viam-sdk 0.41.1__py3-none-linux_armv6l.whl → 0.66.0__py3-none-linux_armv6l.whl

viam/app/data_client.py

@@ -2,11 +2,12 @@ import warnings
 from dataclasses import dataclass
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Dict, List, Mapping, Optional, Sequence, Tuple, Union
+from typing import Any, Dict, List, Mapping, Optional, Sequence, Tuple, Union, cast
 
 import bson
 from google.protobuf.struct_pb2 import Struct
 from grpclib.client import Channel, Stream
+from typing_extensions import Self
 
 from viam import logging
 from viam.proto.app.data import (
@@ -26,12 +27,16 @@ from viam.proto.app.data import (
     CaptureInterval,
     CaptureMetadata,
     ConfigureDatabaseUserRequest,
+    CreateBinaryDataSignedURLRequest,
+    CreateBinaryDataSignedURLResponse,
+    CreateIndexRequest,
     DataRequest,
     DataServiceStub,
     DeleteBinaryDataByFilterRequest,
     DeleteBinaryDataByFilterResponse,
     DeleteBinaryDataByIDsRequest,
     DeleteBinaryDataByIDsResponse,
+    DeleteIndexRequest,
     DeleteTabularDataRequest,
     DeleteTabularDataResponse,
     ExportTabularDataRequest,
@@ -41,6 +46,10 @@ from viam.proto.app.data import (
     GetDatabaseConnectionResponse,
     GetLatestTabularDataRequest,
     GetLatestTabularDataResponse,
+    Index,
+    IndexableCollection,
+    ListIndexesRequest,
+    ListIndexesResponse,
     Order,
     RemoveBinaryDataFromDatasetByIDsRequest,
     RemoveBoundingBoxFromImageByIDRequest,
@@ -54,9 +63,31 @@ from viam.proto.app.data import (
     TabularDataByMQLResponse,
     TabularDataBySQLRequest,
     TabularDataBySQLResponse,
+    TabularDataSource,
+    TabularDataSourceType,
     TagsByFilterRequest,
     TagsByFilterResponse,
 )
+from viam.proto.app.datapipelines import (
+    CreateDataPipelineRequest,
+    CreateDataPipelineResponse,
+    DataPipelineRunStatus,
+    DataPipelinesServiceStub,
+    DeleteDataPipelineRequest,
+    GetDataPipelineRequest,
+    GetDataPipelineResponse,
+    ListDataPipelineRunsRequest,
+    ListDataPipelineRunsResponse,
+    ListDataPipelinesRequest,
+    ListDataPipelinesResponse,
+    RenameDataPipelineRequest,
+)
+from viam.proto.app.datapipelines import (
+    DataPipeline as ProtoDataPipeline,
+)
+from viam.proto.app.datapipelines import (
+    DataPipelineRun as ProtoDataPipelineRun,
+)
 from viam.proto.app.dataset import (
     CreateDatasetRequest,
     CreateDatasetResponse,
@@ -67,6 +98,8 @@ from viam.proto.app.dataset import (
     ListDatasetsByIDsResponse,
     ListDatasetsByOrganizationIDRequest,
     ListDatasetsByOrganizationIDResponse,
+    MergeDatasetsRequest,
+    MergeDatasetsResponse,
     RenameDatasetRequest,
 )
 from viam.proto.app.datasync import (
@@ -84,7 +117,7 @@ from viam.proto.app.datasync import (
     StreamingDataCaptureUploadResponse,
     UploadMetadata,
 )
-from viam.utils import ValueTypes, _alias_param, create_filter, datetime_to_timestamp, struct_to_dict
+from viam.utils import ValueTypes, _alias_param, create_filter, datetime_to_timestamp, dict_to_struct, struct_to_dict
 
 LOGGER = logging.getLogger(__name__)
 
@@ -92,10 +125,10 @@ LOGGER = logging.getLogger(__name__)
 class DataClient:
     """gRPC client for uploading and retrieving data from app.
 
-    Constructor is used by `ViamClient` to instantiate relevant service stubs. Calls to `DataClient` methods should be made through
-    `ViamClient`.
+    This class's constructor instantiates relevant service stubs. Always make :class:`DataClient` method calls through an instance of
+    :class:`ViamClient`.
 
-    Establish a Connection::
+    Establish a connection::
 
         import asyncio
 
@@ -111,11 +144,9 @@ class DataClient:
 
         async def main():
             # Make a ViamClient
-            viam_client = await connect()
-            # Instantiate a DataClient to run data client API methods on
-            data_client = viam_client.data_client
-
-            viam_client.close()
+            async with await connect() as viam_client:
+                # Instantiate a DataClient to run data client API methods on
+                data_client = viam_client.data_client
 
         if __name__ == '__main__':
             asyncio.run(main())
@@ -159,10 +190,10 @@ class DataClient:
         """The resource name"""
 
         resource_api: str
-        """The resource API. Ex: rdk:component:sensor"""
+        """The resource API. For example, rdk:component:sensor"""
 
         method_name: str
-        """The method used for data capture. Ex: Readings"""
+        """The method used for data capture. For example, Readings"""
 
         time_captured: datetime
         """The time at which the data point was captured"""
@@ -220,8 +251,131 @@ class DataClient:
             )
             return self.resource_api
 
+    @dataclass
+    class DataPipeline:
+        """Represents a data pipeline and its associated metadata."""
+
+        id: str
+        """The ID of the data pipeline"""
+
+        organization_id: str
+        """The organization ID"""
+
+        name: str
+        """The name of the data pipeline"""
+
+        mql_binary: List[Dict[str, Any]]
+        """The MQL binary of the data pipeline"""
+
+        schedule: str
+        """The schedule of the data pipeline"""
+
+        created_on: datetime
+        """The time the data pipeline was created"""
+
+        updated_at: datetime
+        """The time the data pipeline was last updated"""
+
+        enabled: bool
+        """Whether the data pipeline is enabled"""
+
+        data_source_type: TabularDataSourceType.ValueType
+        """The type of data source for the data pipeline"""
+
+        @classmethod
+        def from_proto(cls, data_pipeline: ProtoDataPipeline) -> Self:
+            return cls(
+                id=data_pipeline.id,
+                organization_id=data_pipeline.organization_id,
+                name=data_pipeline.name,
+                mql_binary=[bson.decode(bson_bytes) for bson_bytes in data_pipeline.mql_binary],
+                schedule=data_pipeline.schedule,
+                created_on=data_pipeline.created_on.ToDatetime(),
+                updated_at=data_pipeline.updated_at.ToDatetime(),
+                enabled=data_pipeline.enabled,
+                data_source_type=data_pipeline.data_source_type,
+            )
+
+    @dataclass
+    class DataPipelineRun:
+        """Represents a data pipeline run and its associated metadata."""
+
+        id: str
+        """The ID of the data pipeline run"""
+
+        status: DataPipelineRunStatus.ValueType
+        """The status of the data pipeline run"""
+
+        start_time: datetime
+        """The time the data pipeline run started"""
+
+        end_time: datetime
+        """The time the data pipeline run ended"""
+
+        data_start_time: datetime
+        """The start time of the data that was processed in the run."""
+        data_end_time: datetime
+        """The end time of the data that was processed in the run."""
+
+        error_message: str
+        """The error message of the data pipeline run. Only set if the run failed."""
+
+        @classmethod
+        def from_proto(cls, data_pipeline_run: ProtoDataPipelineRun) -> Self:
+            return cls(
+                id=data_pipeline_run.id,
+                status=data_pipeline_run.status,
+                start_time=data_pipeline_run.start_time.ToDatetime(),
+                end_time=data_pipeline_run.end_time.ToDatetime(),
+                data_start_time=data_pipeline_run.data_start_time.ToDatetime(),
+                data_end_time=data_pipeline_run.data_end_time.ToDatetime(),
+                error_message=data_pipeline_run.error_message,
+            )
+
+    @dataclass
+    class DataPipelineRunsPage:
+        """Represents a page of data pipeline runs and provides pagination functionality."""
+
+        _client: "DataClient"
+        """The data client used to make API calls"""
+
+        pipeline_id: str
+        """The ID of the pipeline these runs belong to"""
+
+        page_size: int
+        """The number of runs per page"""
+
+        runs: List["DataClient.DataPipelineRun"]
+        """The list of runs in this page"""
+
+        next_page_token: str
+        """The token to use to get the next page of results"""
+
+        async def next_page(self) -> "DataClient.DataPipelineRunsPage":
+            """Get the next page of data pipeline runs.
+
+            Returns:
+                DataPipelineRunsPage: The next page of runs, or an empty page if there are no more runs
+            """
+            if not self.next_page_token:
+                # no token, return empty next page
+                return DataClient.DataPipelineRunsPage(
+                    _client=self._client, pipeline_id=self.pipeline_id, page_size=self.page_size, runs=[], next_page_token=""
+                )
+            return await self._client._list_data_pipeline_runs(self.pipeline_id, self.page_size, self.next_page_token)
+
+        @classmethod
+        def from_proto(cls, data_pipeline_runs_page: ListDataPipelineRunsResponse, client: "DataClient", page_size: int) -> Self:
+            return cls(
+                _client=client,
+                pipeline_id=data_pipeline_runs_page.pipeline_id,
+                page_size=page_size,
+                runs=[DataClient.DataPipelineRun.from_proto(run) for run in data_pipeline_runs_page.runs],
+                next_page_token=data_pipeline_runs_page.next_page_token,
+            )
+
     def __init__(self, channel: Channel, metadata: Mapping[str, str]):
-        """Create a `DataClient` that maintains a connection to app.
+        """Create a :class:`DataClient` that maintains a connection to app.
 
