Migrate Datasets Client

from arize.experimental.datasets import ArizeDatasetsClient

# v7 api_key parameter took developer key values
client = ArizeDatasetsClient(
    api_key="your-developer-key"  # Developer key (deprecated)
)

from arize import ArizeClient

# v8 api_key parameter takes standard API keys
client = ArizeClient(
    api_key="your-api-key"  # Standard API key
)

from arize.experimental.datasets import ArizeDatasetsClient

# Client initialization
client = ArizeDatasetsClient(api_key="your-developer-key")

# List datasets
datasets_df = client.list_datasets(space_id="your-space-id")

from arize import ArizeClient

# Client initialization
client = ArizeClient(api_key="your-api-key")

# List datasets
response = client.datasets.list(
    space_id="your-space-id",  # Optional in v8
    limit=100,
    cursor=None
)
datasets = response.to_df()

from arize.experimental.datasets import ArizeDatasetsClient
from arize.pandas.proto import flight_pb2
import pandas as pd

# Client initialization
client = ArizeDatasetsClient(api_key="your-developer-key")

# Create dataset
dataset_id = client.create_dataset(
    space_id="your-space-id",
    dataset_name="my-dataset",
    dataset_type=flight_pb2.DatasetType.GENERATIVE,
    data=dataset_df,
    convert_dict_to_json=True,
    max_chunk_size=1000
)

from arize import ArizeClient
import pandas as pd

# Client initialization with max_chunk_size configured at client level
client = ArizeClient(
    api_key="your-api-key",
    pyarrow_max_chunksize=1000  # Configured at client level
)

# Create dataset
dataset = client.datasets.create(
    name="my-dataset",  # Renamed from dataset_name
    space_id="your-space-id",
    examples=dataset_df,  # Renamed from data
    force_http=False
    # dataset_type removed
    # convert_dict_to_json removed (automatic)
    # max_chunk_size now configured at client level
)
dataset_id = dataset.id

from arize.experimental.datasets import ArizeDatasetsClient

# Client initialization
client = ArizeDatasetsClient(api_key="your-developer-key")

# Get dataset examples (underlying data) by ID
dataset_df = client.get_dataset(
    space_id="your-space-id",
    dataset_id="dataset-123",
    dataset_version="v1",
    convert_json_str_to_dict=True
)
# Returns: pandas DataFrame with the dataset examples

# Or get by name
dataset_df = client.get_dataset(
    space_id="your-space-id",
    dataset_name="my-dataset"
)

from arize import ArizeClient

# Client initialization
client = ArizeClient(api_key="your-api-key")

# Step 1: Get dataset metadata (includes versions)
dataset = client.datasets.get(dataset_id="dataset-123")
# Returns: Dataset object with metadata and versions
# Does NOT include examples (underlying data)

# Step 2: Get dataset examples (underlying data)
# Option A: Get all examples at once (uses Flight, more efficient for large datasets)
examples_response = client.datasets.list_examples(
    dataset_id="dataset-123",
    dataset_version_id="version-456",  # Optional, defaults to latest
    all=True  # Retrieves all examples via Flight (bypasses pagination)
)
examples = examples_response.to_df()

# Option B: Use pagination (uses REST, better for browsing/previewing)
examples_response = client.datasets.list_examples(
    dataset_id="dataset-123",
    limit=100,  # Get 100 examples per page
    all=False  # Use REST with pagination (default)
)
examples = examples_response.to_df()
# Use response.pagination.cursor for next page if needed

from arize.experimental.datasets import ArizeDatasetsClient

# Client initialization
client = ArizeDatasetsClient(api_key="your-developer-key")

# Delete dataset by ID
success = client.delete_dataset(
    space_id="your-space-id",
    dataset_id="dataset-123"
)

# Or delete by name
success = client.delete_dataset(
    space_id="your-space-id",
    dataset_name="my-dataset"
)

from arize import ArizeClient

# Client initialization
client = ArizeClient(api_key="your-api-key")

# Delete dataset by ID
client.datasets.delete(dataset_id="dataset-123")
# Returns None on success