stract-api 0.1.0__py3-none-any.whl

stract_api/api/job_document_api.py

@@ -0,0 +1,575 @@
+"""
+    Stract API
+
+    Get structured output from unstructured inputs  ## Machine authentication  Programmatic access to the API is authenticated with an API key. Include the API key in every request as a bearer token in the `authorization` header:  ``` authorization: bearer [apiKey] ```  ## SDKs  Official SDKs are available for the following languages:  - **Node (JavaScript / TypeScript)**: [`stract-api` on npm](https://www.npmjs.com/package/stract-api) - **Java (17+)**: [`com.stract-api:stract-api` on Maven Central](https://central.sonatype.com/artifact/com.stract-api/stract-api) 
+
+    The version of the OpenAPI document: 0.9.4
+    Contact: matt@stract-api.com
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+import warnings
+from pydantic import validate_call, Field, StrictFloat, StrictStr, StrictInt
+from typing import Any, Dict, List, Optional, Tuple, Union
+from typing_extensions import Annotated
+
+from pydantic import Field
+from typing import List
+from typing_extensions import Annotated
+from uuid import UUID
+from stract_api.models.job_document import JobDocument
+from stract_api.models.job_output import JobOutput
+
+from stract_api.api_client import ApiClient, RequestSerialized
+from stract_api.api_response import ApiResponse
+from stract_api.rest import RESTResponseType
+
+
+class JobDocumentApi:
+    """NOTE: This class is auto generated by OpenAPI Generator
+    Ref: https://openapi-generator.tech
+
+    Do not edit the class manually.
+    """
+
+    def __init__(self, api_client=None) -> None:
+        if api_client is None:
+            api_client = ApiClient.get_default()
+        self.api_client = api_client
+
+
+    @validate_call
+    def get_job_document_output(
+        self,
+        job_doc_id: Annotated[UUID, Field(description="Unique identifier of the job document")],
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> JobOutput:
+        """Get the output for a job document
+
+        Retrieve the extracted structured data for the specified job document
+
+        :param job_doc_id: Unique identifier of the job document (required)
+        :type job_doc_id: UUID
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._get_job_document_output_serialize(
+            job_doc_id=job_doc_id,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "JobOutput",
+            '400': "str",
+            '401': "str",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        response_data.read()
+        return self.api_client.response_deserialize(
+            response_data=response_data,
+            response_types_map=_response_types_map,
+        ).data
+
+
+    @validate_call
+    def get_job_document_output_with_http_info(
+        self,
+        job_doc_id: Annotated[UUID, Field(description="Unique identifier of the job document")],
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> ApiResponse[JobOutput]:
+        """Get the output for a job document
+
+        Retrieve the extracted structured data for the specified job document
+
+        :param job_doc_id: Unique identifier of the job document (required)
+        :type job_doc_id: UUID
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._get_job_document_output_serialize(
+            job_doc_id=job_doc_id,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "JobOutput",
+            '400': "str",
+            '401': "str",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        response_data.read()
+        return self.api_client.response_deserialize(
+            response_data=response_data,
+            response_types_map=_response_types_map,
+        )
+
+
+    @validate_call
+    def get_job_document_output_without_preload_content(
+        self,
+        job_doc_id: Annotated[UUID, Field(description="Unique identifier of the job document")],
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> RESTResponseType:
+        """Get the output for a job document
+
+        Retrieve the extracted structured data for the specified job document
+
+        :param job_doc_id: Unique identifier of the job document (required)
+        :type job_doc_id: UUID
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._get_job_document_output_serialize(
+            job_doc_id=job_doc_id,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "JobOutput",
+            '400': "str",
+            '401': "str",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        return response_data.response
+
+
+    def _get_job_document_output_serialize(
+        self,
+        job_doc_id,
+        _request_auth,
+        _content_type,
+        _headers,
+        _host_index,
+    ) -> RequestSerialized:
+
+        _host = None
+
+        _collection_formats: Dict[str, str] = {
+        }
+
+        _path_params: Dict[str, str] = {}
+        _query_params: List[Tuple[str, str]] = []
+        _header_params: Dict[str, Any] = self.api_client._merge_headers(_headers)
+        _form_params: List[Tuple[str, str]] = []
+        _files: Dict[
+            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
+        ] = {}
+        _body_params: Optional[bytes] = None
+
+        # process the path parameters
+        if job_doc_id is not None:
+            _path_params['jobDocId'] = job_doc_id
+        # process the query parameters
+        # process the header parameters
+        # process the form parameters
+        # process the body parameter
+
+
+        # set the HTTP header `Accept`
+        if not any(key.lower() == 'accept' for key in _header_params):
+            _header_params['Accept'] = self.api_client.select_header_accept(
+                [
+                    'application/json'
+                ]
+            )
+
+
+        # authentication setting
+        _auth_settings: List[str] = [
+            'bearerAuth'
+        ]
+
+        return self.api_client.param_serialize(
+            method='GET',
+            resource_path='/job_document/{jobDocId}/output',
+            path_params=_path_params,
+            query_params=_query_params,
+            header_params=_header_params,
+            body=_body_params,
+            post_params=_form_params,
+            files=_files,