         Args:
             channel (grpclib.client.Channel): Connection to app.
@@ -231,11 +385,13 @@ class DataClient:
         self._data_client = DataServiceStub(channel)
         self._data_sync_client = DataSyncServiceStub(channel)
         self._dataset_client = DatasetServiceStub(channel)
+        self._data_pipelines_client = DataPipelinesServiceStub(channel)
         self._channel = channel
 
     _data_client: DataServiceStub
     _data_sync_client: DataSyncServiceStub
     _dataset_client: DatasetServiceStub
+    _data_pipelines_client: DataPipelinesServiceStub
     _metadata: Mapping[str, str]
     _channel: Channel
 
@@ -249,9 +405,8 @@ class DataClient:
         include_internal_data: bool = False,
         dest: Optional[str] = None,
     ) -> Tuple[List[TabularData], int, str]:
-        """Filter and download tabular data. The data will be paginated into pages of `limit` items, and the pagination ID will be included
-        in the returned tuple. If a destination is provided, the data will be saved to that file.
-        If the file is not empty, it will be overwritten.
+        """Filter and download tabular data. The data will be paginated into pages of ``limit`` items; the returned tuple will include
+        the pagination ID. If a destination is provided, this method saves returned data to that file, overwriting any existing file content.
 
         ::
 
@@ -269,23 +424,23 @@ class DataClient:
             print(f"My data: {my_data}")
 
         Args:
-            filter (viam.proto.app.data.Filter): Optional `Filter` specifying tabular data to retrieve. No `Filter` implies all tabular
-                data.
+            filter (~viam.proto.app.data.Filter): Optional, specifies tabular data to retrieve. If missing, matches all tabular data.
             limit (int): The maximum number of entries to include in a page. Defaults to 50 if unspecified.
-            sort_order (viam.proto.app.data.Order): The desired sort order of the data.
+            sort_order (~viam.proto.app.data.Order): The desired sort order of the data.
             last (str): Optional string indicating the object identifier of the last-returned data.
-                        This object identifier is returned by calls to `TabularDataByFilter` as the `last` value.
-                        If provided, the server will return the next data entries after the last object identifier.
+                Returned by calls to :class:`TabularDataByFilter` as the ``last`` value.
+                If provided, the server returns the next data entries after the last object identifier.
             count_only (bool): Whether to return only the total count of entries.
             include_internal_data (bool): Whether to return the internal data. Internal data is used for Viam-specific data ingestion,
-                                          like cloud SLAM. Defaults to `False`.
+                like cloud SLAM. Defaults to ``False``.
             dest (str): Optional filepath for writing retrieved data.
 
         Returns:
             Tuple[List[TabularData], int, str]: A tuple containing the following:
-            List[TabularData]: The tabular data,
-            int: The count (number of entries),
-            str: The last-returned page ID.
+
+                - ``tabular_data`` (*List[TabularData]*): The tabular data.
+                - ``count`` (*int*): The count (number of entries).
+                - ``last`` (*str*): The last-returned page ID.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#tabulardatabyfilter>`_.
         """
@@ -332,7 +487,7 @@ class DataClient:
 
         Args:
             organization_id (str): The ID of the organization that owns the data.
-                You can obtain your organization ID from the Viam app's organization settings page.
+                To find your organization ID, visit the organization settings page.
             sql_query (str): The SQL query to run.
 
         Returns:
@@ -346,7 +501,13 @@ class DataClient:
 
     @_alias_param("query", param_alias="mql_binary")
     async def tabular_data_by_mql(
-        self, organization_id: str, query: Union[List[bytes], List[Dict[str, Any]]], use_recent_data: Optional[bool] = None
+        self,
+        organization_id: str,
+        query: Union[List[bytes], List[Dict[str, Any]]],
+        use_recent_data: Optional[bool] = None,
+        tabular_data_source_type: TabularDataSourceType.ValueType = TabularDataSourceType.TABULAR_DATA_SOURCE_TYPE_STANDARD,
+        pipeline_id: Optional[str] = None,
+        query_prefix_name: Optional[str] = None,
     ) -> List[Dict[str, Union[ValueTypes, datetime]]]:
         """Obtain unified tabular data and metadata, queried with MQL.
 
@@ -363,11 +524,17 @@ class DataClient:
 
         Args:
             organization_id (str): The ID of the organization that owns the data.
-                You can obtain your organization ID from the Viam app's organization settings page.
+                To find your organization ID, visit the organization settings page.
             query (Union[List[bytes], List[Dict[str, Any]]]): The MQL query to run, as a list of MongoDB aggregation pipeline stages.
-                Note: Each stage can be provided as either a dictionary or raw BSON bytes, but support for bytes will be removed in the future,
-                so using a dictionary is preferred.
-            use_recent_data (bool): Whether to query blob storage or your recent data store. Defaults to `False`
+                Each stage can be provided as either a dictionary or raw BSON bytes, but support for bytes will be removed in the
+                future, so prefer the dictionary option.
+            use_recent_data (bool): Whether to query blob storage or your recent data store. Defaults to ``False``..
+                Deprecated, use `tabular_data_source_type` instead.
+            tabular_data_source_type (viam.proto.app.data.TabularDataSourceType): The data source to query.
+                Defaults to `TABULAR_DATA_SOURCE_TYPE_STANDARD`.
+            pipeline_id (str): The ID of the data pipeline to query. Defaults to `None`.
+                Required if `tabular_data_source_type` is `TABULAR_DATA_SOURCE_TYPE_PIPELINE_SINK`.
+            query_prefix_name (str): Optional field that can be used to specify a saved query to run.
 
         Returns:
             List[Dict[str, Union[ValueTypes, datetime]]]: An array of decoded BSON data objects.
@@ -375,13 +542,26 @@ class DataClient:
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#tabulardatabymql>`_.
         """
         binary: List[bytes] = [bson.encode(query) for query in query] if isinstance(query[0], dict) else query  # type: ignore
-        request = TabularDataByMQLRequest(organization_id=organization_id, mql_binary=binary, use_recent_data=use_recent_data)
+        data_source = TabularDataSource(type=tabular_data_source_type, pipeline_id=pipeline_id)
+        if use_recent_data:
+            data_source.type = TabularDataSourceType.TABULAR_DATA_SOURCE_TYPE_HOT_STORAGE
+        request = TabularDataByMQLRequest(
+            organization_id=organization_id,
+            mql_binary=binary,
+            data_source=data_source,
+            query_prefix_name=query_prefix_name,
+        )
         response: TabularDataByMQLResponse = await self._data_client.TabularDataByMQL(request, metadata=self._metadata)
         return [bson.decode(bson_bytes) for bson_bytes in response.raw_data]
 
     @_alias_param("resource_api", param_alias="resource_subtype")
     async def get_latest_tabular_data(
-        self, part_id: str, resource_name: str, resource_api: str, method_name: str
+        self,
+        part_id: str,
+        resource_name: str,
+        resource_api: str,
+        method_name: str,
+        additional_params: Optional[Mapping[str, ValueTypes]] = None,
     ) -> Optional[Tuple[datetime, datetime, Dict[str, ValueTypes]]]:
         """Gets the most recent tabular data captured from the specified data source, as long as it was synced within the last year.
 
@@ -391,7 +571,8 @@ class DataClient:
                 part_id="77ae3145-7b91-123a-a234-e567cdca8910",
                 resource_name="camera-1",
                 resource_api="rdk:component:camera",
-                method_name="GetImage"
+                method_name="GetImages",
+                additional_params={"docommand_input": {"test": "test"}}
             )
 
             if tabular_data:
@@ -404,22 +585,30 @@ class DataClient:
 
         Args:
             part_id (str): The ID of the part that owns the data.
-            resource_name (str): The name of the requested resource that captured the data. Ex: "my-sensor".
-            resource_api (str): The API of the requested resource that captured the data. Ex: "rdk:component:sensor".
-            method_name (str): The data capture method name. Ex: "Readings".
+            resource_name (str): The name of the requested resource that captured the data. For example, "my-sensor".
+            resource_api (str): The API of the requested resource that captured the data. For example, "rdk:component:sensor".
+            method_name (str): The data capture method name. For exampe, "Readings".
+            additional_params (dict): Optional additional parameters of the resource that captured the data.
 
         Returns:
-            Optional[Tuple[datetime, datetime, Dict[str, ValueTypes]]]: A return value of None means that data hasn't been synced yet for the data source
-            or the most recently captured data was over a year ago, otherwise the returned tuple contains the following:
-            datetime: The time captured,
-            datetime: The time synced,
-            Dict[str, ValueTypes]: The latest tabular data captured from the specified data source.
+            Optional[Tuple[datetime, datetime, Dict[str, ValueTypes]]]:
+            A return value of ``None`` means that this data source
+            has not synced data in the last year. Otherwise, the data source has synced some data in the last year, so the returned
+            tuple contains the following:
+
+                - ``time_captured`` (*datetime*): The time captured.
+                - ``time_synced`` (*datetime*): The time synced.
+                - ``payload`` (*Dict[str, ValueTypes]*): The latest tabular data captured from the specified data source.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#getlatesttabulardata>`_.
         """
 
         request = GetLatestTabularDataRequest(
-            part_id=part_id, resource_name=resource_name, resource_subtype=resource_api, method_name=method_name
+            part_id=part_id,
+            resource_name=resource_name,
+            resource_subtype=resource_api,
+            method_name=method_name,
+            additional_parameters=dict_to_struct(additional_params) if additional_params is not None else None,
         )
         response: GetLatestTabularDataResponse = await self._data_client.GetLatestTabularData(request, metadata=self._metadata)
         if not response.payload:
@@ -435,6 +624,7 @@ class DataClient:
         method_name: str,
         start_time: Optional[datetime] = None,
         end_time: Optional[datetime] = None,
+        additional_params: Optional[Mapping[str, ValueTypes]] = None,
     ) -> List[TabularDataPoint]:
         """Obtain unified tabular data and metadata from the specified data source.
 
