# This file was auto-generated by Fern from our API Definition. import typing import urllib.parse from json.decoder import JSONDecodeError from ...core.api_error import ApiError from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ...core.jsonable_encoder import jsonable_encoder from ...core.remove_none_from_dict import remove_none_from_dict from ...errors.unprocessable_entity_error import UnprocessableEntityError from ...types.extract_agent import ExtractAgent from ...types.extract_config import ExtractConfig from ...types.extract_job import ExtractJob from ...types.extract_job_create import ExtractJobCreate from ...types.extract_resultset import ExtractResultset from ...types.extract_run import ExtractRun from ...types.extract_schema_validate_response import ExtractSchemaValidateResponse from ...types.http_validation_error import HttpValidationError from ...types.llama_extract_settings import LlamaExtractSettings from ...types.paginated_extract_runs_response import PaginatedExtractRunsResponse from .types.extract_agent_create_data_schema import ExtractAgentCreateDataSchema from .types.extract_agent_update_data_schema import ExtractAgentUpdateDataSchema from .types.extract_job_create_batch_data_schema_override import ExtractJobCreateBatchDataSchemaOverride from .types.extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema try: import pydantic if pydantic.__version__.startswith("1."): raise ImportError import pydantic.v1 as pydantic # type: ignore except ImportError: import pydantic # type: ignore # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class LlamaExtractClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper def list_extraction_agents(self, *, project_id: str) -> typing.List[ExtractAgent]: """ Parameters: - project_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.list_extraction_agents( project_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"), params=remove_none_from_dict({"project_id": project_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ExtractAgent], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def create_extraction_agent( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, name: str, data_schema: ExtractAgentCreateDataSchema, config: ExtractConfig, ) -> ExtractAgent: """ Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - name: str. The name of the extraction schema - data_schema: ExtractAgentCreateDataSchema. The schema of the data. - config: ExtractConfig. The configuration parameters for the extraction agent. --- from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.create_extraction_agent( name="string", config=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ) """ _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}), json=jsonable_encoder({"name": name, "data_schema": data_schema, "config": config}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def validate_extraction_schema( self, *, data_schema: ExtractSchemaValidateRequestDataSchema ) -> ExtractSchemaValidateResponse: """ Validates an extraction agent's schema definition. Returns the normalized and validated schema if valid, otherwise raises an HTTP 400. Parameters: - data_schema: ExtractSchemaValidateRequestDataSchema. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.validate_extraction_schema() """ _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation" ), json=jsonable_encoder({"data_schema": data_schema}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractSchemaValidateResponse, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_extraction_agent_by_name(self, name: str, *, project_id: typing.Optional[str] = None) -> ExtractAgent: """ Parameters: - name: str. - project_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.get_extraction_agent_by_name( name="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}" ), params=remove_none_from_dict({"project_id": project_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_extraction_agent(self, extraction_agent_id: str) -> ExtractAgent: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.get_extraction_agent( extraction_agent_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def update_extraction_agent( self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig ) -> ExtractAgent: """ Parameters: - extraction_agent_id: str. - data_schema: ExtractAgentUpdateDataSchema. The schema of the data - config: ExtractConfig. The configuration parameters for the extraction agent. --- from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.update_extraction_agent( extraction_agent_id="string", config=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ) """ _response = self._client_wrapper.httpx_client.request( "PUT", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}" ), json=jsonable_encoder({"data_schema": data_schema, "config": config}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def delete_extraction_agent(self, extraction_agent_id: str) -> typing.Any: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.delete_extraction_agent( extraction_agent_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "DELETE", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def list_jobs(self, *, extraction_agent_id: str) -> typing.List[ExtractJob]: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.list_jobs( extraction_agent_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"), params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def run_job(self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreate) -> ExtractJob: """ Parameters: - from_ui: typing.Optional[bool]. - request: ExtractJobCreate. --- from llama_cloud import ( ExtractConfig, ExtractJobCreate, ExtractMode, ExtractTarget, ) from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.run_job( request=ExtractJobCreate( extraction_agent_id="string", file_id="string", config_override=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ), ) """ _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"), params=remove_none_from_dict({"from_ui": from_ui}), json=jsonable_encoder(request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job(self, job_id: str) -> ExtractJob: """ Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.get_job( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def run_job_test_user( self, *, from_ui: typing.Optional[bool] = None, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT, ) -> ExtractJob: """ Parameters: - from_ui: typing.Optional[bool]. - job_create: ExtractJobCreate. - extract_settings: typing.Optional[LlamaExtractSettings]. --- from llama_cloud import ( ChunkMode, ExtractConfig, ExtractJobCreate, ExtractMode, ExtractTarget, FailPageMode, LlamaExtractSettings, LlamaParseParameters, ParsingMode, ) from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.run_job_test_user( job_create=ExtractJobCreate( extraction_agent_id="string", file_id="string", config_override=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ), extract_settings=LlamaExtractSettings( chunk_mode=ChunkMode.PAGE, llama_parse_params=LlamaParseParameters( parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM, replace_failed_page_mode=FailPageMode.RAW_TEXT, ), ), ) """ _request: typing.Dict[str, typing.Any] = {"job_create": job_create} if extract_settings is not OMIT: _request["extract_settings"] = extract_settings _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/test"), params=remove_none_from_dict({"from_ui": from_ui}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def run_job_on_file( self, *, from_ui: typing.Optional[bool] = None, extraction_agent_id: str, file: typing.IO, data_schema_override: typing.Optional[str] = None, config_override: typing.Optional[str] = None, ) -> ExtractJob: """ Parameters: - from_ui: typing.Optional[bool]. - extraction_agent_id: str. - file: typing.IO. - data_schema_override: typing.Optional[str]. - config_override: typing.Optional[str]. """ _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/file"), params=remove_none_from_dict({"from_ui": from_ui}), data=jsonable_encoder( { "extraction_agent_id": extraction_agent_id, "data_schema_override": data_schema_override, "config_override": config_override, } ), files={"file": file}, headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def run_batch_jobs( self, *, from_ui: typing.Optional[bool] = None, extraction_agent_id: str, file_ids: typing.List[str], data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = OMIT, config_override: typing.Optional[ExtractConfig] = OMIT, ) -> typing.List[ExtractJob]: """ Parameters: - from_ui: typing.Optional[bool]. - extraction_agent_id: str. The id of the extraction agent - file_ids: typing.List[str]. The ids of the files - data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride]. The data schema to override the extraction agent's data schema with - config_override: typing.Optional[ExtractConfig]. --- from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.run_batch_jobs( extraction_agent_id="string", file_ids=[], config_override=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ) """ _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_ids": file_ids} if data_schema_override is not OMIT: _request["data_schema_override"] = data_schema_override if config_override is not OMIT: _request["config_override"] = config_override _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"), params=remove_none_from_dict({"from_ui": from_ui}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_result(self, job_id: str) -> ExtractResultset: """ Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.get_job_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractResultset, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def list_extract_runs( self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None ) -> PaginatedExtractRunsResponse: """ Parameters: - extraction_agent_id: str. - skip: typing.Optional[int]. - limit: typing.Optional[int]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.list_extract_runs( extraction_agent_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"), params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(PaginatedExtractRunsResponse, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_latest_run_from_ui(self, *, extraction_agent_id: str) -> typing.Optional[ExtractRun]: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.get_latest_run_from_ui( extraction_agent_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs/latest-from-ui"), params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Optional[ExtractRun], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_run_by_job_id(self, job_id: str) -> ExtractRun: """ Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.get_run_by_job_id( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{job_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractRun, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_run(self, run_id: str) -> ExtractRun: """ Parameters: - run_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.get_run( run_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractRun, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def delete_extraction_run(self, run_id: str) -> typing.Any: """ Parameters: - run_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.llama_extract.delete_extraction_run( run_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "DELETE", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) class AsyncLlamaExtractClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper async def list_extraction_agents(self, *, project_id: str) -> typing.List[ExtractAgent]: """ Parameters: - project_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.list_extraction_agents( project_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"), params=remove_none_from_dict({"project_id": project_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ExtractAgent], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def create_extraction_agent( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, name: str, data_schema: ExtractAgentCreateDataSchema, config: ExtractConfig, ) -> ExtractAgent: """ Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - name: str. The name of the extraction schema - data_schema: ExtractAgentCreateDataSchema. The schema of the data. - config: ExtractConfig. The configuration parameters for the extraction agent. --- from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.create_extraction_agent( name="string", config=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ) """ _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}), json=jsonable_encoder({"name": name, "data_schema": data_schema, "config": config}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def validate_extraction_schema( self, *, data_schema: ExtractSchemaValidateRequestDataSchema ) -> ExtractSchemaValidateResponse: """ Validates an extraction agent's schema definition. Returns the normalized and validated schema if valid, otherwise raises an HTTP 400. Parameters: - data_schema: ExtractSchemaValidateRequestDataSchema. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.validate_extraction_schema() """ _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation" ), json=jsonable_encoder({"data_schema": data_schema}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractSchemaValidateResponse, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_extraction_agent_by_name(self, name: str, *, project_id: typing.Optional[str] = None) -> ExtractAgent: """ Parameters: - name: str. - project_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.get_extraction_agent_by_name( name="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}" ), params=remove_none_from_dict({"project_id": project_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_extraction_agent(self, extraction_agent_id: str) -> ExtractAgent: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.get_extraction_agent( extraction_agent_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def update_extraction_agent( self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig ) -> ExtractAgent: """ Parameters: - extraction_agent_id: str. - data_schema: ExtractAgentUpdateDataSchema. The schema of the data - config: ExtractConfig. The configuration parameters for the extraction