+            auth_settings=_auth_settings,
+            collection_formats=_collection_formats,
+            _host=_host,
+            _request_auth=_request_auth
+        )
+
+
+
+
+    @validate_call
+    def get_job_documents(
+        self,
+        job_id: Annotated[UUID, Field(description="Unique identifier of the job")],
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> List[JobDocument]:
+        """Get the status of document analysis in a job
+
+        Retrieve the per-document status and analysis results for the specified job
+
+        :param job_id: Unique identifier of the job (required)
+        :type job_id: UUID
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._get_job_documents_serialize(
+            job_id=job_id,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "List[JobDocument]",
+            '400': "str",
+            '401': "str",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        response_data.read()
+        return self.api_client.response_deserialize(
+            response_data=response_data,
+            response_types_map=_response_types_map,
+        ).data
+
+
+    @validate_call
+    def get_job_documents_with_http_info(
+        self,
+        job_id: Annotated[UUID, Field(description="Unique identifier of the job")],
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> ApiResponse[List[JobDocument]]:
+        """Get the status of document analysis in a job
+
+        Retrieve the per-document status and analysis results for the specified job
+
+        :param job_id: Unique identifier of the job (required)
+        :type job_id: UUID
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._get_job_documents_serialize(
+            job_id=job_id,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "List[JobDocument]",
+            '400': "str",
+            '401': "str",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        response_data.read()
+        return self.api_client.response_deserialize(
+            response_data=response_data,
+            response_types_map=_response_types_map,
+        )
+
+
+    @validate_call
+    def get_job_documents_without_preload_content(
+        self,
+        job_id: Annotated[UUID, Field(description="Unique identifier of the job")],
+        _request_timeout: Union[
+            None,
+            Annotated[StrictFloat, Field(gt=0)],
+            Tuple[
+                Annotated[StrictFloat, Field(gt=0)],
+                Annotated[StrictFloat, Field(gt=0)]
+            ]
+        ] = None,
+        _request_auth: Optional[Dict[StrictStr, Any]] = None,
+        _content_type: Optional[StrictStr] = None,
+        _headers: Optional[Dict[StrictStr, Any]] = None,
+        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
+    ) -> RESTResponseType:
+        """Get the status of document analysis in a job
+
+        Retrieve the per-document status and analysis results for the specified job
+
+        :param job_id: Unique identifier of the job (required)
+        :type job_id: UUID
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        :type _request_timeout: int, tuple(int, int), optional
+        :param _request_auth: set to override the auth_settings for an a single
+                              request; this effectively ignores the
+                              authentication in the spec for a single request.
+        :type _request_auth: dict, optional
+        :param _content_type: force content-type for the request.
+        :type _content_type: str, Optional
+        :param _headers: set to override the headers for a single
+                         request; this effectively ignores the headers
+                         in the spec for a single request.
+        :type _headers: dict, optional
+        :param _host_index: set to override the host_index for a single
+                            request; this effectively ignores the host_index
+                            in the spec for a single request.
+        :type _host_index: int, optional
+        :return: Returns the result object.
+        """ # noqa: E501
+
+        _param = self._get_job_documents_serialize(
+            job_id=job_id,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "List[JobDocument]",
+            '400': "str",
+            '401': "str",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        return response_data.response
+
+
+    def _get_job_documents_serialize(
+        self,
+        job_id,
+        _request_auth,
+        _content_type,
+        _headers,
+        _host_index,
+    ) -> RequestSerialized:
+
+        _host = None
+
+        _collection_formats: Dict[str, str] = {
+        }
+
+        _path_params: Dict[str, str] = {}
+        _query_params: List[Tuple[str, str]] = []
+        _header_params: Dict[str, Any] = self.api_client._merge_headers(_headers)
+        _form_params: List[Tuple[str, str]] = []
+        _files: Dict[
+            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
+        ] = {}
+        _body_params: Optional[bytes] = None
+
+        # process the path parameters
+        if job_id is not None:
+            _path_params['jobId'] = job_id
+        # process the query parameters
+        # process the header parameters
+        # process the form parameters
+        # process the body parameter
+
+
+        # set the HTTP header `Accept`
+        if not any(key.lower() == 'accept' for key in _header_params):
+            _header_params['Accept'] = self.api_client.select_header_accept(
+                [
+                    'application/json'
+                ]
+            )
+
+
+        # authentication setting
+        _auth_settings: List[str] = [
+            'bearerAuth'
+        ]
+
+        return self.api_client.param_serialize(
+            method='GET',
+            resource_path='/job/{jobId}/job_document',
+            path_params=_path_params,
+            query_params=_query_params,
+            header_params=_header_params,
+            body=_body_params,
+            post_params=_form_params,
+            files=_files,
+            auth_settings=_auth_settings,
+            collection_formats=_collection_formats,
+            _host=_host,
+            _request_auth=_request_auth
+        )
+
+