@@ -447,6 +637,7 @@ class DataClient:
                 method_name="<METHOD-NAME>",
                 start_time="<START_TIME>"
                 end_time="<END_TIME>"
+                additional_params="<ADDITIONAL_PARAMETERS>"
             )
 
             print(f"My data: {tabular_data}")
@@ -458,6 +649,7 @@ class DataClient:
             method_name (str): The data capture method name.
             start_time (datetime): Optional start time for requesting a specific range of data.
             end_time (datetime): Optional end time for requesting a specific range of data.
+            additional_params (dict): Optional additional parameters of the resource that captured the data.
 
         Returns:
             List[TabularDataPoint]: The unified tabular data and metadata.
@@ -467,7 +659,12 @@ class DataClient:
 
         interval = CaptureInterval(start=datetime_to_timestamp(start_time), end=datetime_to_timestamp(end_time))
         request = ExportTabularDataRequest(
-            part_id=part_id, resource_name=resource_name, resource_subtype=resource_api, method_name=method_name, interval=interval
+            part_id=part_id,
+            resource_name=resource_name,
+            resource_subtype=resource_api,
+            method_name=method_name,
+            interval=interval,
+            additional_parameters=dict_to_struct(additional_params) if additional_params is not None else None,
         )
         response: List[ExportTabularDataResponse] = await self._data_client.ExportTabularData(request, metadata=self._metadata)
 
@@ -501,9 +698,9 @@ class DataClient:
         include_internal_data: bool = False,
         dest: Optional[str] = None,
     ) -> Tuple[List[BinaryData], int, str]:
-        """Filter and download binary data. The data will be paginated into pages of `limit` items, and the pagination ID will be included
-        in the returned tuple. If a destination is provided, the data will be saved to that file.
-        If the file is not empty, it will be overwritten.
+        """Filter and download binary data. The data will be paginated into pages of ``limit`` items, and the pagination ID will be included
+        in the returned tuple as ``last``. If a destination is provided, this method saves returned data to that file,
+        overwriting any existing file content.
 
         ::
 
@@ -542,25 +739,25 @@ class DataClient:
                 my_untagged_data.extend(data)
 
         Args:
-            filter (viam.proto.app.data.Filter): Optional `Filter` specifying tabular data to retrieve. No `Filter` implies all binary
-                data.
+            filter (~viam.proto.app.data.Filter): Optional, specifies tabular data to retrieve. An empty filter matches all binary data.
             limit (int): The maximum number of entries to include in a page. Defaults to 50 if unspecified.
-            sort_order (viam.proto.app.data.Order): The desired sort order of the data.
+            sort_order (~viam.proto.app.data.Order): The desired sort order of the data.
             last (str): Optional string indicating the object identifier of the last-returned data.
-                        This object identifier is returned by calls to `BinaryDataByFilter` as the `last` value.
-                        If provided, the server will return the next data entries after the last object identifier.
+                This object identifier is returned by calls to :meth:`binary_data_by_filter` as the ``last`` value.
+                If provided, the server will return the next data entries after the last object identifier.
             include_binary_data (bool): Boolean specifying whether to actually include the binary file data with each retrieved file.
-                                        Defaults to true (that is, both the files' data and metadata are returned).
+                Defaults to true (that is, both the files' data and metadata are returned).
             count_only (bool): Whether to return only the total count of entries.
             include_internal_data (bool): Whether to return the internal data. Internal data is used for Viam-specific data ingestion,
-                                          like cloud SLAM. Defaults to `False`.
+                like cloud SLAM. Defaults to ``False``.
             dest (str): Optional filepath for writing retrieved data.
 
         Returns:
-            Tuple[List[viam.proto.app.data.BinaryData], int, str]: A tuple containing the following:
-            List[viam.proto.app.data.BinaryData]: The binary data,
-            int: The count (number of entries),
-            str: The last-returned page ID.
+            Tuple[List[~viam.proto.app.data.BinaryData], int, str]: A tuple containing the following:
+
+                - ``data`` (*List[* :class:`~viam.proto.app.data.BinaryData` *]*): The binary data.
+                - ``count`` (*int*): The count (number of entries).
+                - ``last`` (*str*): The last-returned page ID.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#binarydatabyfilter>`_.
         """
@@ -592,15 +789,14 @@ class DataClient:
 
     async def binary_data_by_ids(
         self,
-        binary_ids: List[BinaryID],
+        binary_ids: Union[List[BinaryID], List[str]],
+        include_binary_data: bool = True,
         dest: Optional[str] = None,
     ) -> List[BinaryData]:
         """Filter and download binary data.
 
         ::
 
-            from viam.proto.app.data import BinaryID
-
             binary_metadata, count, last = await data_client.binary_data_by_filter(
                 include_binary_data=False
             )
@@ -608,29 +804,34 @@ class DataClient:
             my_ids = []
 
             for obj in binary_metadata:
-                my_ids.append(
-                    BinaryID(
-                        file_id=obj.metadata.id,
-                        organization_id=obj.metadata.capture_metadata.organization_id,
-                        location_id=obj.metadata.capture_metadata.location_id
-                    )
-                )
+                my_ids.append(obj.metadata.binary_data_id)
 
             binary_data = await data_client.binary_data_by_ids(my_ids)
 
         Args:
-            binary_ids (List[viam.proto.app.data.BinaryID]): `BinaryID` objects specifying the desired data. Must be non-empty.
+            binary_ids (Union[List[~viam.proto.app.data.BinaryID], List[str]]): Binary data ID strings specifying the desired data or
+                :class:`BinaryID` objects. Must be non-empty.
+                *DEPRECATED:* :class:`BinaryID` *is deprecated and will be removed in a future release. Instead, pass binary data IDs as a
+                list of strings.*
+            include_binary_data (bool): Boolean specifying whether to actually include the binary file data with each retrieved file.
+                Defaults to true (that is, both the files' data and metadata are returned).
             dest (str): Optional filepath for writing retrieved data.
 
         Raises:
-            GRPCError: If no `BinaryID` objects are provided.
+            GRPCError: If no binary data ID strings or :class:`BinaryID` objects are provided.
 
         Returns:
-            List[viam.proto.app.data.BinaryData]: The binary data.
+            List[~viam.proto.app.data.BinaryData]: The binary data.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#binarydatabyids>`_.
         """
-        request = BinaryDataByIDsRequest(binary_ids=binary_ids, include_binary=True)
+        request = BinaryDataByIDsRequest()
+        if len(binary_ids) > 0 and isinstance(binary_ids[0], str):
+            binary_data_ids = cast(List[str], binary_ids)
+            request = BinaryDataByIDsRequest(binary_data_ids=binary_data_ids, include_binary=include_binary_data)
+        else:
+            bin_ids = cast(List[BinaryID], binary_ids)
+            request = BinaryDataByIDsRequest(binary_ids=bin_ids, include_binary=include_binary_data)
         response: BinaryDataByIDsResponse = await self._data_client.BinaryDataByIDs(request, metadata=self._metadata)
         if dest:
             try:
@@ -652,10 +853,10 @@ class DataClient:
             )
 
         Args:
-            organization_id (str): ID of organization to delete data from.
-                You can obtain your organization ID from the Viam app's organization settings page.
-            delete_older_than_days (int): Delete data that was captured up to this many days ago. For example if `delete_older_than_days`
-                is 10, this deletes any data that was captured up to 10 days ago. If it is 0, all existing data is deleted.
+            organization_id (str): The ID of the organization to delete the data from.
+                To find your organization ID, visit the organization settings page.
+            delete_older_than_days (int): Delete data that was captured up to *this many* days ago. For example, a value of
+                10 deletes any data that was captured up to 10 days ago. A value of 0 deletes *all* existing data.
 
         Returns:
             int: The number of items deleted.
@@ -667,7 +868,7 @@ class DataClient:
         return response.deleted_count
 
     async def delete_tabular_data_by_filter(self, filter: Optional[Filter]) -> int:
-        """Deprecated: use delete_tabular_data instead."""
+        """Deprecated: use :meth:`delete_tabular_data` instead."""
         raise NotImplementedError()
 
     async def delete_binary_data_by_filter(self, filter: Optional[Filter]) -> int:
@@ -682,9 +883,10 @@ class DataClient:
             res = await data_client.delete_binary_data_by_filter(my_filter)
 
         Args:
-            filter (viam.proto.app.data.Filter): Optional `Filter` specifying binary data to delete. Passing an empty `Filter` will lead to
-                all data being deleted. Exercise caution when using this option. You must specify an organization ID with
-                "organization_ids" when using this option.
+            filter (~viam.proto.app.data.Filter): Optional, specifies binary data to delete.
+                **CAUTION: Passing an empty** ``Filter`` **deletes all binary data!**
+                You must specify an organization ID with ``organization_ids`` when using this option.
+                To find your organization ID, visit the organization settings page.
 
         Returns:
             int: The number of items deleted.
@@ -696,7 +898,7 @@ class DataClient:
         response: DeleteBinaryDataByFilterResponse = await self._data_client.DeleteBinaryDataByFilter(request, metadata=self._metadata)
         return response.deleted_count
 
-    async def delete_binary_data_by_ids(self, binary_ids: List[BinaryID]) -> int:
+    async def delete_binary_data_by_ids(self, binary_ids: Union[List[BinaryID], List[str]]) -> int:
         """Filter and delete binary data.
 
         ::
@@ -715,36 +917,40 @@ class DataClient:
 
             for obj in binary_metadata:
                 my_ids.append(
-                    BinaryID(
-                        file_id=obj.metadata.id,
-                        organization_id=obj.metadata.capture_metadata.organization_id,
-                        location_id=obj.metadata.capture_metadata.location_id
-                    )
+                    obj.metadata.binary_data_id
                 )
 
             binary_data = await data_client.delete_binary_data_by_ids(my_ids)
 
         Args:
-            binary_ids (List[viam.proto.app.data.BinaryID]): `BinaryID` objects specifying the data to be deleted. Must be non-empty.
+            binary_ids (Union[List[~viam.proto.app.data.BinaryID], List[str]]): Binary data ID strings specifying the data to be deleted or
+                :class:`BinaryID` objects. Must be non-empty.
+                *DEPRECATED:* :class:`BinaryID` *is deprecated and will be removed in a future release. Instead, pass binary data IDs as a
+                list of strings.*
 
         Raises:
-            GRPCError: If no `BinaryID` objects are provided.
+            GRPCError: If no binary data ID strings or :class:`BinaryID` objects are provided.
 
