# This file was auto-generated by Fern from our API Definition. import datetime as dt import typing from .. import core from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ..core.request_options import RequestOptions from ..types.dataset_type import DatasetType from ..types.dataset_validation_status import DatasetValidationStatus from .raw_client import AsyncRawDatasetsClient, RawDatasetsClient from .types.datasets_create_response import DatasetsCreateResponse from .types.datasets_get_response import DatasetsGetResponse from .types.datasets_get_usage_response import DatasetsGetUsageResponse from .types.datasets_list_response import DatasetsListResponse # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class DatasetsClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._raw_client = RawDatasetsClient(client_wrapper=client_wrapper) @property def with_raw_response(self) -> RawDatasetsClient: """ Retrieves a raw implementation of this client that returns raw responses. Returns ------- RawDatasetsClient """ return self._raw_client def list( self, *, dataset_type: typing.Optional[str] = None, before: typing.Optional[dt.datetime] = None, after: typing.Optional[dt.datetime] = None, limit: typing.Optional[float] = None, offset: typing.Optional[float] = None, validation_status: typing.Optional[DatasetValidationStatus] = None, request_options: typing.Optional[RequestOptions] = None, ) -> DatasetsListResponse: """ List datasets that have been created. Parameters ---------- dataset_type : typing.Optional[str] optional filter by dataset type before : typing.Optional[dt.datetime] optional filter before a date after : typing.Optional[dt.datetime] optional filter after a date limit : typing.Optional[float] optional limit to number of results offset : typing.Optional[float] optional offset to start of results validation_status : typing.Optional[DatasetValidationStatus] optional filter by validation status request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsListResponse A successful response. Examples -------- from cohere import Client client = Client( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) client.datasets.list() """ _response = self._raw_client.list( dataset_type=dataset_type, before=before, after=after, limit=limit, offset=offset, validation_status=validation_status, request_options=request_options, ) return _response.data def create( self, *, name: str, type: DatasetType, data: core.File, keep_original_file: typing.Optional[bool] = None, skip_malformed_input: typing.Optional[bool] = None, keep_fields: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None, optional_fields: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None, text_separator: typing.Optional[str] = None, csv_delimiter: typing.Optional[str] = None, eval_data: typing.Optional[core.File] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> DatasetsCreateResponse: """ Create a dataset by uploading a file. See ['Dataset Creation'](https://docs.cohere.com/docs/datasets#dataset-creation) for more information. Parameters ---------- name : str The name of the uploaded dataset. type : DatasetType The dataset type, which is used to validate the data. The only valid type is `embed-input` used in conjunction with the Embed Jobs API. data : core.File See core.File for more documentation keep_original_file : typing.Optional[bool] Indicates if the original file should be stored. skip_malformed_input : typing.Optional[bool] Indicates whether rows with malformed input should be dropped (instead of failing the validation check). Dropped rows will be returned in the warnings field. keep_fields : typing.Optional[typing.Union[str, typing.Sequence[str]]] List of names of fields that will be persisted in the Dataset. By default the Dataset will retain only the required fields indicated in the [schema for the corresponding Dataset type](https://docs.cohere.com/docs/datasets#dataset-types). For example, datasets of type `embed-input` will drop all fields other than the required `text` field. If any of the fields in `keep_fields` are missing from the uploaded file, Dataset validation will fail. optional_fields : typing.Optional[typing.Union[str, typing.Sequence[str]]] List of names of fields that will be persisted in the Dataset. By default the Dataset will retain only the required fields indicated in the [schema for the corresponding Dataset type](https://docs.cohere.com/docs/datasets#dataset-types). For example, Datasets of type `embed-input` will drop all fields other than the required `text` field. If any of the fields in `optional_fields` are missing from the uploaded file, Dataset validation will pass. text_separator : typing.Optional[str] Raw .txt uploads will be split into entries using the text_separator value. csv_delimiter : typing.Optional[str] The delimiter used for .csv uploads. eval_data : typing.Optional[core.File] See core.File for more documentation request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsCreateResponse A successful response. Examples -------- from cohere import Client client = Client( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) client.datasets.create( name="name", type="embed-input", ) """ _response = self._raw_client.create( name=name, type=type, data=data, keep_original_file=keep_original_file, skip_malformed_input=skip_malformed_input, keep_fields=keep_fields, optional_fields=optional_fields, text_separator=text_separator, csv_delimiter=csv_delimiter, eval_data=eval_data, request_options=request_options, ) return _response.data def get_usage(self, *, request_options: typing.Optional[RequestOptions] = None) -> DatasetsGetUsageResponse: """ View the dataset storage usage for your Organization. Each Organization can have up to 10GB of storage across all their users. Parameters ---------- request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsGetUsageResponse A successful response. Examples -------- from cohere import Client client = Client( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) client.datasets.get_usage() """ _response = self._raw_client.get_usage(request_options=request_options) return _response.data def get(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DatasetsGetResponse: """ Retrieve a dataset by ID. See ['Datasets'](https://docs.cohere.com/docs/datasets) for more information. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsGetResponse A successful response. Examples -------- from cohere import Client client = Client( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) client.datasets.get( id="id", ) """ _response = self._raw_client.get(id, request_options=request_options) return _response.data def delete( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> typing.Dict[str, typing.Optional[typing.Any]]: """ Delete a dataset by ID. Datasets are automatically deleted after 30 days, but they can also be deleted manually. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- typing.Dict[str, typing.Optional[typing.Any]] A successful response. Examples -------- from cohere import Client client = Client( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) client.datasets.delete( id="id", ) """ _response = self._raw_client.delete(id, request_options=request_options) return _response.data class AsyncDatasetsClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._raw_client = AsyncRawDatasetsClient(client_wrapper=client_wrapper) @property def with_raw_response(self) -> AsyncRawDatasetsClient: """ Retrieves a raw implementation of this client that returns raw responses. Returns ------- AsyncRawDatasetsClient """ return self._raw_client async def list( self, *, dataset_type: typing.Optional[str] = None, before: typing.Optional[dt.datetime] = None, after: typing.Optional[dt.datetime] = None, limit: typing.Optional[float] = None, offset: typing.Optional[float] = None, validation_status: typing.Optional[DatasetValidationStatus] = None, request_options: typing.Optional[RequestOptions] = None, ) -> DatasetsListResponse: """ List datasets that have been created. Parameters ---------- dataset_type : typing.Optional[str] optional filter by dataset type before : typing.Optional[dt.datetime] optional filter before a date after : typing.Optional[dt.datetime] optional filter after a date limit : typing.Optional[float] optional limit to number of results offset : typing.Optional[float] optional offset to start of results validation_status : typing.Optional[DatasetValidationStatus] optional filter by validation status request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsListResponse A successful response. Examples -------- import asyncio from cohere import AsyncClient client = AsyncClient( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) async def main() -> None: await client.datasets.list() asyncio.run(main()) """ _response = await self._raw_client.list( dataset_type=dataset_type, before=before, after=after, limit=limit, offset=offset, validation_status=validation_status, request_options=request_options, ) return _response.data async def create( self, *, name: str, type: DatasetType, data: core.File, keep_original_file: typing.Optional[bool] = None, skip_malformed_input: typing.Optional[bool] = None, keep_fields: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None, optional_fields: typing.Optional[typing.Union[str, typing.Sequence[str]]] = None, text_separator: typing.Optional[str] = None, csv_delimiter: typing.Optional[str] = None, eval_data: typing.Optional[core.File] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> DatasetsCreateResponse: """ Create a dataset by uploading a file. See ['Dataset Creation'](https://docs.cohere.com/docs/datasets#dataset-creation) for more information. Parameters ---------- name : str The name of the uploaded dataset. type : DatasetType The dataset type, which is used to validate the data. The only valid type is `embed-input` used in conjunction with the Embed Jobs API. data : core.File See core.File for more documentation keep_original_file : typing.Optional[bool] Indicates if the original file should be stored. skip_malformed_input : typing.Optional[bool] Indicates whether rows with malformed input should be dropped (instead of failing the validation check). Dropped rows will be returned in the warnings field. keep_fields : typing.Optional[typing.Union[str, typing.Sequence[str]]] List of names of fields that will be persisted in the Dataset. By default the Dataset will retain only the required fields indicated in the [schema for the corresponding Dataset type](https://docs.cohere.com/docs/datasets#dataset-types). For example, datasets of type `embed-input` will drop all fields other than the required `text` field. If any of the fields in `keep_fields` are missing from the uploaded file, Dataset validation will fail. optional_fields : typing.Optional[typing.Union[str, typing.Sequence[str]]] List of names of fields that will be persisted in the Dataset. By default the Dataset will retain only the required fields indicated in the [schema for the corresponding Dataset type](https://docs.cohere.com/docs/datasets#dataset-types). For example, Datasets of type `embed-input` will drop all fields other than the required `text` field. If any of the fields in `optional_fields` are missing from the uploaded file, Dataset validation will pass. text_separator : typing.Optional[str] Raw .txt uploads will be split into entries using the text_separator value. csv_delimiter : typing.Optional[str] The delimiter used for .csv uploads. eval_data : typing.Optional[core.File] See core.File for more documentation request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsCreateResponse A successful response. Examples -------- import asyncio from cohere import AsyncClient client = AsyncClient( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) async def main() -> None: await client.datasets.create( name="name", type="embed-input", ) asyncio.run(main()) """ _response = await self._raw_client.create( name=name, type=type, data=data, keep_original_file=keep_original_file, skip_malformed_input=skip_malformed_input, keep_fields=keep_fields, optional_fields=optional_fields, text_separator=text_separator, csv_delimiter=csv_delimiter, eval_data=eval_data, request_options=request_options, ) return _response.data async def get_usage(self, *, request_options: typing.Optional[RequestOptions] = None) -> DatasetsGetUsageResponse: """ View the dataset storage usage for your Organization. Each Organization can have up to 10GB of storage across all their users. Parameters ---------- request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsGetUsageResponse A successful response. Examples -------- import asyncio from cohere import AsyncClient client = AsyncClient( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) async def main() -> None: await client.datasets.get_usage() asyncio.run(main()) """ _response = await self._raw_client.get_usage(request_options=request_options) return _response.data async def get(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> DatasetsGetResponse: """ Retrieve a dataset by ID. See ['Datasets'](https://docs.cohere.com/docs/datasets) for more information. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- DatasetsGetResponse A successful response. Examples -------- import asyncio from cohere import AsyncClient client = AsyncClient( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) async def main() -> None: await client.datasets.get( id="id", ) asyncio.run(main()) """ _response = await self._raw_client.get(id, request_options=request_options) return _response.data async def delete( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> typing.Dict[str, typing.Optional[typing.Any]]: """ Delete a dataset by ID. Datasets are automatically deleted after 30 days, but they can also be deleted manually. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- typing.Dict[str, typing.Optional[typing.Any]] A successful response. Examples -------- import asyncio from cohere import AsyncClient client = AsyncClient( client_name="YOUR_CLIENT_NAME", token="YOUR_TOKEN", ) async def main() -> None: await client.datasets.delete( id="id", ) asyncio.run(main()) """ _response = await self._raw_client.delete(id, request_options=request_options) return _response.data