import ArizeClient
from datetime import datetime
# Client initialization
client = ArizeClient(api_key="your-api-key")
# Export spans/traces to DataFrame
df = client.spans.export_to_df(
space_id="your-space-id",
project_name="my-llm-project", # Renamed from model_id
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
where="span.name = 'generate'",
columns=["span_id", "parent_span_id", "span.name"],
stream_chunk_size=1000
# environment removed (always TRACING)
# include_actuals removed (not applicable)
# model_version removed (not applicable)
# batch_id removed (not applicable)
# parallelize_exports removed
)
export_model_to_parquet() for Spans
Theexport_model_to_parquet() method for tracing data migrates to client.spans.export_to_parquet().
Parameter Reference
| Parameter | v7 | v8 | Changes |
|---|---|---|---|
path | Required | Required | — |
space_id | Required | Required | — |
model_id | Required | Required | Renamed to project_name |
project_name | N/A | ✅ Required | Renamed from model_id |
environment | Required | ❌ Removed | Always TRACING for spans |
start_time | Required | Required | — |
end_time | Required | Required | — |
include_actuals | Optional | ❌ Removed | Not applicable to spans |
model_version | Optional | ❌ Removed | Not applicable to spans |
batch_id | Optional | ❌ Removed | Not applicable to spans |
where | Optional | Optional | — |
similarity_search_params | Optional | Optional | — |
columns | Optional | Optional | — |
stream_chunk_size | Optional | Optional | — |
parallelize_exports | Optional | ❌ Removed | No longer supported |
Side-by-Side Comparison
from arize.exporter import ArizeExportClient
from arize.utils.types import Environments
from datetime import datetime
# Client initialization
client = ArizeExportClient(api_key="your-api-key")
# Export spans/traces to Parquet
client.export_model_to_parquet(
path="/path/to/output.parquet",
space_id="your-space-id",
model_id="my-llm-project",
environment=Environments.TRACING,
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
where="span.name = 'generate'",
columns=["span_id", "parent_span_id", "span.name"],
stream_chunk_size=1000,
parallelize_exports=True
)
from arize import ArizeClient
from datetime import datetime
# Client initialization
client = ArizeClient(api_key="your-api-key")
# Export spans/traces to Parquet
client.spans.export_to_parquet(
path="/path/to/output.parquet",
space_id="your-space-id",
project_name="my-llm-project", # Renamed from model_id
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
where="span.name = 'generate'",
columns=["span_id", "parent_span_id", "span.name"],
stream_chunk_size=1000
# environment removed (always TRACING)
# include_actuals removed (not applicable)
# model_version removed (not applicable)
# batch_id removed (not applicable)
# parallelize_exports removed
)
Exporting Models (Traditional ML Data)
In v8, model export methods are available onclient.ml.
export_model_to_df() for Models
Theexport_model_to_df() method for traditional ML models migrates to client.ml.export_to_df().
Parameter Reference
| Parameter | v7 | v8 | Changes |
|---|---|---|---|
space_id | Required | Required | — |
model_id | Required | Required | Renamed to model_name |
model_name | N/A | ✅ Required | Renamed from model_id |
environment | Required | Required | — |
start_time | Required | Required | — |
end_time | Required | Required | — |
include_actuals | Optional | Optional | — |
model_version | Optional | Optional | — |
batch_id | Optional | Optional | — |
where | Optional | Optional | — |
similarity_search_params | Optional | Optional | — |
columns | Optional | Optional | — |
stream_chunk_size | Optional | Optional | — |
parallelize_exports | Optional | ❌ Removed | No longer supported |
Side-by-Side Comparison
from arize.exporter import ArizeExportClient
from arize.utils.types import Environments
from datetime import datetime
# Client initialization
client = ArizeExportClient(api_key="your-api-key")
# Export model data to DataFrame
df = client.export_model_to_df(
space_id="your-space-id",
model_id="fraud-detection",
environment=Environments.PRODUCTION,
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
include_actuals=True,
model_version="v1.0",
where="prediction_score > 0.8",
columns=["prediction_id", "prediction_label", "actual_label"],
stream_chunk_size=1000,
parallelize_exports=True
)
from arize import ArizeClient
from arize.ml.types import Environments
from datetime import datetime
# Client initialization
client = ArizeClient(api_key="your-api-key")
# Export model data to DataFrame
df = client.ml.export_to_df(
space_id="your-space-id",
model_name="fraud-detection", # Renamed from model_id
environment=Environments.PRODUCTION,
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
include_actuals=True,
model_version="v1.0",
where="prediction_score > 0.8",
columns=["prediction_id", "prediction_label", "actual_label"],
stream_chunk_size=1000
# parallelize_exports removed
)
export_model_to_parquet() for Models
Theexport_model_to_parquet() method for traditional ML models migrates to client.ml.export_to_parquet().
Parameter Reference
| Parameter | v7 | v8 | Changes |
|---|---|---|---|
path | Required | Required | — |
space_id | Required | Required | — |
model_id | Required | Required | Renamed to model_name |
model_name | N/A | ✅ Required | Renamed from model_id |
environment | Required | Required | — |
start_time | Required | Required | — |
end_time | Required | Required | — |
include_actuals | Optional | Optional | — |
model_version | Optional | Optional | — |
batch_id | Optional | Optional | — |
where | Optional | Optional | — |
similarity_search_params | Optional | Optional | — |
columns | Optional | Optional | — |
stream_chunk_size | Optional | Optional | — |
parallelize_exports | Optional | ❌ Removed | No longer supported |
Side-by-Side Comparison
from arize.exporter import ArizeExportClient
from arize.utils.types import Environments
from datetime import datetime
# Client initialization
client = ArizeExportClient(api_key="your-api-key")
# Export model data to Parquet
client.export_model_to_parquet(
path="/path/to/output.parquet",
space_id="your-space-id",
model_id="fraud-detection",
environment=Environments.PRODUCTION,
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
include_actuals=True,
model_version="v1.0",
where="prediction_score > 0.8",
columns=["prediction_id", "prediction_label", "actual_label"],
stream_chunk_size=1000,
parallelize_exports=True
)
from arize import ArizeClient
from arize.ml.types import Environments
from datetime import datetime
# Client initialization
client = ArizeClient(api_key="your-api-key")
# Export model data to Parquet
client.ml.export_to_parquet(
path="/path/to/output.parquet",
space_id="your-space-id",
model_name="fraud-detection", # Renamed from model_id
environment=Environments.PRODUCTION,
start_time=datetime(2024, 1, 1),
end_time=datetime(2024, 1, 31),
include_actuals=True,
model_version="v1.0",
where="prediction_score > 0.8",
columns=["prediction_id", "prediction_label", "actual_label"],
stream_chunk_size=1000
# parallelize_exports removed
)