         Returns:
             int: The number of items deleted.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#deletebinarydatabyids>`_.
         """
-        request = DeleteBinaryDataByIDsRequest(binary_ids=binary_ids)
+        request = DeleteBinaryDataByIDsRequest()
+        if len(binary_ids) > 0 and isinstance(binary_ids[0], str):
+            binary_data_ids = cast(List[str], binary_ids)
+            request = DeleteBinaryDataByIDsRequest(binary_data_ids=binary_data_ids)
+        else:
+            bin_ids = cast(List[BinaryID], binary_ids)
+            request = DeleteBinaryDataByIDsRequest(binary_ids=bin_ids)
         response: DeleteBinaryDataByIDsResponse = await self._data_client.DeleteBinaryDataByIDs(request, metadata=self._metadata)
         return response.deleted_count
 
-    async def add_tags_to_binary_data_by_ids(self, tags: List[str], binary_ids: List[BinaryID]) -> None:
+    async def add_tags_to_binary_data_by_ids(self, tags: List[str], binary_ids: Union[List[BinaryID], List[str]]) -> None:
         """Add tags to binary data.
 
         ::
 
-            from viam.proto.app.data import BinaryID
             from viam.utils import create_filter
 
             tags = ["tag1", "tag2"]
@@ -760,25 +966,30 @@ class DataClient:
 
             for obj in binary_metadata:
                 my_ids.append(
-                    BinaryID(
-                        file_id=obj.metadata.id,
-                        organization_id=obj.metadata.capture_metadata.organization_id,
-                        location_id=obj.metadata.capture_metadata.location_id
-                    )
+                    obj.metadata.binary_data_id
                 )
 
             binary_data = await data_client.add_tags_to_binary_data_by_ids(tags, my_ids)
 
         Args:
             tags (List[str]): List of tags to add to specified binary data. Must be non-empty.
-            binary_ids (List[viam.app.proto.BinaryID]): List of `BinaryID` objects specifying binary data to tag. Must be non-empty.
+            binary_ids (Union[List[~viam.proto.app.data.BinaryID], List[str]]): Binary data ID strings specifying the data to be tagged or
+                :class:`BinaryID` objects. Must be non-empty.
+                *DEPRECATED:* :class:`BinaryID` *is deprecated and will be removed in a future release. Instead, pass binary data IDs as a
+                list of strings.*
 
         Raises:
-            GRPCError: If no `BinaryID` objects or tags are provided.
+            GRPCError: If no binary data ID strings or :class:`BinaryID` objects are provided.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#addtagstobinarydatabyids>`_.
         """
-        request = AddTagsToBinaryDataByIDsRequest(binary_ids=binary_ids, tags=tags)
+        request = AddTagsToBinaryDataByIDsRequest()
+        if len(binary_ids) > 0 and isinstance(binary_ids[0], str):
+            binary_data_ids = cast(List[str], binary_ids)
+            request = AddTagsToBinaryDataByIDsRequest(binary_data_ids=binary_data_ids, tags=tags)
+        else:
+            bin_ids = cast(List[BinaryID], binary_ids)
+            request = AddTagsToBinaryDataByIDsRequest(binary_ids=bin_ids, tags=tags)
         await self._data_client.AddTagsToBinaryDataByIDs(request, metadata=self._metadata)
 
     async def add_tags_to_binary_data_by_filter(self, tags: List[str], filter: Optional[Filter] = None) -> None:
@@ -794,8 +1005,7 @@ class DataClient:
 
         Args:
             tags (List[str]): List of tags to add to specified binary data. Must be non-empty.
-            filter (viam.proto.app.data.Filter): `Filter` specifying binary data to tag. If no `Filter` is provided, all data will be
-                tagged.
+            filter (~viam.proto.app.data.Filter): Specifies binary data to tag. If none is provided, tags all data.
 
         Raises:
             GRPCError: If no tags are provided.
@@ -806,12 +1016,11 @@ class DataClient:
         request = AddTagsToBinaryDataByFilterRequest(filter=filter, tags=tags)
         await self._data_client.AddTagsToBinaryDataByFilter(request, metadata=self._metadata)
 
-    async def remove_tags_from_binary_data_by_ids(self, tags: List[str], binary_ids: List[BinaryID]) -> int:
+    async def remove_tags_from_binary_data_by_ids(self, tags: List[str], binary_ids: Union[List[BinaryID], List[str]]) -> int:
         """Remove tags from binary data by IDs.
 
         ::
 
-            from viam.proto.app.data import BinaryID
             from viam.utils import create_filter
 
             tags = ["tag1", "tag2"]
@@ -828,11 +1037,7 @@ class DataClient:
 
             for obj in binary_metadata:
                 my_ids.append(
-                    BinaryID(
-                        file_id=obj.metadata.id,
-                        organization_id=obj.metadata.capture_metadata.organization_id,
-                        location_id=obj.metadata.capture_metadata.location_id
-                    )
+                    obj.metadata.binary_data_id
                 )
 
             binary_data = await data_client.remove_tags_from_binary_data_by_ids(
@@ -840,17 +1045,26 @@ class DataClient:
 
         Args:
             tags (List[str]): List of tags to remove from specified binary data. Must be non-empty.
-            binary_ids (List[BinaryID]): List of `BinaryID` objects specifying binary data to untag. Must be non-empty.
+            binary_ids (Union[List[~viam.proto.app.data.BinaryID], List[str]]): Binary data ID strings specifying the data to be untagged
+                or `BinaryID` objects. Must be non-empty.
+                *DEPRECATED:* :class:`BinaryID` *is deprecated and will be removed in a future release. Instead, pass binary data IDs as a
+                list of strings.*
 
         Raises:
-            GRPCError: If no binary_ids or tags are provided.
+            GRPCError: If no binary data ID strings, :class:`BinaryID` objects, or tags are provided.
 
         Returns:
             int: The number of tags removed.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#removetagsfrombinarydatabyids>`_.
         """
-        request = RemoveTagsFromBinaryDataByIDsRequest(binary_ids=binary_ids, tags=tags)
+        request = RemoveTagsFromBinaryDataByIDsRequest(tags=tags)
+        if len(binary_ids) > 0 and isinstance(binary_ids[0], str):
+            binary_data_ids = cast(List[str], binary_ids)
+            request = RemoveTagsFromBinaryDataByIDsRequest(binary_data_ids=binary_data_ids, tags=tags)
+        else:
+            bin_ids = cast(List[BinaryID], binary_ids)
+            request = RemoveTagsFromBinaryDataByIDsRequest(binary_ids=bin_ids, tags=tags)
         response: RemoveTagsFromBinaryDataByIDsResponse = await self._data_client.RemoveTagsFromBinaryDataByIDs(
             request, metadata=self._metadata
         )
@@ -869,8 +1083,7 @@ class DataClient:
 
         Args:
             tags (List[str]): List of tags to remove from specified binary data.
-            filter (viam.proto.app.data.Filter): `Filter` specifying binary data to untag. If no `Filter` is provided, all data will be
-                untagged.
+            filter (~viam.proto.app.data.Filter): Specifies binary data to untag. If none is provided, removes tags from all data.
 
         Raises:
             GRPCError: If no tags are provided.
@@ -898,8 +1111,7 @@ class DataClient:
             tags = await data_client.tags_by_filter(my_filter)
 
         Args:
-            filter (viam.proto.app.data.Filter): `Filter` specifying data to retrieve from. If no `Filter` is provided, all data tags will
-                return.
+            filter (~viam.proto.app.data.Filter): Specifies subset ofdata to retrieve tags from. If none is provided, returns all tags.
 
         Returns:
             List[str]: The list of tags.
@@ -913,7 +1125,7 @@ class DataClient:
 
     async def add_bounding_box_to_image_by_id(
         self,
-        binary_id: BinaryID,
+        binary_id: Union[BinaryID, str],
         label: str,
         x_min_normalized: float,
         y_min_normalized: float,
@@ -924,16 +1136,8 @@ class DataClient:
 
         ::
 
-            from viam.proto.app.data import BinaryID
-
-            MY_BINARY_ID = BinaryID(
-                file_id="<YOUR-FILE-ID>",
-                organization_id="<YOUR-ORG-ID>",
-                location_id="<YOUR-LOCATION-ID>"
-            )
-
             bbox_id = await data_client.add_bounding_box_to_image_by_id(
-                binary_id=MY_BINARY_ID,
+                binary_id="<YOUR-BINARY-DATA-ID>",
                 label="label",
                 x_min_normalized=0,
                 y_min_normalized=.1,
@@ -944,7 +1148,9 @@ class DataClient:
             print(bbox_id)
 