agent. --- from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.update_extraction_agent( extraction_agent_id="string", config=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ) """ _response = await self._client_wrapper.httpx_client.request( "PUT", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}" ), json=jsonable_encoder({"data_schema": data_schema, "config": config}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractAgent, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def delete_extraction_agent(self, extraction_agent_id: str) -> typing.Any: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.delete_extraction_agent( extraction_agent_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "DELETE", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def list_jobs(self, *, extraction_agent_id: str) -> typing.List[ExtractJob]: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.list_jobs( extraction_agent_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"), params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def run_job(self, *, from_ui: typing.Optional[bool] = None, request: ExtractJobCreate) -> ExtractJob: """ Parameters: - from_ui: typing.Optional[bool]. - request: ExtractJobCreate. --- from llama_cloud import ( ExtractConfig, ExtractJobCreate, ExtractMode, ExtractTarget, ) from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.run_job( request=ExtractJobCreate( extraction_agent_id="string", file_id="string", config_override=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ), ) """ _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"), params=remove_none_from_dict({"from_ui": from_ui}), json=jsonable_encoder(request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job(self, job_id: str) -> ExtractJob: """ Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.get_job( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def run_job_test_user( self, *, from_ui: typing.Optional[bool] = None, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT, ) -> ExtractJob: """ Parameters: - from_ui: typing.Optional[bool]. - job_create: ExtractJobCreate. - extract_settings: typing.Optional[LlamaExtractSettings]. --- from llama_cloud import ( ChunkMode, ExtractConfig, ExtractJobCreate, ExtractMode, ExtractTarget, FailPageMode, LlamaExtractSettings, LlamaParseParameters, ParsingMode, ) from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.run_job_test_user( job_create=ExtractJobCreate( extraction_agent_id="string", file_id="string", config_override=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ), extract_settings=LlamaExtractSettings( chunk_mode=ChunkMode.PAGE, llama_parse_params=LlamaParseParameters( parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM, replace_failed_page_mode=FailPageMode.RAW_TEXT, ), ), ) """ _request: typing.Dict[str, typing.Any] = {"job_create": job_create} if extract_settings is not OMIT: _request["extract_settings"] = extract_settings _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/test"), params=remove_none_from_dict({"from_ui": from_ui}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def run_job_on_file( self, *, from_ui: typing.Optional[bool] = None, extraction_agent_id: str, file: typing.IO, data_schema_override: typing.Optional[str] = None, config_override: typing.Optional[str] = None, ) -> ExtractJob: """ Parameters: - from_ui: typing.Optional[bool]. - extraction_agent_id: str. - file: typing.IO. - data_schema_override: typing.Optional[str]. - config_override: typing.Optional[str]. """ _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/file"), params=remove_none_from_dict({"from_ui": from_ui}), data=jsonable_encoder( { "extraction_agent_id": extraction_agent_id, "data_schema_override": data_schema_override, "config_override": config_override, } ), files={"file": file}, headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def run_batch_jobs( self, *, from_ui: typing.Optional[bool] = None, extraction_agent_id: str, file_ids: typing.List[str], data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = OMIT, config_override: typing.Optional[ExtractConfig] = OMIT, ) -> typing.List[ExtractJob]: """ Parameters: - from_ui: typing.Optional[bool]. - extraction_agent_id: str. The id of the extraction agent - file_ids: typing.List[str]. The ids of the files - data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride]. The data schema to override the extraction agent's data schema with - config_override: typing.Optional[ExtractConfig]. --- from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.run_batch_jobs( extraction_agent_id="string", file_ids=[], config_override=ExtractConfig( extraction_target=ExtractTarget.PER_DOC, extraction_mode=ExtractMode.FAST, ), ) """ _request: typing.Dict[str, typing.Any] = {"extraction_agent_id": extraction_agent_id, "file_ids": file_ids} if data_schema_override is not OMIT: _request["data_schema_override"] = data_schema_override if config_override is not OMIT: _request["config_override"] = config_override _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"), params=remove_none_from_dict({"from_ui": from_ui}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ExtractJob], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_result(self, job_id: str) -> ExtractResultset: """ Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.get_job_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractResultset, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def list_extract_runs( self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None ) -> PaginatedExtractRunsResponse: """ Parameters: - extraction_agent_id: str. - skip: typing.Optional[int]. - limit: typing.Optional[int]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.list_extract_runs( extraction_agent_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"), params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(PaginatedExtractRunsResponse, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_latest_run_from_ui(self, *, extraction_agent_id: str) -> typing.Optional[ExtractRun]: """ Parameters: - extraction_agent_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.get_latest_run_from_ui( extraction_agent_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs/latest-from-ui"), params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Optional[ExtractRun], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_run_by_job_id(self, job_id: str) -> ExtractRun: """ Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.get_run_by_job_id( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{job_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractRun, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_run(self, run_id: str) -> ExtractRun: """ Parameters: - run_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.get_run( run_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ExtractRun, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def delete_extraction_run(self, run_id: str) -> typing.Any: """ Parameters: - run_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.llama_extract.delete_extraction_run( run_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "DELETE", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json)