unstructured-transform-client 0.18.17__py3-none-any.whl

unstructured_transform_client/_generated/api/extract_api.py

@@ -0,0 +1,351 @@
+"""
+    Unstructured Transform API
+
+    One document in, the parsed document back. A single call takes a document and returns structured output — no job graph, no strategy selection, no model provider setup, and no polling loop. An optional schema switches the request from parse-only to parse-then-extract.
+
+    The version of the OpenAPI document: 0.1.0
+    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, StrictStr
+from typing import Optional
+from typing_extensions import Annotated
+from unstructured_transform_client._generated.models.extract_request import ExtractRequest
+from unstructured_transform_client._generated.models.parse_result import ParseResult
+
+from unstructured_transform_client._generated.api_client import ApiClient, RequestSerialized
+from unstructured_transform_client._generated.api_response import ApiResponse
+from unstructured_transform_client._generated.rest import RESTResponseType
+
+
+class ExtractApi:
+    """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 extract_run(
+        self,
+        extract_request: ExtractRequest,
+        prefer: Annotated[Optional[StrictStr], Field(description="Wait up to this many seconds for completed extraction.")] = None,
+        _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,
+    ) -> ParseResult:
+        """Extract fields from a parse or document
+
+        Takes either a parse ID or a document and a schema, then returns the fields. A multipart input is limited to 50 MB and to the supported extensions: bmp, docx, heic, jpeg, jpg, pdf, png, pptx, tiff.
+
+        :param extract_request: (required)
+        :type extract_request: ExtractRequest
+        :param prefer: Wait up to this many seconds for completed extraction.
+        :type prefer: str
+        :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._extract_run_serialize(
+            extract_request=extract_request,
+            prefer=prefer,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "ParseResult",
+            '202': "JobAccepted",
+            '400': "Error",
+            '401': "Error",
+            '404': "Error",
+            '409': "Error",
+            '413': "Error",
+            '415': "Error",
+        }
+        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 extract_run_with_http_info(
+        self,
+        extract_request: ExtractRequest,
+        prefer: Annotated[Optional[StrictStr], Field(description="Wait up to this many seconds for completed extraction.")] = None,
+        _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[ParseResult]:
+        """Extract fields from a parse or document
+
+        Takes either a parse ID or a document and a schema, then returns the fields. A multipart input is limited to 50 MB and to the supported extensions: bmp, docx, heic, jpeg, jpg, pdf, png, pptx, tiff.
+
+        :param extract_request: (required)
+        :type extract_request: ExtractRequest
+        :param prefer: Wait up to this many seconds for completed extraction.
+        :type prefer: str
+        :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._extract_run_serialize(
+            extract_request=extract_request,
+            prefer=prefer,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "ParseResult",
+            '202': "JobAccepted",
+            '400': "Error",
+            '401': "Error",
+            '404': "Error",
+            '409': "Error",
+            '413': "Error",
+            '415': "Error",
+        }
+        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 extract_run_without_preload_content(
+        self,
+        extract_request: ExtractRequest,
+        prefer: Annotated[Optional[StrictStr], Field(description="Wait up to this many seconds for completed extraction.")] = None,
+        _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:
+        """Extract fields from a parse or document
+
+        Takes either a parse ID or a document and a schema, then returns the fields. A multipart input is limited to 50 MB and to the supported extensions: bmp, docx, heic, jpeg, jpg, pdf, png, pptx, tiff.
+
+        :param extract_request: (required)
+        :type extract_request: ExtractRequest
+        :param prefer: Wait up to this many seconds for completed extraction.
+        :type prefer: str
+        :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._extract_run_serialize(
+            extract_request=extract_request,
+            prefer=prefer,
+            _request_auth=_request_auth,
+            _content_type=_content_type,
+            _headers=_headers,
+            _host_index=_host_index
+        )
+
+        _response_types_map: Dict[str, Optional[str]] = {
+            '200': "ParseResult",
+            '202': "JobAccepted",
+            '400': "Error",
+            '401': "Error",
+            '404': "Error",
+            '409': "Error",
+            '413': "Error",
+            '415': "Error",
+        }
+        response_data = self.api_client.call_api(
+            *_param,
+            _request_timeout=_request_timeout
+        )
+        return response_data.response
+
+
+    def _extract_run_serialize(
+        self,
+        extract_request,
+        prefer,
+        _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, Optional[str]] = _headers or {}
+        _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
+        # process the query parameters
+        # process the header parameters
+        if prefer is not None:
+            _header_params['Prefer'] = prefer
+        # process the form parameters
+        # process the body parameter
+        if extract_request is not None:
+            _body_params = extract_request
+
+
+        # set the HTTP header `Accept`
+        if 'Accept' not in _header_params:
+            _header_params['Accept'] = self.api_client.select_header_accept(
+                [
+                    'application/json'
+                ]
+            )
+
+        # set the HTTP header `Content-Type`
+        if _content_type:
+            _header_params['Content-Type'] = _content_type
+        else:
+            _default_content_type = (
+                self.api_client.select_header_content_type(
+                    [
+                        'application/json', 
+                        'multipart/form-data'
+                    ]
+                )
+            )
+            if _default_content_type is not None:
+                _header_params['Content-Type'] = _default_content_type
+
+        # authentication setting
+        _auth_settings: List[str] = [
+            'ApiKeyAuth', 
+            'BearerAuth'
+        ]
+
+        return self.api_client.param_serialize(
+            method='POST',
+            resource_path='/api/v2/extract',
+            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
+        )
+
+