         Args:
-            binary_id (viam.proto.app.data.BinaryID): The ID of the image to add the bounding box to.
+            binary_id (Union[~viam.proto.app.data.BinaryID, str]): The binary data ID or :class:`BinaryID` of the image to add the bounding
+                box to. *DEPRECATED:* :class:`BinaryID` *is deprecated and will be removed in a future release. Instead, pass binary data IDs as a
+                list of strings.*
             label (str): A label for the bounding box.
             x_min_normalized (float): Min X value of the bounding box normalized from 0 to 1.
             y_min_normalized (float): Min Y value of the bounding box normalized from 0 to 1.
@@ -959,42 +1165,53 @@ class DataClient:
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#addboundingboxtoimagebyid>`_.
         """
-        request = AddBoundingBoxToImageByIDRequest(
-            label=label,
-            binary_id=binary_id,
-            x_max_normalized=x_max_normalized,
-            x_min_normalized=x_min_normalized,
-            y_max_normalized=y_max_normalized,
-            y_min_normalized=y_min_normalized,
-        )
+        request = AddBoundingBoxToImageByIDRequest()
+        if isinstance(binary_id, str):
+            request = AddBoundingBoxToImageByIDRequest(
+                binary_data_id=binary_id,
+                label=label,
+                x_max_normalized=x_max_normalized,
+                x_min_normalized=x_min_normalized,
+                y_max_normalized=y_max_normalized,
+                y_min_normalized=y_min_normalized,
+            )
+        else:
+            request = AddBoundingBoxToImageByIDRequest(
+                binary_id=binary_id,
+                label=label,
+                x_max_normalized=x_max_normalized,
+                x_min_normalized=x_min_normalized,
+                y_max_normalized=y_max_normalized,
+                y_min_normalized=y_min_normalized,
+            )
         response: AddBoundingBoxToImageByIDResponse = await self._data_client.AddBoundingBoxToImageByID(request, metadata=self._metadata)
         return response.bbox_id
 
-    async def remove_bounding_box_from_image_by_id(self, bbox_id: str, binary_id: BinaryID) -> None:
+    async def remove_bounding_box_from_image_by_id(self, bbox_id: str, binary_id: Union[BinaryID, str]) -> None:
         """Removes a bounding box from an image.
 
         ::
 
-            from viam.proto.app.data import BinaryID
-
-            MY_BINARY_ID = BinaryID(
-                file_id=your-file_id,
-                organization_id=your-org-id,
-                location_id=your-location-id
-            )
-
             await data_client.remove_bounding_box_from_image_by_id(
-            binary_id=MY_BINARY_ID,
+            binary_id="<YOUR-BINARY-DATA-ID>",
             bbox_id="your-bounding-box-id-to-delete"
             )
 
         Args:
             bbox_id (str): The ID of the bounding box to remove.
-            binary_id (viam.proto.arr.data.BinaryID): Binary ID of the image to remove the bounding box from.
+            binary_id (Union[~viam.proto.app.data.BinaryID, str]): The binary data ID or :class:`BinaryID` of the image to remove the
+                bounding box from.
+                *DEPRECATED:* :class:`BinaryID` *is deprecated and will be removed in a future release. Instead, pass binary data IDs as a
+                list of strings.*
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#removeboundingboxfromimagebyid>`_.
         """
-        request = RemoveBoundingBoxFromImageByIDRequest(bbox_id=bbox_id, binary_id=binary_id)
+        request = RemoveBoundingBoxFromImageByIDRequest()
+        if isinstance(binary_id, str):
+            request = RemoveBoundingBoxFromImageByIDRequest(binary_data_id=binary_id, bbox_id=bbox_id)
+        else:
+            request = RemoveBoundingBoxFromImageByIDRequest(binary_id=binary_id, bbox_id=bbox_id)
+
         await self._data_client.RemoveBoundingBoxFromImageByID(request, metadata=self._metadata)
 
     async def bounding_box_labels_by_filter(self, filter: Optional[Filter] = None) -> List[str]:
@@ -1011,8 +1228,8 @@ class DataClient:
             print(bounding_box_labels)
 
         Args:
-            filter (viam.proto.app.data.Filter): `Filter` specifying data to retrieve from. If no `Filter` is provided, all labels will
-                return.
+            filter (~viam.proto.app.data.Filter): Specifies data to retrieve bounding box labels from. If none is provided, returns labels
+            from all data.
 
         Returns:
             List[str]: The list of bounding box labels.
@@ -1032,8 +1249,8 @@ class DataClient:
             hostname = await data_client.get_database_connection(organization_id="<YOUR-ORG-ID>")
 
         Args:
-            organization_id (str): Organization to retrieve the connection for.
-                You can obtain your organization ID from the Viam app's organization settings page.
+            organization_id (str): The ID of the organization you'd like to connect to.
+                To find your organization ID, visit the organization settings page.
 
         Returns:
             str: The hostname of the federated database.
@@ -1056,8 +1273,8 @@ class DataClient:
             )
 
         Args:
-            organization_id (str): The ID of the organization.
-                You can obtain your organization ID from the Viam app's organization settings page.
+            organization_id (str): The ID of the organization you'd like to configure a database user for.
+                To find your organization ID, visit the organization settings page.
             password (str): The password of the user.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#configuredatabaseuser>`_.
@@ -1079,7 +1296,7 @@ class DataClient:
         Args:
             name (str): The name of the dataset being created.
             organization_id (str): The ID of the organization where the dataset is being created.
-                You can obtain your organization ID from the Viam app's organization settings page.
+                To find your organization ID, visit the organization settings page.
 
         Returns:
             str: The dataset ID of the created dataset.
@@ -1090,6 +1307,32 @@ class DataClient:
         response: CreateDatasetResponse = await self._dataset_client.CreateDataset(request, metadata=self._metadata)
         return response.id
 
+    async def merge_datasets(self, name: str, organization_id: str, dataset_ids: List[str]) -> str:
+        """Merge multiple datasets into a new dataset.
+
+        ::
+
+            dataset_id = await data_client.merge_datasets(
+                name="<DATASET-NAME>",
+                organization_id="<YOUR-ORG-ID>",
+                dataset_ids=["<YOUR-DATASET-ID-1>", "<YOUR-DATASET-ID-2>"]
+            )
+            print(dataset_id)
+
+        Args:
+            name (str): The name of the dataset being created.
+            organization_id (str): The ID of the organization where the dataset is being created.
+                To find your organization ID, visit the organization settings page.
+            dataset_ids (List[str]): The IDs of the datasets that you would like to merge.
+        Returns:
+            str: The dataset ID of the created dataset.
+
+        For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#mergedatasets>`_.
+        """
+        request = MergeDatasetsRequest(name=name, organization_id=organization_id, dataset_ids=dataset_ids)
+        response: MergeDatasetsResponse = await self._dataset_client.MergeDatasets(request, metadata=self._metadata)
+        return response.dataset_id
+
     async def list_dataset_by_ids(self, ids: List[str]) -> Sequence[Dataset]:
         """Get a list of datasets using their IDs.
 
@@ -1101,9 +1344,12 @@ class DataClient:
             print(datasets)
 
         Args:
-            ids (List[str]): The IDs of the datasets being called for. To retrieve these IDs,
-                navigate to your dataset's page in the Viam app,
-                click **...** in the left-hand menu, and click **Copy dataset ID**.
+            ids (List[str]): The IDs of the datasets that you would like to retrieve information about. To retrieve a dataset ID:
+
+                - Navigate to the **DATASETS** tab of the **DATA** page.
+                - Click on the dataset.
+                - Click the **...** menu.
+                - Select **Copy dataset ID**.
 
         Returns:
             Sequence[Dataset]: The list of datasets.
@@ -1126,8 +1372,8 @@ class DataClient:
             print(datasets)
 
         Args:
-            organization_id (str): The ID of the organization.
-                You can obtain your organization ID from the Viam app's organization settings page.
+            organization_id (str): The ID of the organization you'd like to retrieve datasets from.
+                To find your organization ID, visit the organization settings page.
 
         Returns:
             Sequence[Dataset]: The list of datasets in the organization.
@@ -1152,8 +1398,12 @@ class DataClient:
             )
 
         Args:
-            id (str): The ID of the dataset. You can retrieve this by navigating to the **DATASETS** sub-tab of the **DATA** tab,
-                clicking on the dataset, clicking the **...** menu and selecting **Copy dataset ID**.
+            id (str): The ID of the dataset. To retrieve the dataset ID:
+
+                - Navigate to the **DATASETS** tab of the **DATA** page.
+                - Click on the dataset.
+                - Click the **...** menu.
+                - Select **Copy dataset ID**.
             name (str): The new name of the dataset.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#renamedataset>`_.
@@ -1171,92 +1421,106 @@ class DataClient:
             )
 
         Args:
-            id (str): The ID of the dataset. You can retrieve this by navigating to the **DATASETS** sub-tab of the **DATA** tab,
-                clicking on the dataset, clicking the **...** menu and selecting **Copy dataset ID**.
+            id (str): The ID of the dataset. To retrieve the dataset ID:
+
+                    - Navigate to the **DATASETS** tab of the **DATA** page.
+                    - Click on the dataset.
+                    - Click the **...** menu.
+                    - Select **Copy dataset ID**.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#deletedataset>`_.
         """
         request = DeleteDatasetRequest(id=id)
         await self._dataset_client.DeleteDataset(request, metadata=self._metadata)
 
-    async def add_binary_data_to_dataset_by_ids(self, binary_ids: List[BinaryID], dataset_id: str) -> None:
+    async def add_binary_data_to_dataset_by_ids(self, binary_ids: Union[List[BinaryID], List[str]], dataset_id: str) -> None:
         """Add the BinaryData to the provided dataset.
 
         This BinaryData will be tagged with the VIAM_DATASET_{id} label.
 
