Datasets SDK Reference - Orq.ai Documentation

Datasets

List Datasets

Retrieves a paginated list of datasets for the current workspace. Results can be paginated using cursor-based pagination.

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.list(limit=10)

    # Handle response
    print(res)

Show Parameters

{
    "limit": Optional[int],
    "starting_after": Optional[str],
    "ending_before": Optional[str],
}

Show Response

{
    "object": Literal["list"],
    "data": {
        "id": str,
        "display_name": str,
        "project_id": str,
        "workspace_id": str,
        "metadata": {
            "total_versions": float,
            "datapoints_count": float,
        },
        "created_by_id": OptionalNullable[str],
        "updated_by_id": OptionalNullable[str],
        "created": date,
        "updated": date,
    },
    "has_more": bool,
}

Create a Dataset

Creates a new dataset in the specified project.

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.create(request={
        "display_name": "Neva.Raynor10",
        "path": "Default",
    })

    # Handle response
    print(res)

Show Parameters

{
    "display_name": str,  # required
    "path": str,  # required
}

Show Response

{
    "id": str,
    "display_name": str,
    "project_id": str,
    "workspace_id": str,
    "metadata": {
        "total_versions": float,
        "datapoints_count": float,
    },
    "created_by_id": OptionalNullable[str],
    "updated_by_id": OptionalNullable[str],
    "created": date,
    "updated": date,
}

Retrieve a Dataset

Retrieves a specific dataset by its unique identifier

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.retrieve(dataset_id="<id>")

    # Handle response
    print(res)

Show Parameters

{
    "dataset_id": str,  # required
}

Show Response

{
    "id": str,
    "display_name": str,
    "project_id": str,
    "workspace_id": str,
    "metadata": {
        "total_versions": float,
        "datapoints_count": float,
    },
    "created_by_id": OptionalNullable[str],
    "updated_by_id": OptionalNullable[str],
    "created": date,
    "updated": date,
}

Update a Dataset

Update a dataset

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.update(dataset_id="<id>", path="Default")

    # Handle response
    print(res)

Show Parameters

{
    "dataset_id": str,  # required
    "display_name": Optional[str],
    "project_id": Optional[str],
    "path": Optional[str],
}

Show Response

{
    "id": str,
    "display_name": str,
    "project_id": str,
    "workspace_id": str,
    "metadata": {
        "total_versions": float,
        "datapoints_count": float,
    },
    "created_by_id": OptionalNullable[str],
    "updated_by_id": OptionalNullable[str],
    "created": date,
    "updated": date,
}

Delete a Dataset

Permanently deletes a dataset and all its datapoints. This action is irreversible.

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    orq.datasets.delete(dataset_id="<id>")

    # Use the SDK ...

Show Parameters

{
    "dataset_id": str,  # required
}

List Datapoints

Retrieves a paginated list of datapoints from a specific dataset.

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.list_datapoints(dataset_id="<id>", limit=10)

    # Handle response
    print(res)

Show Parameters

{
    "dataset_id": str,  # required
    "limit": Optional[int],
    "starting_after": Optional[str],
    "ending_before": Optional[str],
}

Show Response

{
    "object": Literal["list"],
    "data": {
        "id": str,
        "workspace_id": str,
        "inputs": Dict[str, Any],
        "messages": Union[ListDatasetDatapointsMessagesSystemMessage, ListDatasetDatapointsMessagesDeveloperMessage, ListDatasetDatapointsMessagesUserMessage, ListDatasetDatapointsMessagesAssistantMessage, ListDatasetDatapointsMessagesToolMessage],
        "expected_output": Optional[str],
        "evaluations": Union[ListDatasetDatapointsEvaluations1, ListDatasetDatapointsEvaluations2, ListDatasetDatapointsEvaluations3],
        "dataset_id": str,
        "snapshot_version": Optional[str],
        "created_by_id": OptionalNullable[str],
        "updated_by_id": OptionalNullable[str],
        "created": date,
        "updated": date,
    },
    "has_more": bool,
}

Create Datapoint

Creates a new datapoint in the specified dataset.

