# This file was auto-generated by Fern from our API Definition. import contextlib import typing from json.decoder import JSONDecodeError from ..core.api_error import ApiError from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ..core.http_response import AsyncHttpResponse, HttpResponse from ..core.jsonable_encoder import jsonable_encoder from ..core.pydantic_utilities import parse_obj_as from ..core.request_options import RequestOptions from ..core.serialization import convert_and_respect_annotation_metadata from ..errors.bad_request_error import BadRequestError from ..errors.conflict_error import ConflictError from ..errors.not_found_error import NotFoundError from ..types.dataset_expansion_response import DatasetExpansionResponse from ..types.dataset_export_job_public import DatasetExportJobPublic from ..types.dataset_item_changes_public import DatasetItemChangesPublic from ..types.dataset_item_filter import DatasetItemFilter from ..types.dataset_item_page_compare import DatasetItemPageCompare from ..types.dataset_item_page_public import DatasetItemPagePublic from ..types.dataset_item_public import DatasetItemPublic from ..types.dataset_item_update import DatasetItemUpdate from ..types.dataset_item_write import DatasetItemWrite from ..types.dataset_item_write_source import DatasetItemWriteSource from ..types.dataset_page_public import DatasetPagePublic from ..types.dataset_public import DatasetPublic from ..types.dataset_version_diff import DatasetVersionDiff from ..types.dataset_version_page_public import DatasetVersionPagePublic from ..types.dataset_version_public import DatasetVersionPublic from ..types.evaluator_item_write import EvaluatorItemWrite from ..types.execution_policy_write import ExecutionPolicyWrite from ..types.json_node import JsonNode from ..types.page_columns import PageColumns from ..types.project_stats_public import ProjectStatsPublic from ..types.span_enrichment_options import SpanEnrichmentOptions from ..types.trace_enrichment_options import TraceEnrichmentOptions from .types.dataset_update_visibility import DatasetUpdateVisibility from .types.dataset_write_type import DatasetWriteType from .types.dataset_write_visibility import DatasetWriteVisibility # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class RawDatasetsClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper def apply_dataset_item_changes( self, id: str, *, request: DatasetItemChangesPublic, override: typing.Optional[bool] = None, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetVersionPublic]: """ Apply delta changes (add, edit, delete) to a dataset version with conflict detection. This endpoint: - Creates a new version with the applied changes - Validates that baseVersion matches the latest version (unless override=true) - Returns 409 Conflict if baseVersion is stale and override is not set Use `override=true` query parameter to force version creation even with stale baseVersion. Parameters ---------- id : str request : DatasetItemChangesPublic override : typing.Optional[bool] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetVersionPublic] Version created successfully """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/changes", method="POST", params={ "override": override, }, json=request, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 409: raise ConflictError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def batch_update_dataset_items( self, *, update: DatasetItemUpdate, ids: typing.Optional[typing.Sequence[str]] = OMIT, filters: typing.Optional[typing.Sequence[DatasetItemFilter]] = OMIT, dataset_id: typing.Optional[str] = OMIT, merge_tags: typing.Optional[bool] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Update multiple dataset items Parameters ---------- update : DatasetItemUpdate ids : typing.Optional[typing.Sequence[str]] List of dataset item IDs to update (max 1000). Mutually exclusive with 'filters'. filters : typing.Optional[typing.Sequence[DatasetItemFilter]] dataset_id : typing.Optional[str] Dataset ID. Required when using 'filters', optional when using 'ids'. merge_tags : typing.Optional[bool] If true, merge tags with existing tags instead of replacing them. Default: false. When using 'filters', this is automatically set to true. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/items/batch", method="PATCH", json={ "ids": ids, "filters": convert_and_respect_annotation_metadata( object_=filters, annotation=typing.Sequence[DatasetItemFilter], direction="write" ), "dataset_id": dataset_id, "update": convert_and_respect_annotation_metadata( object_=update, annotation=DatasetItemUpdate, direction="write" ), "merge_tags": merge_tags, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def find_datasets( self, *, page: typing.Optional[int] = None, size: typing.Optional[int] = None, with_experiments_only: typing.Optional[bool] = None, with_optimizations_only: typing.Optional[bool] = None, prompt_id: typing.Optional[str] = None, project_id: typing.Optional[str] = None, name: typing.Optional[str] = None, sorting: typing.Optional[str] = None, filters: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetPagePublic]: """ Find datasets Parameters ---------- page : typing.Optional[int] size : typing.Optional[int] with_experiments_only : typing.Optional[bool] with_optimizations_only : typing.Optional[bool] prompt_id : typing.Optional[str] project_id : typing.Optional[str] name : typing.Optional[str] sorting : typing.Optional[str] filters : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetPagePublic] Dataset resource """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets", method="GET", params={ "page": page, "size": size, "with_experiments_only": with_experiments_only, "with_optimizations_only": with_optimizations_only, "prompt_id": prompt_id, "project_id": project_id, "name": name, "sorting": sorting, "filters": filters, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetPagePublic, parse_obj_as( type_=DatasetPagePublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def create_dataset( self, *, name: str, id: typing.Optional[str] = OMIT, project_id: typing.Optional[str] = OMIT, project_name: typing.Optional[str] = OMIT, type: typing.Optional[DatasetWriteType] = OMIT, visibility: typing.Optional[DatasetWriteVisibility] = OMIT, tags: typing.Optional[typing.Sequence[str]] = OMIT, description: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Create dataset Parameters ---------- name : str id : typing.Optional[str] project_id : typing.Optional[str] Project ID. Takes precedence over project_name when both are provided. project_name : typing.Optional[str] For project scope, specify either project_id or project_name. If project_name is provided and the project does not exist, it will be created. Ignored when project_id is provided. If neither is provided, the dataset is created at workspace level. type : typing.Optional[DatasetWriteType] visibility : typing.Optional[DatasetWriteVisibility] tags : typing.Optional[typing.Sequence[str]] description : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets", method="POST", json={ "id": id, "name": name, "project_id": project_id, "project_name": project_name, "type": type, "visibility": visibility, "tags": tags, "description": description, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def create_or_update_dataset_items( self, *, items: typing.Sequence[DatasetItemWrite], dataset_name: typing.Optional[str] = OMIT, dataset_id: typing.Optional[str] = OMIT, batch_group_id: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Create/update dataset items based on dataset item id Parameters ---------- items : typing.Sequence[DatasetItemWrite] dataset_name : typing.Optional[str] If null, dataset_id must be provided dataset_id : typing.Optional[str] If null, dataset_name must be provided batch_group_id : typing.Optional[str] Optional batch group ID to group multiple batches into a single dataset version. If null, mutates the latest version instead of creating a new one. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/items", method="PUT", json={ "dataset_name": dataset_name, "dataset_id": dataset_id, "items": convert_and_respect_annotation_metadata( object_=items, annotation=typing.Sequence[DatasetItemWrite], direction="write" ), "batch_group_id": batch_group_id, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def create_dataset_items_from_csv( self, *, file: typing.Dict[str, typing.Optional[typing.Any]], dataset_id: str, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Create dataset items from uploaded CSV file. CSV should have headers in the first row. Processing happens asynchronously in batches. Parameters ---------- file : typing.Dict[str, typing.Optional[typing.Any]] dataset_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/items/from-csv", method="POST", data={ "file": file, "dataset_id": dataset_id, }, files={}, headers={ "content-type": "multipart/form-data", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def create_dataset_items_from_spans( self, dataset_id: str, *, span_ids: typing.Sequence[str], enrichment_options: SpanEnrichmentOptions, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Create dataset items from spans with enriched metadata Parameters ---------- dataset_id : str span_ids : typing.Sequence[str] Set of span IDs to add to the dataset enrichment_options : SpanEnrichmentOptions request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(dataset_id)}/items/from-spans", method="POST", json={ "span_ids": span_ids, "enrichment_options": convert_and_respect_annotation_metadata( object_=enrichment_options, annotation=SpanEnrichmentOptions, direction="write" ), }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def create_dataset_items_from_traces( self, dataset_id: str, *, trace_ids: typing.Sequence[str], enrichment_options: TraceEnrichmentOptions, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Create dataset items from traces with enriched metadata Parameters ---------- dataset_id : str trace_ids : typing.Sequence[str] Set of trace IDs to add to the dataset enrichment_options : TraceEnrichmentOptions request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(dataset_id)}/items/from-traces", method="POST", json={ "trace_ids": trace_ids, "enrichment_options": convert_and_respect_annotation_metadata( object_=enrichment_options, annotation=TraceEnrichmentOptions, direction="write" ), }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_by_id( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[DatasetPublic]: """ Get dataset by id Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetPublic] Dataset resource """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetPublic, parse_obj_as( type_=DatasetPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def update_dataset( self, id: str, *, name: str, description: typing.Optional[str] = OMIT, visibility: typing.Optional[DatasetUpdateVisibility] = OMIT, tags: typing.Optional[typing.Sequence[str]] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Update dataset by id Parameters ---------- id : str name : str description : typing.Optional[str] visibility : typing.Optional[DatasetUpdateVisibility] tags : typing.Optional[typing.Sequence[str]] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}", method="PUT", json={ "name": name, "description": description, "visibility": visibility, "tags": tags, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def delete_dataset(self, id: str, *, request_options: typing.Optional[RequestOptions] = None) -> HttpResponse[None]: """ Delete dataset by id Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}", method="DELETE", request_options=request_options, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def delete_dataset_by_name( self, *, dataset_name: str, project_name: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Delete dataset by name Parameters ---------- dataset_name : str project_name : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/delete", method="POST", json={ "dataset_name": dataset_name, "project_name": project_name, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def delete_dataset_items( self, *, item_ids: typing.Optional[typing.Sequence[str]] = OMIT, dataset_id: typing.Optional[str] = OMIT, filters: typing.Optional[typing.Sequence[DatasetItemFilter]] = OMIT, batch_group_id: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Delete dataset items using one of two modes: 1. **Delete by IDs**: Provide 'item_ids' to delete specific items by their IDs 2. **Delete by filters**: Provide 'dataset_id' with optional 'filters' to delete items matching criteria When using filters, an empty 'filters' array will delete all items in the specified dataset. Parameters ---------- item_ids : typing.Optional[typing.Sequence[str]] List of dataset item IDs to delete (max 1000). Use this to delete specific items by their IDs. Mutually exclusive with 'dataset_id' and 'filters'. dataset_id : typing.Optional[str] Dataset ID to scope the deletion. Required when using 'filters'. Mutually exclusive with 'item_ids'. filters : typing.Optional[typing.Sequence[DatasetItemFilter]] Filters to select dataset items to delete within the specified dataset. Must be used with 'dataset_id'. Mutually exclusive with 'item_ids'. Empty array means 'delete all items in the dataset'. batch_group_id : typing.Optional[str] Optional batch group ID to group multiple delete operations into a single dataset version. If null, mutates the latest version instead of creating a new one. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/items/delete", method="POST", json={ "item_ids": item_ids, "dataset_id": dataset_id, "filters": convert_and_respect_annotation_metadata( object_=filters, annotation=typing.Sequence[DatasetItemFilter], direction="write" ), "batch_group_id": batch_group_id, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def delete_datasets_batch( self, *, ids: typing.Sequence[str], request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[None]: """ Delete datasets batch Parameters ---------- ids : typing.Sequence[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/delete-batch", method="POST", json={ "ids": ids, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) @contextlib.contextmanager def download_dataset_export( self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> typing.Iterator[HttpResponse[typing.Iterator[bytes]]]: """ Downloads the exported CSV file for a completed export job. This endpoint proxies the file download to avoid exposing internal storage URLs. Parameters ---------- job_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Returns ------- typing.Iterator[HttpResponse[typing.Iterator[bytes]]] CSV file content """ with self._client_wrapper.httpx_client.stream( f"v1/private/datasets/export-jobs/{jsonable_encoder(job_id)}/download", method="GET", request_options=request_options, ) as _response: def stream() -> HttpResponse[typing.Iterator[bytes]]: try: if 200 <= _response.status_code < 300: _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None return HttpResponse( response=_response, data=(_chunk for _chunk in _response.iter_bytes(chunk_size=_chunk_size)) ) _response.read() if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError( status_code=_response.status_code, headers=dict(_response.headers), body=_response.text ) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) yield