         ::
 
-            from viam.proto.app.data import BinaryID
-
             binary_metadata, count, last = await data_client.binary_data_by_filter(
                 include_binary_data=False
             )
 
-            my_binary_ids = []
+            my_binary_data_ids = []
 
             for obj in binary_metadata:
-                my_binary_ids.append(
-                    BinaryID(
-                        file_id=obj.metadata.id,
-                        organization_id=obj.metadata.capture_metadata.organization_id,
-                        location_id=obj.metadata.capture_metadata.location_id
-                        )
+                my_binary_data_ids.append(
+                    obj.metadata.binary_data_id
                     )
 
             await data_client.add_binary_data_to_dataset_by_ids(
-                binary_ids=my_binary_ids,
+                binary_ids=my_binary_data_ids,
                 dataset_id="abcd-1234xyz-8765z-123abc"
             )
 
         Args:
-            binary_ids (List[BinaryID]): The IDs of binary data to add to dataset. To retrieve these IDs,
-                navigate to your dataset's page in the Viam app,
-                click **...** in the left-hand menu, and click **Copy dataset ID**.
-            dataset_id (str): The ID of the dataset to be added to.
+            binary_ids (List[~viam.proto.app.data.BinaryID]): Unique identifiers for binary data to add to the dataset. To retrieve these IDs,
+                navigate to the DATA page, click on an image, and copy its Binary Data ID from the details tab.
+            dataset_id (str): The ID of the dataset to be added to.  To retrieve the dataset ID:
+
+                - Navigate to the **DATASETS** tab of the **DATA** page.
+                - Click on the dataset.
+                - Click the **...** menu.
+                - Select **Copy dataset ID**.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#addbinarydatatodatasetbyids>`_.
         """
-        request = AddBinaryDataToDatasetByIDsRequest(binary_ids=binary_ids, dataset_id=dataset_id)
+        request = AddBinaryDataToDatasetByIDsRequest()
+        if len(binary_ids) > 0 and isinstance(binary_ids[0], str):
+            binary_data_ids = cast(List[str], binary_ids)
+            request = AddBinaryDataToDatasetByIDsRequest(binary_data_ids=binary_data_ids, dataset_id=dataset_id)
+        else:
+            bin_ids = cast(List[BinaryID], binary_ids)
+            request = AddBinaryDataToDatasetByIDsRequest(binary_ids=bin_ids, dataset_id=dataset_id)
         await self._data_client.AddBinaryDataToDatasetByIDs(request, metadata=self._metadata)
 
-    async def remove_binary_data_from_dataset_by_ids(self, binary_ids: List[BinaryID], dataset_id: str) -> None:
+    async def remove_binary_data_from_dataset_by_ids(self, binary_ids: Union[List[BinaryID], List[str]], dataset_id: str) -> None:
         """Remove the BinaryData from the provided dataset.
 
         This BinaryData will lose the VIAM_DATASET_{id} tag.
 
         ::
 
-            from viam.proto.app.data import BinaryID
-
             binary_metadata, count, last = await data_client.binary_data_by_filter(
                 include_binary_data=False
             )
 
-            my_binary_ids = []
+            my_binary_data_ids = []
 
             for obj in binary_metadata:
-                my_binary_ids.append(
-                    BinaryID(
-                        file_id=obj.metadata.id,
-                        organization_id=obj.metadata.capture_metadata.organization_id,
-                        location_id=obj.metadata.capture_metadata.location_id
-                    )
+                my_binary_data_ids.append(
+                    obj.metadata.binary_data_id
                 )
 
             await data_client.remove_binary_data_from_dataset_by_ids(
-                binary_ids=my_binary_ids,
+                binary_ids=my_binary_data_ids,
                 dataset_id="abcd-1234xyz-8765z-123abc"
             )
 
         Args:
-            binary_ids (List[BinaryID]): The IDs of binary data to remove from dataset. To retrieve these IDs,
-                navigate to your dataset's page in the Viam app,
-                click **...** in the left-hand menu, and click **Copy dataset ID**.
-            dataset_id (str): The ID of the dataset to be removed from.
+            binary_ids (Union[List[~viam.proto.app.data.BinaryID], List[str]]): Unique identifiers for the binary data to remove from the dataset. To retrieve these IDs,
+                navigate to the DATA page, click on an image and copy its Binary Data ID from the details tab.
+                *DEPRECATED:* :class:`BinaryID` *is deprecated and will be removed in a future release. Instead, pass binary data IDs as a
+                list of strings.*
+            dataset_id (str): The ID of the dataset to be removed from. To retrieve the dataset ID:
+
+                - Navigate to the **DATASETS** tab of the **DATA** page.
+                - Click on the dataset.
+                - Click the **...** menu.
+                - Select **Copy dataset ID**.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#removebinarydatafromdatasetbyids>`_.
         """
-        request = RemoveBinaryDataFromDatasetByIDsRequest(binary_ids=binary_ids, dataset_id=dataset_id)
+        request = RemoveBinaryDataFromDatasetByIDsRequest()
+        if len(binary_ids) > 0 and isinstance(binary_ids[0], str):
+            binary_data_ids = cast(List[str], binary_ids)
+            request = RemoveBinaryDataFromDatasetByIDsRequest(binary_data_ids=binary_data_ids, dataset_id=dataset_id)
+        else:
+            bin_ids = cast(List[BinaryID], binary_ids)
+            request = RemoveBinaryDataFromDatasetByIDsRequest(binary_ids=bin_ids, dataset_id=dataset_id)
         await self._data_client.RemoveBinaryDataFromDatasetByIDs(request, metadata=self._metadata)
 
     async def binary_data_capture_upload(
@@ -1269,12 +1533,13 @@ class DataClient:
         file_extension: str,
         method_parameters: Optional[Mapping[str, Any]] = None,
         tags: Optional[List[str]] = None,
+        dataset_ids: Optional[List[str]] = None,
         data_request_times: Optional[Tuple[datetime, datetime]] = None,
     ) -> str:
         """Upload binary sensor data.
 
-        Upload binary data collected on a robot through a specific component (for example, a motor) along with the relevant metadata to
-        app.viam.com. Binary data can be found under the "Files" subtab of the Data tab on app.viam.com.
+        Upload binary data collected on a robot through a specific component (for example, a motor), along with the relevant metadata.
+        Binary data can be found on the **DATA** page.
 
         ::
 
@@ -1290,7 +1555,8 @@ class DataClient:
                 tags=["tag_1", "tag_2"],
                 data_request_times=[time_requested, time_received],
                 file_extension=".jpg",
-                binary_data=b"Encoded image bytes"
+                binary_data=b"Encoded image bytes",
+                dataset_ids=["dataset_1", "dataset_2"]
             )
 
         Args:
@@ -1299,19 +1565,20 @@ class DataClient:
             component_type (str): Type of the component used to capture the data (for example, "movement_sensor").
             component_name (str): Name of the component used to capture the data.
             method_name (str): Name of the method used to capture the data.
-            file_extension (str): The file extension of binary data including the period, for example .jpg, .png, .pcd.
-                The backend will route the binary to its corresponding mime type based on this extension. Files with a .jpeg, .jpg,
-                or .png extension will be saved to the images tab.
+            file_extension (str): The file extension of binary data, *including the period*, for example ``.jpg``, ``.png``, ``.pcd``.
+                The backend routes the binary to its corresponding mime type based on this extension. Files with a ``.jpeg``, ``.jpg``,
+                or ``.png`` extension will appear in the **Images** tab.
             method_parameters (Optional[Mapping[str, Any]]): Optional dictionary of method parameters. No longer in active use.
             tags (Optional[List[str]]): Optional list of tags to allow for tag-based data filtering when retrieving data.
+            dataset_ids (Optional[List[str]]): Optional list of datasets to add the data to.
             data_request_times (Optional[Tuple[datetime.datetime, datetime.datetime]]): Optional tuple containing datetime objects
-                denoting the times this data was requested[0] by the robot and received[1] from the appropriate sensor.
+                denoting the times this data was requested ``[0]`` by the robot and received ``[1]`` from the appropriate sensor.
 
         Raises:
             GRPCError: If an invalid part ID is passed.
 
         Returns:
-            str: The file_id of the uploaded data.
+            str: The binary data ID of the uploaded data.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#binarydatacaptureupload>`_.
         """
@@ -1335,11 +1602,12 @@ class DataClient:
             type=DataType.DATA_TYPE_BINARY_SENSOR,
             method_parameters=method_parameters,
             tags=tags,
+            dataset_ids=dataset_ids,
         )
         if file_extension:
             metadata.file_extension = file_extension if file_extension[0] == "." else f".{file_extension}"
         response = await self._data_capture_upload(metadata=metadata, sensor_contents=[sensor_contents])
-        return response.file_id
+        return response.binary_data_id
 
     async def tabular_data_capture_upload(
         self,
@@ -1354,8 +1622,8 @@ class DataClient:
     ) -> str:
         """Upload tabular sensor data.
 
-        Upload tabular data collected on a robot through a specific component (for example, a motor) along with the relevant metadata to
-        app.viam.com. Tabular data can be found under the "Sensors" subtab of the Data tab on app.viam.com.
+        Upload tabular data collected on a robot through a specific component (for example, a motor), along with the relevant metadata.
+        Tabular data can be found under the **Sensors** tab of the **DATA** page.
 
         ::
 
@@ -1380,24 +1648,24 @@ class DataClient:
 
         Args:
             tabular_data (List[Mapping[str, Any]]): List of the data to be uploaded, represented tabularly as a collection of dictionaries.
-                Must include the key "readings" for sensors.
+                Must include the key ``readings`` for sensors.
             part_id (str): Part ID of the component used to capture the data.
-            component_type (str): Type of the component used to capture the data (for example, "rdk:component:movement_sensor").
+            component_type (str): Type of the component used to capture the data (for example, ``rdk:component:movement_sensor``).
             component_name (str): Name of the component used to capture the data.
             method_name (str): Name of the method used to capture the data.
-            data_request_times (List[Tuple[datetime.datetime, datetime.datetime]]): List of tuples, each containing `datetime` objects
-                denoting the times this data was requested[0] by the robot and received[1] from the appropriate sensor. Passing a list of
-                tabular data and Timestamps with length n > 1 will result in n datapoints being uploaded, all tied to the same metadata.
+            data_request_times (List[Tuple[datetime.datetime, datetime.datetime]]): List of tuples, each containing ``datetime`` objects
+                denoting the times this data was requested ``[0]`` by the robot and received ``[1]`` from the appropriate sensor.
+                Pass a list of tabular data and timestamps with length ``n > 1`` to upload ``n`` datapoints, all with the same metadata.
             method_parameters (Optional[Mapping[str, Any]]): Optional dictionary of method parameters. No longer in active use.
             tags (Optional[List[str]]): Optional list of tags to allow for tag-based data filtering when retrieving data.
 