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.create_datapoint(dataset_id="<id>")

    # Handle response
    print(res)

Show Parameters

{
    "dataset_id": str,  # required
    "request_body": {  # optional
        "inputs": Dict[str, Any],
        "messages": Union[CreateDatasetItemMessagesSystemMessage, CreateDatasetItemMessagesDeveloperMessage, CreateDatasetItemMessagesUserMessage, CreateDatasetItemMessagesAssistantMessage, CreateDatasetItemMessagesToolMessage],
        "expected_output": Optional[str],
    },
}

Retrieve Datapoint

Retrieves a datapoint object

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.retrieve_datapoint(dataset_id="<id>", datapoint_id="<id>")

    # Handle response
    print(res)

Show Parameters

{
    "dataset_id": str,  # required
    "datapoint_id": str,  # required
}

Show Response

{
    "id": str,
    "workspace_id": str,
    "inputs": Dict[str, Any],
    "messages": Union[RetrieveDatapointMessagesSystemMessage, RetrieveDatapointMessagesDeveloperMessage, RetrieveDatapointMessagesUserMessage, RetrieveDatapointMessagesAssistantMessage, RetrieveDatapointMessagesToolMessage],
    "expected_output": Optional[str],
    "evaluations": Union[RetrieveDatapointEvaluations1, RetrieveDatapointEvaluations2, RetrieveDatapointEvaluations3],
    "dataset_id": str,
    "snapshot_version": Optional[str],
    "created_by_id": OptionalNullable[str],
    "updated_by_id": OptionalNullable[str],
    "created": date,
    "updated": date,
}

Update Datapoint

Update a datapoint

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    res = orq.datasets.update_datapoint(dataset_id="<id>", datapoint_id="<id>")

    # Handle response
    print(res)

Show Parameters

{
    "dataset_id": str,  # required
    "datapoint_id": str,  # required
    "inputs": Dict[str, Any],
    "messages": Union[UpdateDatapointMessagesSystemMessage, UpdateDatapointMessagesDeveloperMessage, UpdateDatapointMessagesUserMessage, UpdateDatapointMessagesAssistantMessage, UpdateDatapointMessagesToolMessage],
    "expected_output": Optional[str],
}

Show Response

{
    "id": str,
    "workspace_id": str,
    "inputs": Dict[str, Any],
    "messages": Union[UpdateDatapointMessagesDatasetsSystemMessage, UpdateDatapointMessagesDatasetsDeveloperMessage, UpdateDatapointMessagesDatasetsUserMessage, UpdateDatapointMessagesDatasetsAssistantMessage, UpdateDatapointMessagesDatasetsToolMessage],
    "expected_output": Optional[str],
    "evaluations": Union[UpdateDatapointEvaluations1, UpdateDatapointEvaluations2, UpdateDatapointEvaluations3],
    "dataset_id": str,
    "snapshot_version": Optional[str],
    "created_by_id": OptionalNullable[str],
    "updated_by_id": OptionalNullable[str],
    "created": date,
    "updated": date,
}

Delete Datapoint

Permanently deletes a specific datapoint from a dataset.

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    orq.datasets.delete_datapoint(dataset_id="<id>", datapoint_id="<id>")

    # Use the SDK ...

Show Parameters

{
    "dataset_id": str,  # required
    "datapoint_id": str,  # required
}

Clear Datasets

Delete all datapoints from a dataset. This action is irreversible.

from orq_ai_sdk import Orq
import os

with Orq(
    api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:

    orq.datasets.clear(dataset_id="<id>")

    # Use the SDK ...

Show Parameters

{
    "dataset_id": str,  # required
}

​Datasets

​List Datasets

​Create a Dataset

​Retrieve a Dataset

​Update a Dataset

​Delete a Dataset

​List Datapoints

​Create Datapoint

​Retrieve Datapoint

​Update Datapoint

​Delete Datapoint

​Clear Datasets

Datasets

List Datasets

Create a Dataset

Retrieve a Dataset

Update a Dataset

Delete a Dataset

List Datapoints

Create Datapoint

Retrieve Datapoint

Update Datapoint

Delete Datapoint

Clear Datasets