stream() def expand_dataset( self, id: str, *, model: str, sample_count: typing.Optional[int] = OMIT, preserve_fields: typing.Optional[typing.Sequence[str]] = OMIT, variation_instructions: typing.Optional[str] = OMIT, custom_prompt: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetExpansionResponse]: """ Generate synthetic dataset samples using LLM based on existing data patterns Parameters ---------- id : str model : str The model to use for synthetic data generation sample_count : typing.Optional[int] Number of synthetic samples to generate preserve_fields : typing.Optional[typing.Sequence[str]] Fields to preserve patterns from original data variation_instructions : typing.Optional[str] Additional instructions for data variation custom_prompt : typing.Optional[str] Custom prompt to use for generation instead of auto-generated one request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetExpansionResponse] Generated synthetic samples """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/expansions", method="POST", json={ "model": model, "sample_count": sample_count, "preserve_fields": preserve_fields, "variation_instructions": variation_instructions, "custom_prompt": custom_prompt, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetExpansionResponse, parse_obj_as( type_=DatasetExpansionResponse, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def find_dataset_items_with_experiment_items( self, id: str, *, experiment_ids: str, page: typing.Optional[int] = None, size: typing.Optional[int] = None, filters: typing.Optional[str] = None, sorting: typing.Optional[str] = None, search: typing.Optional[str] = None, truncate: typing.Optional[bool] = None, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetItemPageCompare]: """ Find dataset items with experiment items Parameters ---------- id : str experiment_ids : str page : typing.Optional[int] size : typing.Optional[int] filters : typing.Optional[str] sorting : typing.Optional[str] search : typing.Optional[str] truncate : typing.Optional[bool] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetItemPageCompare] Dataset item resource """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/experiments/items", method="GET", params={ "page": page, "size": size, "experiment_ids": experiment_ids, "filters": filters, "sorting": sorting, "search": search, "truncate": truncate, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetItemPageCompare, parse_obj_as( type_=DatasetItemPageCompare, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_by_identifier( self, *, dataset_name: str, project_name: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetPublic]: """ Get dataset by name Parameters ---------- dataset_name : str project_name : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetPublic] Dataset resource """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/retrieve", method="POST", json={ "dataset_name": dataset_name, "project_name": project_name, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetPublic, parse_obj_as( type_=DatasetPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_experiment_items_stats( self, id: str, *, experiment_ids: str, filters: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[ProjectStatsPublic]: """ Get experiment items stats for dataset Parameters ---------- id : str experiment_ids : str filters : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[ProjectStatsPublic] Experiment items stats resource """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/experiments/items/stats", method="GET", params={ "experiment_ids": experiment_ids, "filters": filters, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( ProjectStatsPublic, parse_obj_as( type_=ProjectStatsPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_export_job( self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[DatasetExportJobPublic]: """ Retrieves the current status of a dataset export job Parameters ---------- job_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetExportJobPublic] Export job details """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/export-jobs/{jsonable_encoder(job_id)}", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetExportJobPublic, parse_obj_as( type_=DatasetExportJobPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_export_jobs( self, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[typing.List[DatasetExportJobPublic]]: """ Retrieves all export jobs for the workspace. This is used to restore the export panel state after page refresh. Parameters ---------- request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[typing.List[DatasetExportJobPublic]] List of export jobs """ _response = self._client_wrapper.httpx_client.request( "v1/private/datasets/export-jobs", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( typing.List[DatasetExportJobPublic], parse_obj_as( type_=typing.List[DatasetExportJobPublic], # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_item_by_id( self, item_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[DatasetItemPublic]: """ Get dataset item by id Parameters ---------- item_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetItemPublic] Dataset item resource """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/items/{jsonable_encoder(item_id)}", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetItemPublic, parse_obj_as( type_=DatasetItemPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def patch_dataset_item( self, item_id: str, *, source: DatasetItemWriteSource, data: JsonNode, id: typing.Optional[str] = OMIT, trace_id: typing.Optional[str] = OMIT, span_id: typing.Optional[str] = OMIT, description: typing.Optional[str] = OMIT, tags: typing.Optional[typing.Sequence[str]] = OMIT, evaluators: typing.Optional[typing.Sequence[EvaluatorItemWrite]] = OMIT, execution_policy: typing.Optional[ExecutionPolicyWrite] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[None]: """ Partially update dataset item by id. Only provided fields will be updated. Parameters ---------- item_id : str source : DatasetItemWriteSource data : JsonNode id : typing.Optional[str] trace_id : typing.Optional[str] span_id : typing.Optional[str] description : typing.Optional[str] tags : typing.Optional[typing.Sequence[str]] evaluators : typing.Optional[typing.Sequence[EvaluatorItemWrite]] execution_policy : typing.Optional[ExecutionPolicyWrite] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/items/{jsonable_encoder(item_id)}", method="PATCH", json={ "id": id, "trace_id": trace_id, "span_id": span_id, "source": source, "data": data, "description": description, "tags": tags, "evaluators": convert_and_respect_annotation_metadata( object_=evaluators, annotation=typing.Sequence[EvaluatorItemWrite], direction="write" ), "execution_policy": convert_and_respect_annotation_metadata( object_=execution_policy, annotation=ExecutionPolicyWrite, direction="write" ), }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_items( self, id: str, *, page: typing.Optional[int] = None, size: typing.Optional[int] = None, version: typing.Optional[str] = None, filters: typing.Optional[str] = None, truncate: typing.Optional[bool] = None, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetItemPagePublic]: """ Get dataset items Parameters ---------- id : str page : typing.Optional[int] size : typing.Optional[int] version : typing.Optional[str] filters : typing.Optional[str] truncate : typing.Optional[bool] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetItemPagePublic] Dataset items resource """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items", method="GET", params={ "page": page, "size": size, "version": version, "filters": filters, "truncate": truncate, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetItemPagePublic, parse_obj_as( type_=DatasetItemPagePublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def get_dataset_items_output_columns( self, id: str, *, experiment_ids: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[PageColumns]: """ Get dataset items output columns Parameters ---------- id : str experiment_ids : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[PageColumns] Dataset item output columns """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/experiments/items/output/columns", method="GET", params={ "experiment_ids": experiment_ids, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( PageColumns, parse_obj_as( type_=PageColumns, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def mark_dataset_export_job_viewed( self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[None]: """ Marks a dataset export job as viewed by setting the viewed_at timestamp. This is used to track that a user has seen a failed job's error message. This operation is idempotent. Parameters ---------- job_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/export-jobs/{jsonable_encoder(job_id)}/mark-viewed", method="PUT", request_options=request_options, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def start_dataset_export( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[DatasetExportJobPublic]: """ Initiates an asynchronous CSV export job for the dataset. Returns immediately with job details for polling. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetExportJobPublic] Existing export job in progress """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/export", method="POST", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetExportJobPublic, parse_obj_as( type_=DatasetExportJobPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) @contextlib.contextmanager def stream_dataset_items( self, *, dataset_name: str, last_retrieved_id: typing.Optional[str] = OMIT, steam_limit: typing.Optional[int] = OMIT, dataset_version: typing.Optional[str] = OMIT, project_name: typing.Optional[str] = OMIT, filters: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> typing.Iterator[HttpResponse[typing.Iterator[bytes]]]: """ Stream dataset items Parameters ---------- dataset_name : str last_retrieved_id : typing.Optional[str] steam_limit : typing.Optional[int] dataset_version : typing.Optional[str] project_name : typing.Optional[str] filters : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Returns ------- typing.Iterator[HttpResponse[typing.Iterator[bytes]]] Dataset items stream or error during process """ with self._client_wrapper.httpx_client.stream( "v1/private/datasets/items/stream", method="POST", json={ "dataset_name": dataset_name, "last_retrieved_id": last_retrieved_id, "steam_limit": steam_limit, "dataset_version": dataset_version, "project_name": project_name, "filters": filters, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) as _response: def stream() -> HttpResponse[typing.Iterator[bytes]]: try: if 200 <= _response.status_code < 300: _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None return HttpResponse( response=_response, data=(_chunk for _chunk in _response.iter_bytes(chunk_size=_chunk_size)) ) _response.read() _response_json = _response.json() except JSONDecodeError: raise ApiError( status_code=_response.status_code, headers=dict(_response.headers), body=_response.text ) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) yield stream() def compare_dataset_versions( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[DatasetVersionDiff]: """ Compare the latest committed dataset version with the current draft state. This endpoint provides insights into changes made since the last version was committed. The comparison calculates additions, modifications, deletions, and unchanged items between the latest version snapshot and current draft. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetVersionDiff] Diff computed successfully """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/diff", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionDiff, parse_obj_as( type_=DatasetVersionDiff, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def create_version_tag( self, id: str, version_hash: str, *, tag: str, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[None]: """ Add a tag to a specific dataset version for easy reference (e.g., 'baseline', 'v1.0', 'production') Parameters ---------- id : str version_hash : str tag : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/hash/{jsonable_encoder(version_hash)}/tags", method="POST", json={ "tag": tag, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 409: raise ConflictError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def delete_version_tag( self, id: str, version_hash: str, tag: str, *, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[None]: """ Remove a tag from a dataset version. The version itself is not deleted, only the tag reference. Parameters ---------- id : str version_hash : str tag : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[None] """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/{jsonable_encoder(version_hash)}/tags/{jsonable_encoder(tag)}", method="DELETE", request_options=request_options, ) try: if 200 <= _response.status_code < 300: return HttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def list_dataset_versions( self, id: str, *, page: typing.Optional[int] = None, size: typing.Optional[int] = None, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetVersionPagePublic]: """ Get paginated list of versions for a dataset, ordered by creation time (newest first) Parameters ---------- id : str page : typing.Optional[int] size : typing.Optional[int] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetVersionPagePublic] Dataset versions """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions", method="GET", params={ "page": page, "size": size, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPagePublic, parse_obj_as( type_=DatasetVersionPagePublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def restore_dataset_version( self, id: str, *, version_ref: str, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[DatasetVersionPublic]: """ Restores the dataset to a previous version state by creating a new version with items copied from the specified version. If the version is already the latest, returns it as-is (no-op). Parameters ---------- id : str version_ref : str Version hash or tag to restore from request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetVersionPublic] Version restored successfully """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/restore", method="POST", json={ "version_ref": version_ref, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def retrieve_dataset_version( self, id: str, *, version_name: str, request_options: typing.Optional[RequestOptions] = None ) -> HttpResponse[DatasetVersionPublic]: """ Get a specific version by its version name (e.g., 'v1', 'v373'). This is more efficient than paginating through all versions for large datasets. Parameters ---------- id : str version_name : str Version name in format 'vN' (e.g., 'v1', 'v373') request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetVersionPublic] Dataset version """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/retrieve", method="POST", json={ "version_name": version_name, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def update_dataset_version( self, id: str, version_hash: str, *, change_description: typing.Optional[str] = OMIT, tags_to_add: typing.Optional[typing.Sequence[str]] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[DatasetVersionPublic]: """ Update a dataset version's change_description and/or add new tags Parameters ---------- id : str version_hash : str change_description : typing.Optional[str] Optional description of changes in this version tags_to_add : typing.Optional[typing.Sequence[str]] Optional list of tags to add to this version request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[DatasetVersionPublic] Version updated successfully """ _response = self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/hash/{jsonable_encoder(version_hash)}", method="PATCH", json={ "change_description": change_description, "tags_to_add": tags_to_add, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 409: raise ConflictError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) class AsyncRawDatasetsClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper async def apply_dataset_item_changes( self, id: str, *, request: DatasetItemChangesPublic, override: typing.Optional[bool] = None, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetVersionPublic]: """ Apply delta changes (add, edit, delete) to a dataset version with conflict detection. This endpoint: - Creates a new version with the applied changes - Validates that baseVersion matches the latest version (unless override=true) - Returns 409 Conflict if baseVersion is stale and override is not set Use `override=true` query parameter to force version creation even with stale baseVersion. Parameters ---------- id : str request : DatasetItemChangesPublic override : typing.Optional[bool] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetVersionPublic] Version created successfully """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/changes", method="POST", params={ "override": override, }, json=request, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 409: raise ConflictError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def batch_update_dataset_items( self, *, update: DatasetItemUpdate, ids: typing.Optional[typing.Sequence[str]] = OMIT, filters: typing.Optional[typing.Sequence[DatasetItemFilter]] = OMIT, dataset_id: typing.Optional[str] = OMIT, merge_tags: typing.Optional[bool] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Update multiple dataset items Parameters ---------- update : DatasetItemUpdate ids : typing.Optional[typing.Sequence[str]] List of dataset item IDs to update (max 1000). Mutually exclusive with 'filters'. filters : typing.Optional[typing.Sequence[DatasetItemFilter]] dataset_id : typing.Optional[str] Dataset ID. Required when using 'filters', optional when using 'ids'. merge_tags : typing.Optional[bool] If true, merge tags with existing tags instead of replacing them. Default: false. When using 'filters', this is automatically set to true. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/items/batch", method="PATCH", json={ "ids": ids, "filters": convert_and_respect_annotation_metadata( object_=filters, annotation=typing.Sequence[DatasetItemFilter], direction="write" ), "dataset_id": dataset_id, "update": convert_and_respect_annotation_metadata( object_=update, annotation=DatasetItemUpdate, direction="write" ), "merge_tags": merge_tags, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def find_datasets( self, *, page: typing.Optional[int] = None, size: typing.Optional[int] = None, with_experiments_only: typing.Optional[bool] = None, with_optimizations_only: typing.Optional[bool] = None, prompt_id: typing.Optional[str] = None, project_id: typing.Optional[str] = None, name: typing.Optional[str] = None, sorting: typing.Optional[str] = None, filters: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetPagePublic]: """ Find datasets Parameters ---------- page : typing.Optional[int] size : typing.Optional[int] with_experiments_only : typing.Optional[bool] with_optimizations_only : typing.Optional[bool] prompt_id : typing.Optional[str] project_id : typing.Optional[str] name : typing.Optional[str] sorting : typing.Optional[str] filters : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetPagePublic] Dataset resource """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets", method="GET", params={ "page": page, "size": size, "with_experiments_only": with_experiments_only, "with_optimizations_only": with_optimizations_only, "prompt_id": prompt_id, "project_id": project_id, "name": name, "sorting": sorting, "filters": filters, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetPagePublic, parse_obj_as( type_=DatasetPagePublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def create_dataset( self, *, name: str, id: typing.Optional[str] = OMIT, project_id: typing.Optional[str] = OMIT, project_name: typing.Optional[str] = OMIT, type: typing.Optional[DatasetWriteType] = OMIT, visibility: typing.Optional[DatasetWriteVisibility] = OMIT, tags: typing.Optional[typing.Sequence[str]] = OMIT, description: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Create dataset Parameters ---------- name : str id : typing.Optional[str] project_id : typing.Optional[str] Project ID. Takes precedence over project_name when both are provided. project_name : typing.Optional[str] For project scope, specify either project_id or project_name. If project_name is provided and the project does not exist, it will be created. Ignored when project_id is provided. If neither is provided, the dataset is created at workspace level. type : typing.Optional[DatasetWriteType] visibility : typing.Optional[DatasetWriteVisibility] tags : typing.Optional[typing.Sequence[str]] description : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets", method="POST", json={ "id": id, "name": name, "project_id": project_id, "project_name": project_name, "type": type, "visibility": visibility, "tags": tags, "description": description, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def create_or_update_dataset_items( self, *, items: typing.Sequence[DatasetItemWrite], dataset_name: typing.Optional[str] = OMIT, dataset_id: typing.Optional[str] = OMIT, batch_group_id: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Create/update dataset items based on dataset item id Parameters ---------- items : typing.Sequence[DatasetItemWrite] dataset_name : typing.Optional[str] If null, dataset_id must be provided dataset_id : typing.Optional[str] If null, dataset_name must be provided batch_group_id : typing.Optional[str] Optional batch group ID to group multiple batches into a single dataset version. If null, mutates the latest version instead of creating a new one. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/items", method="PUT", json={ "dataset_name": dataset_name, "dataset_id": dataset_id, "items": convert_and_respect_annotation_metadata( object_=items, annotation=typing.Sequence[DatasetItemWrite], direction="write" ), "batch_group_id": batch_group_id, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def create_dataset_items_from_csv( self, *, file: typing.Dict[str, typing.Optional[typing.Any]], dataset_id: str, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Create dataset items from uploaded CSV file. CSV should have headers in the first row. Processing happens asynchronously in batches. Parameters ---------- file : typing.Dict[str, typing.Optional[typing.Any]] dataset_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/items/from-csv", method="POST", data={ "file": file, "dataset_id": dataset_id, }, files={}, headers={ "content-type": "multipart/form-data", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def create_dataset_items_from_spans( self, dataset_id: str, *, span_ids: typing.Sequence[str], enrichment_options: SpanEnrichmentOptions, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Create dataset items from spans with enriched metadata Parameters ---------- dataset_id : str span_ids : typing.Sequence[str] Set of span IDs to add to the dataset enrichment_options : SpanEnrichmentOptions request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(dataset_id)}/items/from-spans", method="POST", json={ "span_ids": span_ids, "enrichment_options": convert_and_respect_annotation_metadata( object_=enrichment_options, annotation=SpanEnrichmentOptions, direction="write" ), }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def create_dataset_items_from_traces( self, dataset_id: str, *, trace_ids: typing.Sequence[str], enrichment_options: TraceEnrichmentOptions, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Create dataset items from traces with enriched metadata Parameters ---------- dataset_id : str trace_ids : typing.Sequence[str] Set of trace IDs to add to the dataset enrichment_options : TraceEnrichmentOptions request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(dataset_id)}/items/from-traces", method="POST", json={ "trace_ids": trace_ids, "enrichment_options": convert_and_respect_annotation_metadata( object_=enrichment_options, annotation=TraceEnrichmentOptions, direction="write" ), }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_by_id( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[DatasetPublic]: """ Get dataset by id Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetPublic] Dataset resource """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetPublic, parse_obj_as( type_=DatasetPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def update_dataset( self, id: str, *, name: str, description: typing.Optional[str] = OMIT, visibility: typing.Optional[DatasetUpdateVisibility] = OMIT, tags: typing.Optional[typing.Sequence[str]] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Update dataset by id Parameters ---------- id : str name : str description : typing.Optional[str] visibility : typing.Optional[DatasetUpdateVisibility] tags : typing.Optional[typing.Sequence[str]] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}", method="PUT", json={ "name": name, "description": description, "visibility": visibility, "tags": tags, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def delete_dataset( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[None]: """ Delete dataset by id Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}", method="DELETE", request_options=request_options, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def delete_dataset_by_name( self, *, dataset_name: str, project_name: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Delete dataset by name Parameters ---------- dataset_name : str project_name : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/delete", method="POST", json={ "dataset_name": dataset_name, "project_name": project_name, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def delete_dataset_items( self, *, item_ids: typing.Optional[typing.Sequence[str]] = OMIT, dataset_id: typing.Optional[str] = OMIT, filters: typing.Optional[typing.Sequence[DatasetItemFilter]] = OMIT, batch_group_id: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Delete dataset items using one of two modes: 1. **Delete by IDs**: Provide 'item_ids' to delete specific items by their IDs 2. **Delete by filters**: Provide 'dataset_id' with optional 'filters' to delete items matching criteria When using filters, an empty 'filters' array will delete all items in the specified dataset. Parameters ---------- item_ids : typing.Optional[typing.Sequence[str]] List of dataset item IDs to delete (max 1000). Use this to delete specific items by their IDs. Mutually exclusive with 'dataset_id' and 'filters'. dataset_id : typing.Optional[str] Dataset ID to scope the deletion. Required when using 'filters'. Mutually exclusive with 'item_ids'. filters : typing.Optional[typing.Sequence[DatasetItemFilter]] Filters to select dataset items to delete within the specified dataset. Must be used with 'dataset_id'. Mutually exclusive with 'item_ids'. Empty array means 'delete all items in the dataset'. batch_group_id : typing.Optional[str] Optional batch group ID to group multiple delete operations into a single dataset version. If null, mutates the latest version instead of creating a new one. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/items/delete", method="POST", json={ "item_ids": item_ids, "dataset_id": dataset_id, "filters": convert_and_respect_annotation_metadata( object_=filters, annotation=typing.Sequence[DatasetItemFilter], direction="write" ), "batch_group_id": batch_group_id, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def delete_datasets_batch( self, *, ids: typing.Sequence[str], request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[None]: """ Delete datasets batch Parameters ---------- ids : typing.Sequence[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/delete-batch", method="POST", json={ "ids": ids, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) @contextlib.asynccontextmanager async def download_dataset_export( self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]]: """ Downloads the exported CSV file for a completed export job. This endpoint proxies the file download to avoid exposing internal storage URLs. Parameters ---------- job_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Returns ------- typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]] CSV file content """ async with self._client_wrapper.httpx_client.stream( f"v1/private/datasets/export-jobs/{jsonable_encoder(job_id)}/download", method="GET", request_options=request_options, ) as _response: async def stream() -> AsyncHttpResponse[typing.AsyncIterator[bytes]]: try: if 200 <= _response.status_code < 300: _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None return AsyncHttpResponse( response=_response, data=(_chunk async for _chunk in _response.aiter_bytes(chunk_size=_chunk_size)), ) await _response.aread() if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError( status_code=_response.status_code, headers=dict(_response.headers), body=_response.text ) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) yield await stream() async def expand_dataset( self, id: str, *, model: str, sample_count: typing.Optional[int] = OMIT, preserve_fields: typing.Optional[typing.Sequence[str]] = OMIT, variation_instructions: typing.Optional[str] = OMIT, custom_prompt: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetExpansionResponse]: """ Generate synthetic dataset samples using LLM based on existing data patterns Parameters ---------- id : str model : str The model to use for synthetic data generation sample_count : typing.Optional[int] Number of synthetic samples to generate preserve_fields : typing.Optional[typing.Sequence[str]] Fields to preserve patterns from original data variation_instructions : typing.Optional[str] Additional instructions for data variation custom_prompt : typing.Optional[str] Custom prompt to use for generation instead of auto-generated one request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetExpansionResponse] Generated synthetic samples """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/expansions", method="POST", json={ "model": model, "sample_count": sample_count, "preserve_fields": preserve_fields, "variation_instructions": variation_instructions, "custom_prompt": custom_prompt, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetExpansionResponse, parse_obj_as( type_=DatasetExpansionResponse, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def