         Raises:
             GRPCError: If an invalid part ID is passed.
-            ValueError: If a list of `Timestamp` objects is provided and its length does not match the length of the list of tabular
+            ValueError: If the provided list of `Timestamp` objects has a length that does not match the length of the list of tabular
                 data.
 
         Returns:
-            str: The file_id of the uploaded data.
+            str: The file ID of the uploaded data.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#tabulardatacaptureupload>`_.
         """
@@ -1452,6 +1720,7 @@ class DataClient:
         method_parameters: Optional[Mapping[str, Any]] = None,
         data_request_times: Optional[Tuple[datetime, datetime]] = None,
         tags: Optional[List[str]] = None,
+        dataset_ids: Optional[List[str]] = None,
     ) -> str:
         """Uploads the metadata and contents of streaming binary data.
 
@@ -1468,26 +1737,28 @@ class DataClient:
                 component_name='left_motor',
                 method_name='IsPowered',
                 data_request_times=[time_requested, time_received],
-                tags=["tag_1", "tag_2"]
+                tags=["tag_1", "tag_2"],
+                dataset_ids=["dataset_1", "dataset_2"]
             )
 
         Args:
-            data (bytes): the data to be uploaded.
+            data (bytes): The data to be uploaded.
             part_id (str): Part ID of the resource associated with the file.
-            file_ext (str): file extension type for the data. required for determining MIME type.
+            file_ext (str): File extension type for the data. required for determining MIME type.
             component_type (Optional[str]): Optional type of the component associated with the file (for example, "movement_sensor").
             component_name (Optional[str]): Optional name of the component associated with the file.
             method_name (Optional[str]): Optional name of the method associated with the file.
             method_parameters (Optional[str]): Optional dictionary of the method parameters. No longer in active use.
             data_request_times (Optional[Tuple[datetime.datetime, datetime.datetime]]): Optional tuple containing datetime objects
-                denoting the times this data was requested[0] by the robot and received[1] from the appropriate sensor.
+                denoting the times this data was requested ``[0]`` by the robot and received ``[1]`` from the appropriate sensor.
             tags (Optional[List[str]]): Optional list of tags to allow for tag-based filtering when retrieving data.
+            dataset_ids (Optional[List[str]]): Optional list of datasets to add the data to.
 
         Raises:
             GRPCError: If an invalid part ID is passed.
 
         Returns:
-            str: The file_id of the uploaded data.
+            str: The binary data ID of the uploaded data.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#streamingdatacaptureupload>`_.
         """
@@ -1501,6 +1772,7 @@ class DataClient:
             type=DataType.DATA_TYPE_BINARY_SENSOR,
             file_extension=file_ext if file_ext[0] == "." else f".{file_ext}",
             tags=tags,
+            dataset_ids=dataset_ids,
         )
         sensor_metadata = SensorMetadata(
             time_requested=datetime_to_timestamp(data_request_times[0]) if data_request_times else None,
@@ -1516,7 +1788,7 @@ class DataClient:
             if not response:
                 await stream.recv_trailing_metadata()  # causes us to throw appropriate gRPC error
                 raise TypeError("Response cannot be empty")
-            return response.file_id
+            return response.binary_data_id
 
     async def file_upload(
         self,
@@ -1529,11 +1801,12 @@ class DataClient:
         method_parameters: Optional[Mapping[str, Any]] = None,
         file_extension: Optional[str] = None,
         tags: Optional[List[str]] = None,
+        dataset_ids: Optional[List[str]] = None,
     ) -> str:
         """Upload arbitrary file data.
 
-        Upload file data that may be stored on a robot along with the relevant metadata to app.viam.com. File data can be found under the
-        "Files" subtab of the Data tab on app.viam.com.
+        Upload file data that may be stored on a robot along with the relevant metadata. File data can be found in the
+        **Files** tab of the **DATA** page.
 
         ::
 
@@ -1542,7 +1815,8 @@ class DataClient:
                 part_id="INSERT YOUR PART ID",
                 tags=["tag_1", "tag_2"],
                 file_name="your-file",
-                file_extension=".txt"
+                file_extension=".txt",
+                dataset_ids=["dataset_1", "dataset_2"]
             )
 
         Args:
@@ -1551,18 +1825,19 @@ class DataClient:
             component_type (Optional[str]): Optional type of the component associated with the file (for example, "movement_sensor").
             component_name (Optional[str]): Optional name of the component associated with the file.
             method_name (Optional[str]): Optional name of the method associated with the file.
-            file_name (Optional[str]): Optional name of the file. The empty string "" will be assigned as the file name if one isn't
+            file_name (Optional[str]): Optional name of the file. The empty string ``""`` will be assigned as the file name if one isn't
                 provided.
             method_parameters (Optional[str]): Optional dictionary of the method parameters. No longer in active use.
-            file_extension (Optional[str]): Optional file extension. The empty string "" will be assigned as the file extension if one isn't
-                provided. Files with a .jpeg, .jpg, or .png extension will be saved to the images tab.
+            file_extension (Optional[str]): Optional file extension. The empty string ``""`` will be assigned as the file extension if one
+                isn't provided. Files with a ``.jpeg``, ``.jpg``, or ``.png`` extension will be saved to the **Images** tab.
             tags (Optional[List[str]]): Optional list of tags to allow for tag-based filtering when retrieving data.
+            dataset_ids (Optional[List[str]]): Optional list of datasets to add the data to.
 
         Raises:
             GRPCError: If an invalid part ID is passed.
 
         Returns:
-            str: ID of the new file.
+            str: Binary data ID of the new file.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#fileupload>`_.
         """
@@ -1576,9 +1851,10 @@ class DataClient:
             method_parameters=method_parameters,
             file_extension=file_extension if file_extension else "",
             tags=tags,
+            dataset_ids=dataset_ids,
         )
         response: FileUploadResponse = await self._file_upload(metadata=metadata, file_contents=FileData(data=data))
-        return response.file_id
+        return response.binary_data_id
 
     async def file_upload_from_path(
         self,
@@ -1589,17 +1865,19 @@ class DataClient:
         method_name: Optional[str] = None,
         method_parameters: Optional[Mapping[str, Any]] = None,
         tags: Optional[List[str]] = None,
+        dataset_ids: Optional[List[str]] = None,
     ) -> str:
         """Upload arbitrary file data.
 
-        Upload file data that may be stored on a robot along with the relevant metadata to app.viam.com. File data can be found under the
-        "Files" subtab of the Data tab on app.viam.com.
+        Upload file data that may be stored on a robot along with the relevant metadata. File data can be found in the
+        **Files** tab of the **DATA** page.
 
         ::
 
             file_id = await data_client.file_upload_from_path(
                 part_id="INSERT YOUR PART ID",
                 tags=["tag_1", "tag_2"],
+                dataset_ids=["dataset_1", "dataset_2"],
                 filepath="/Users/<your-username>/<your-directory>/<your-file.txt>"
             )
 
@@ -1611,23 +1889,22 @@ class DataClient:
             method_name (Optional[str]): Optional name of the method associated with the file.
             method_parameters (Optional[str]): Optional dictionary of the method parameters. No longer in active use.
             tags (Optional[List[str]]): Optional list of tags to allow for tag-based filtering when retrieving data.
-
+            dataset_ids (Optional[List[str]]): Optional list of datasets to add the data to.
 
         Raises:
             GRPCError: If an invalid part ID is passed.
             FileNotFoundError: If the provided filepath is not found.
 
         Returns:
-            str: ID of the new file.
+            str: Binary data ID of the new file.
 
         For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#fileuploadfrompath>`_.
         """
         path = Path(filepath)
         file_name = path.stem
         file_extension = path.suffix if path.suffix != "" else None
-        f = open(filepath, "rb")
-        data = f.read()
-        f.close()
+        with open(filepath, "rb") as f:
+            data = f.read()
 
         metadata = UploadMetadata(
             part_id=part_id,
@@ -1639,9 +1916,10 @@ class DataClient:
             method_parameters=method_parameters,
             file_extension=file_extension if file_extension else "",
             tags=tags,
+            dataset_ids=dataset_ids,
         )
         response: FileUploadResponse = await self._file_upload(metadata=metadata, file_contents=FileData(data=data if data else bytes()))
-        return response.file_id
+        return response.binary_data_id
 
     async def _file_upload(self, metadata: UploadMetadata, file_contents: FileData) -> FileUploadResponse:
         request_metadata = FileUploadRequest(metadata=metadata)
@@ -1656,6 +1934,265 @@ class DataClient:
                 raise TypeError("Response cannot be empty")
             return response
 
+    async def get_data_pipeline(self, id: str) -> DataPipeline:
+        """Get a data pipeline by its ID.
+
+        ::
+
+            data_pipeline = await data_client.get_data_pipeline(id="<YOUR-DATA-PIPELINE-ID>")
+
+        Args:
+            id (str): The ID of the data pipeline to get.
+
+        Returns:
+            DataPipeline: The data pipeline with the given ID.
+        """
+        request = GetDataPipelineRequest(id=id)
+        response: GetDataPipelineResponse = await self._data_pipelines_client.GetDataPipeline(request, metadata=self._metadata)
+        return DataClient.DataPipeline.from_proto(response.data_pipeline)
+
+    async def list_data_pipelines(self, organization_id: str) -> List[DataPipeline]:
+        """List all of the data pipelines for an organization.
+
+        ::
+
+            data_pipelines = await data_client.list_data_pipelines(organization_id="<YOUR-ORGANIZATION-ID>")
+
+        Args:
+            organization_id (str): The ID of the organization that owns the pipelines.
+                You can obtain your organization ID from the organization settings page.
+
+        Returns:
+            List[DataPipeline]: A list of all of the data pipelines for the given organization.
+        """
+        request = ListDataPipelinesRequest(organization_id=organization_id)
+        response: ListDataPipelinesResponse = await self._data_pipelines_client.ListDataPipelines(request, metadata=self._metadata)
+        return [DataClient.DataPipeline.from_proto(pipeline) for pipeline in response.data_pipelines]
+
+    async def create_data_pipeline(
+        self,
+        organization_id: str,
+        name: str,
+        mql_binary: List[Dict[str, Any]],
+        schedule: str,
+        enable_backfill: bool,
+        data_source_type: TabularDataSourceType.ValueType = TabularDataSourceType.TABULAR_DATA_SOURCE_TYPE_STANDARD,
+    ) -> str:
+        """Create a new data pipeline.
+
+        ::
+
+            data_pipeline_id = await data_client.create_data_pipeline(
+                organization_id="<YOUR-ORGANIZATION-ID>",
+                name="<YOUR-PIPELINE-NAME>",
+                mql_binary=[<YOUR-MQL-PIPELINE-AGGREGATION>],
+                schedule="<YOUR-SCHEDULE>",
+                enable_backfill=False,
+                data_source_type=TabularDataSourceType.TABULAR_DATA_SOURCE_TYPE_STANDARD,
+            )
+
+        Args:
+            organization_id (str): The ID of the organization that will own the pipeline.
+                You can obtain your organization ID from the organization settings page.
+            name (str): The name of the pipeline.
+            mql_binary (List[Dict[str, Any]]):The MQL pipeline to run, as a list of MongoDB aggregation pipeline stages.
+            schedule (str): A cron expression representing the expected execution schedule in UTC (note this also
+                defines the input time window; an hourly schedule would process 1 hour of data at a time).
+            enable_backfill (bool):  When true, pipeline runs will be scheduled for the organization's past data.
+            data_source_type (TabularDataSourceType): The type of data source to use for the pipeline.
+                Defaults to TabularDataSourceType.TABULAR_DATA_SOURCE_TYPE_STANDARD.
+
+        Returns:
+            str: The ID of the newly created pipeline.
+        """
+        binary: List[bytes] = [bson.encode(query) for query in mql_binary]
+        request = CreateDataPipelineRequest(
+            organization_id=organization_id,
+            name=name,
+            mql_binary=binary,
+            schedule=schedule,
+            enable_backfill=enable_backfill,
+            data_source_type=data_source_type,
+        )
+        response: CreateDataPipelineResponse = await self._data_pipelines_client.CreateDataPipeline(request, metadata=self._metadata)
+        return response.id
+
+    async def rename_data_pipeline(self, id: str, name: str) -> None:
+        """Rename a data pipeline by its ID.
+        ::
+
+            await data_client.rename_data_pipeline(id="<YOUR-DATA-PIPELINE-ID>", name="<YOUR-NEW-NAME>")
+
+        Args:
+            id (str): The ID of the data pipeline to rename.
+            name (str): The new name of the data pipeline.
+        """
+        if not id or not name:
+            raise ValueError("id and name are required")
+        request = RenameDataPipelineRequest(id=id, name=name)
+        await self._data_pipelines_client.RenameDataPipeline(request, metadata=self._metadata)
+
+    async def delete_data_pipeline(self, id: str) -> None:
+        """Delete a data pipeline by its ID.
+
+        ::
+
+            await data_client.delete_data_pipeline(id="<YOUR-DATA-PIPELINE-ID>")
+
+        Args:
+            id (str): The ID of the data pipeline to delete.
+        """
+        request = DeleteDataPipelineRequest(id=id)
+        await self._data_pipelines_client.DeleteDataPipeline(request, metadata=self._metadata)
+
+    async def list_data_pipeline_runs(self, id: str, page_size: int = 10) -> DataPipelineRunsPage:
+        """List all of the data pipeline runs for a data pipeline.
+
+        ::
+
+            data_pipeline_runs = await data_client.list_data_pipeline_runs(id="<YOUR-DATA-PIPELINE-ID>")
+            while len(data_pipeline_runs.runs) > 0:
+                data_pipeline_runs = await data_pipeline_runs.next_page()
+
+        Args:
+            id (str): The ID of the pipeline to list runs for
+            page_size (int): The number of runs to return per page. Defaults to 10.
+
+        Returns:
+            DataPipelineRunsPage: A page of data pipeline runs with pagination support
+        """
+        return await self._list_data_pipeline_runs(id, page_size)
+
+    async def _list_data_pipeline_runs(self, id: str, page_size: int, page_token: str = "") -> DataPipelineRunsPage:
+        """Internal method to list data pipeline runs with pagination.
+
+        Args:
+            id (str): The ID of the pipeline to list runs for
+            page_size (int): The number of runs to return per page
+            page_token (str): The token to use to get the next page of results
+
+        Returns:
+            DataPipelineRunsPage: A page of data pipeline runs with pagination support
+        """
+        request = ListDataPipelineRunsRequest(id=id, page_size=page_size, page_token=page_token)
+        response: ListDataPipelineRunsResponse = await self._data_pipelines_client.ListDataPipelineRuns(request, metadata=self._metadata)
+        return DataClient.DataPipelineRunsPage.from_proto(response, self, page_size)
+
+    async def create_index(
+        self,
+        organization_id: str,
+        collection_type: IndexableCollection.ValueType,
+        index_spec: Dict[str, Any],
+        pipeline_name: Optional[str] = None,
+    ) -> None:
+        """Starts a custom index build.
+
+        Args:
+            organization_id (str): The ID of the organization that owns the data.
+                To find your organization ID, visit the organization settings page.
+            collection_type (IndexableCollection.ValueType): The type of collection the index is on.
+            index_spec (List[Dict[str, Any]]): The MongoDB index specification defined in JSON format.
+            pipeline_name (Optional[str]): The name of the pipeline if the collection type is PIPELINE_SINK.
+
+        For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#createindex>`_.
+        """
+        index_spec_bytes = [bson.encode(index_spec)]
+        request = CreateIndexRequest(
+            organization_id=organization_id,
+            collection_type=collection_type,
+            index_spec=index_spec_bytes,
+            pipeline_name=pipeline_name,
+        )
+        await self._data_client.CreateIndex(request, metadata=self._metadata)
+
+    async def list_indexes(
+        self,
+        organization_id: str,
+        collection_type: IndexableCollection.ValueType,
+        pipeline_name: Optional[str] = None,
+    ) -> Sequence[Index]:
+        """Returns all the indexes for a given collection.
+
+        Args:
+            organization_id (str): The ID of the organization that owns the data.
+                To find your organization ID, visit the organization settings page.
+            collection_type (IndexableCollection.ValueType): The type of collection the index is on.
+            pipeline_name (Optional[str]): The name of the pipeline if the collection type is PIPELINE_SINK.
+
+        Returns:
+            List[Index]: A list of indexes.
+
+        For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#listindexes>`_.
+        """
+        request = ListIndexesRequest(
+            organization_id=organization_id,
+            collection_type=collection_type,
+            pipeline_name=pipeline_name,
+        )
+        response: ListIndexesResponse = await self._data_client.ListIndexes(request, metadata=self._metadata)
+        return response.indexes
+
+    async def delete_index(
+        self,
+        organization_id: str,
+        collection_type: IndexableCollection.ValueType,
+        index_name: str,
+        pipeline_name: Optional[str] = None,
+    ) -> None:
+        """Drops the specified custom index from a collection.
+
+        Args:
+            organization_id (str): The ID of the organization that owns the data.
+                To find your organization ID, visit the organization settings page.
+            collection_type (IndexableCollection.ValueType): The type of collection the index is on.
+            index_name (str): The name of the index to delete.
+            pipeline_name (Optional[str]): The name of the pipeline if the collection type is PIPELINE_SINK.
+
+        For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#deleteindex>`_.
+        """
+        request = DeleteIndexRequest(
+            organization_id=organization_id,
+            collection_type=collection_type,
+            index_name=index_name,
+            pipeline_name=pipeline_name,
+        )
+        await self._data_client.DeleteIndex(request, metadata=self._metadata)
+
+    async def create_binary_data_signed_url(
+        self,
+        binary_data_id: str,
+        expiration_minutes: Optional[int] = None,
+    ) -> Tuple[str, datetime]:
+        """Create a signed URL for binary data.
+
+        ::
+
+            signed_url, expires_at = await data_client.create_binary_data_signed_url(
+                binary_data_id="<YOUR-BINARY-DATA-ID>",
+                expiration_minutes=60
+            )
+
+            print(f"Signed URL: {signed_url}")
+            print(f"Expires at: {expires_at}")
+
+        Args:
+            binary_data_id (str): The binary data ID of the file to create a signed URL for.
+            expiration_minutes (Optional[int]): Expiration time in minutes. Defaults to 15 minutes if not specified.
+                Maximum allowed is 10080 minutes (7 days).
+
+        Returns:
+            Tuple[str, datetime]: A tuple containing:
+                - ``signed_url`` (*str*): The signed URL for the binary data file.
+                - ``expires_at`` (*datetime*): The expiration time of the signed URL token.
+
+        For more information, see `Data Client API <https://docs.viam.com/dev/reference/apis/data-client/#createbinarydatasignedurl>`_.
+        """
+        request = CreateBinaryDataSignedURLRequest(binary_data_id=binary_data_id)
+        if expiration_minutes is not None:
+            request.expiration_minutes = expiration_minutes
+        response: CreateBinaryDataSignedURLResponse = await self._data_client.CreateBinaryDataSignedURL(request, metadata=self._metadata)
+        return response.signed_url, response.expires_at.ToDatetime()
+
     @staticmethod
     def create_filter(
         component_name: Optional[str] = None,