find_dataset_items_with_experiment_items( self, id: str, *, experiment_ids: str, page: typing.Optional[int] = None, size: typing.Optional[int] = None, filters: typing.Optional[str] = None, sorting: typing.Optional[str] = None, search: typing.Optional[str] = None, truncate: typing.Optional[bool] = None, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetItemPageCompare]: """ Find dataset items with experiment items Parameters ---------- id : str experiment_ids : str page : typing.Optional[int] size : typing.Optional[int] filters : typing.Optional[str] sorting : typing.Optional[str] search : typing.Optional[str] truncate : typing.Optional[bool] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetItemPageCompare] Dataset item resource """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/experiments/items", method="GET", params={ "page": page, "size": size, "experiment_ids": experiment_ids, "filters": filters, "sorting": sorting, "search": search, "truncate": truncate, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetItemPageCompare, parse_obj_as( type_=DatasetItemPageCompare, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_by_identifier( self, *, dataset_name: str, project_name: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetPublic]: """ Get dataset by name Parameters ---------- dataset_name : str project_name : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetPublic] Dataset resource """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/retrieve", method="POST", json={ "dataset_name": dataset_name, "project_name": project_name, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetPublic, parse_obj_as( type_=DatasetPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_experiment_items_stats( self, id: str, *, experiment_ids: str, filters: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[ProjectStatsPublic]: """ Get experiment items stats for dataset Parameters ---------- id : str experiment_ids : str filters : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[ProjectStatsPublic] Experiment items stats resource """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/experiments/items/stats", method="GET", params={ "experiment_ids": experiment_ids, "filters": filters, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( ProjectStatsPublic, parse_obj_as( type_=ProjectStatsPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_export_job( self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[DatasetExportJobPublic]: """ Retrieves the current status of a dataset export job Parameters ---------- job_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetExportJobPublic] Export job details """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/export-jobs/{jsonable_encoder(job_id)}", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetExportJobPublic, parse_obj_as( type_=DatasetExportJobPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_export_jobs( self, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[typing.List[DatasetExportJobPublic]]: """ Retrieves all export jobs for the workspace. This is used to restore the export panel state after page refresh. Parameters ---------- request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[typing.List[DatasetExportJobPublic]] List of export jobs """ _response = await self._client_wrapper.httpx_client.request( "v1/private/datasets/export-jobs", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( typing.List[DatasetExportJobPublic], parse_obj_as( type_=typing.List[DatasetExportJobPublic], # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_item_by_id( self, item_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[DatasetItemPublic]: """ Get dataset item by id Parameters ---------- item_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetItemPublic] Dataset item resource """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/items/{jsonable_encoder(item_id)}", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetItemPublic, parse_obj_as( type_=DatasetItemPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def patch_dataset_item( self, item_id: str, *, source: DatasetItemWriteSource, data: JsonNode, id: typing.Optional[str] = OMIT, trace_id: typing.Optional[str] = OMIT, span_id: typing.Optional[str] = OMIT, description: typing.Optional[str] = OMIT, tags: typing.Optional[typing.Sequence[str]] = OMIT, evaluators: typing.Optional[typing.Sequence[EvaluatorItemWrite]] = OMIT, execution_policy: typing.Optional[ExecutionPolicyWrite] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[None]: """ Partially update dataset item by id. Only provided fields will be updated. Parameters ---------- item_id : str source : DatasetItemWriteSource data : JsonNode id : typing.Optional[str] trace_id : typing.Optional[str] span_id : typing.Optional[str] description : typing.Optional[str] tags : typing.Optional[typing.Sequence[str]] evaluators : typing.Optional[typing.Sequence[EvaluatorItemWrite]] execution_policy : typing.Optional[ExecutionPolicyWrite] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/items/{jsonable_encoder(item_id)}", method="PATCH", json={ "id": id, "trace_id": trace_id, "span_id": span_id, "source": source, "data": data, "description": description, "tags": tags, "evaluators": convert_and_respect_annotation_metadata( object_=evaluators, annotation=typing.Sequence[EvaluatorItemWrite], direction="write" ), "execution_policy": convert_and_respect_annotation_metadata( object_=execution_policy, annotation=ExecutionPolicyWrite, direction="write" ), }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_items( self, id: str, *, page: typing.Optional[int] = None, size: typing.Optional[int] = None, version: typing.Optional[str] = None, filters: typing.Optional[str] = None, truncate: typing.Optional[bool] = None, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetItemPagePublic]: """ Get dataset items Parameters ---------- id : str page : typing.Optional[int] size : typing.Optional[int] version : typing.Optional[str] filters : typing.Optional[str] truncate : typing.Optional[bool] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetItemPagePublic] Dataset items resource """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items", method="GET", params={ "page": page, "size": size, "version": version, "filters": filters, "truncate": truncate, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetItemPagePublic, parse_obj_as( type_=DatasetItemPagePublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def get_dataset_items_output_columns( self, id: str, *, experiment_ids: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[PageColumns]: """ Get dataset items output columns Parameters ---------- id : str experiment_ids : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[PageColumns] Dataset item output columns """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/items/experiments/items/output/columns", method="GET", params={ "experiment_ids": experiment_ids, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( PageColumns, parse_obj_as( type_=PageColumns, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def mark_dataset_export_job_viewed( self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[None]: """ Marks a dataset export job as viewed by setting the viewed_at timestamp. This is used to track that a user has seen a failed job's error message. This operation is idempotent. Parameters ---------- job_id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/export-jobs/{jsonable_encoder(job_id)}/mark-viewed", method="PUT", request_options=request_options, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def start_dataset_export( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[DatasetExportJobPublic]: """ Initiates an asynchronous CSV export job for the dataset. Returns immediately with job details for polling. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetExportJobPublic] Existing export job in progress """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/export", method="POST", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetExportJobPublic, parse_obj_as( type_=DatasetExportJobPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) @contextlib.asynccontextmanager async def stream_dataset_items( self, *, dataset_name: str, last_retrieved_id: typing.Optional[str] = OMIT, steam_limit: typing.Optional[int] = OMIT, dataset_version: typing.Optional[str] = OMIT, project_name: typing.Optional[str] = OMIT, filters: typing.Optional[str] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]]: """ Stream dataset items Parameters ---------- dataset_name : str last_retrieved_id : typing.Optional[str] steam_limit : typing.Optional[int] dataset_version : typing.Optional[str] project_name : typing.Optional[str] filters : typing.Optional[str] request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Returns ------- typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]] Dataset items stream or error during process """ async with self._client_wrapper.httpx_client.stream( "v1/private/datasets/items/stream", method="POST", json={ "dataset_name": dataset_name, "last_retrieved_id": last_retrieved_id, "steam_limit": steam_limit, "dataset_version": dataset_version, "project_name": project_name, "filters": filters, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) as _response: async def stream() -> AsyncHttpResponse[typing.AsyncIterator[bytes]]: try: if 200 <= _response.status_code < 300: _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None return AsyncHttpResponse( response=_response, data=(_chunk async for _chunk in _response.aiter_bytes(chunk_size=_chunk_size)), ) await _response.aread() _response_json = _response.json() except JSONDecodeError: raise ApiError( status_code=_response.status_code, headers=dict(_response.headers), body=_response.text ) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) yield await stream() async def compare_dataset_versions( self, id: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[DatasetVersionDiff]: """ Compare the latest committed dataset version with the current draft state. This endpoint provides insights into changes made since the last version was committed. The comparison calculates additions, modifications, deletions, and unchanged items between the latest version snapshot and current draft. Parameters ---------- id : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetVersionDiff] Diff computed successfully """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/diff", method="GET", request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionDiff, parse_obj_as( type_=DatasetVersionDiff, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def create_version_tag( self, id: str, version_hash: str, *, tag: str, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[None]: """ Add a tag to a specific dataset version for easy reference (e.g., 'baseline', 'v1.0', 'production') Parameters ---------- id : str version_hash : str tag : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/hash/{jsonable_encoder(version_hash)}/tags", method="POST", json={ "tag": tag, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 409: raise ConflictError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def delete_version_tag( self, id: str, version_hash: str, tag: str, *, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[None]: """ Remove a tag from a dataset version. The version itself is not deleted, only the tag reference. Parameters ---------- id : str version_hash : str tag : str request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[None] """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/{jsonable_encoder(version_hash)}/tags/{jsonable_encoder(tag)}", method="DELETE", request_options=request_options, ) try: if 200 <= _response.status_code < 300: return AsyncHttpResponse(response=_response, data=None) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def list_dataset_versions( self, id: str, *, page: typing.Optional[int] = None, size: typing.Optional[int] = None, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetVersionPagePublic]: """ Get paginated list of versions for a dataset, ordered by creation time (newest first) Parameters ---------- id : str page : typing.Optional[int] size : typing.Optional[int] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetVersionPagePublic] Dataset versions """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions", method="GET", params={ "page": page, "size": size, }, request_options=request_options, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPagePublic, parse_obj_as( type_=DatasetVersionPagePublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def restore_dataset_version( self, id: str, *, version_ref: str, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[DatasetVersionPublic]: """ Restores the dataset to a previous version state by creating a new version with items copied from the specified version. If the version is already the latest, returns it as-is (no-op). Parameters ---------- id : str version_ref : str Version hash or tag to restore from request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetVersionPublic] Version restored successfully """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/restore", method="POST", json={ "version_ref": version_ref, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def retrieve_dataset_version( self, id: str, *, version_name: str, request_options: typing.Optional[RequestOptions] = None ) -> AsyncHttpResponse[DatasetVersionPublic]: """ Get a specific version by its version name (e.g., 'v1', 'v373'). This is more efficient than paginating through all versions for large datasets. Parameters ---------- id : str version_name : str Version name in format 'vN' (e.g., 'v1', 'v373') request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetVersionPublic] Dataset version """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/retrieve", method="POST", json={ "version_name": version_name, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def update_dataset_version( self, id: str, version_hash: str, *, change_description: typing.Optional[str] = OMIT, tags_to_add: typing.Optional[typing.Sequence[str]] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[DatasetVersionPublic]: """ Update a dataset version's change_description and/or add new tags Parameters ---------- id : str version_hash : str change_description : typing.Optional[str] Optional description of changes in this version tags_to_add : typing.Optional[typing.Sequence[str]] Optional list of tags to add to this version request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[DatasetVersionPublic] Version updated successfully """ _response = await self._client_wrapper.httpx_client.request( f"v1/private/datasets/{jsonable_encoder(id)}/versions/hash/{jsonable_encoder(version_hash)}", method="PATCH", json={ "change_description": change_description, "tags_to_add": tags_to_add, }, headers={ "content-type": "application/json", }, request_options=request_options, omit=OMIT, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( DatasetVersionPublic, parse_obj_as( type_=DatasetVersionPublic, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 404: raise NotFoundError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 409: raise ConflictError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)