vectorize_client.api.extraction_api

Vectorize API

API for Vectorize services (Beta)

The version of the OpenAPI document: 0.1.2 Generated by OpenAPI Generator (https://openapi-generator.tech)

Do not edit the class manually.

  1# coding: utf-8
  2
  3"""
  4    Vectorize API
  5
  6    API for Vectorize services (Beta)
  7
  8    The version of the OpenAPI document: 0.1.2
  9    Generated by OpenAPI Generator (https://openapi-generator.tech)
 10
 11    Do not edit the class manually.
 12"""  # noqa: E501
 13
 14import warnings
 15from pydantic import validate_call, Field, StrictFloat, StrictStr, StrictInt
 16from typing import Any, Dict, List, Optional, Tuple, Union
 17from typing_extensions import Annotated
 18
 19from pydantic import StrictStr
 20from vectorize_client.models.extraction_result_response import ExtractionResultResponse
 21from vectorize_client.models.start_extraction_request import StartExtractionRequest
 22from vectorize_client.models.start_extraction_response import StartExtractionResponse
 23
 24from vectorize_client.api_client import ApiClient, RequestSerialized
 25from vectorize_client.api_response import ApiResponse
 26from vectorize_client.rest import RESTResponseType
 27
 28
 29class ExtractionApi:
 30    """NOTE: This class is auto generated by OpenAPI Generator
 31    Ref: https://openapi-generator.tech
 32
 33    Do not edit the class manually.
 34    """
 35
 36    def __init__(self, api_client=None) -> None:
 37        if api_client is None:
 38            api_client = ApiClient.get_default()
 39        self.api_client = api_client
 40
 41
 42    @validate_call
 43    def get_extraction_result(
 44        self,
 45        organization_id: StrictStr,
 46        extraction_id: StrictStr,
 47        _request_timeout: Union[
 48            None,
 49            Annotated[StrictFloat, Field(gt=0)],
 50            Tuple[
 51                Annotated[StrictFloat, Field(gt=0)],
 52                Annotated[StrictFloat, Field(gt=0)]
 53            ]
 54        ] = None,
 55        _request_auth: Optional[Dict[StrictStr, Any]] = None,
 56        _content_type: Optional[StrictStr] = None,
 57        _headers: Optional[Dict[StrictStr, Any]] = None,
 58        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
 59    ) -> ExtractionResultResponse:
 60        """Get extraction result
 61
 62        Get extraction result
 63
 64        :param organization_id: (required)
 65        :type organization_id: str
 66        :param extraction_id: (required)
 67        :type extraction_id: str
 68        :param _request_timeout: timeout setting for this request. If one
 69                                 number provided, it will be total request
 70                                 timeout. It can also be a pair (tuple) of
 71                                 (connection, read) timeouts.
 72        :type _request_timeout: int, tuple(int, int), optional
 73        :param _request_auth: set to override the auth_settings for an a single
 74                              request; this effectively ignores the
 75                              authentication in the spec for a single request.
 76        :type _request_auth: dict, optional
 77        :param _content_type: force content-type for the request.
 78        :type _content_type: str, Optional
 79        :param _headers: set to override the headers for a single
 80                         request; this effectively ignores the headers
 81                         in the spec for a single request.
 82        :type _headers: dict, optional
 83        :param _host_index: set to override the host_index for a single
 84                            request; this effectively ignores the host_index
 85                            in the spec for a single request.
 86        :type _host_index: int, optional
 87        :return: Returns the result object.
 88        """ # noqa: E501
 89
 90        _param = self._get_extraction_result_serialize(
 91            organization_id=organization_id,
 92            extraction_id=extraction_id,
 93            _request_auth=_request_auth,
 94            _content_type=_content_type,
 95            _headers=_headers,
 96            _host_index=_host_index
 97        )
 98
 99        _response_types_map: Dict[str, Optional[str]] = {
100            '200': "ExtractionResultResponse",
101            '400': "GetPipelines400Response",
102            '401': "GetPipelines400Response",
103            '403': "GetPipelines400Response",
104            '404': "GetPipelines400Response",
105            '500': "GetPipelines400Response",
106        }
107        response_data = self.api_client.call_api(
108            *_param,
109            _request_timeout=_request_timeout
110        )
111        response_data.read()
112        return self.api_client.response_deserialize(
113            response_data=response_data,
114            response_types_map=_response_types_map,
115        ).data
116
117
118    @validate_call
119    def get_extraction_result_with_http_info(
120        self,
121        organization_id: StrictStr,
122        extraction_id: StrictStr,
123        _request_timeout: Union[
124            None,
125            Annotated[StrictFloat, Field(gt=0)],
126            Tuple[
127                Annotated[StrictFloat, Field(gt=0)],
128                Annotated[StrictFloat, Field(gt=0)]
129            ]
130        ] = None,
131        _request_auth: Optional[Dict[StrictStr, Any]] = None,
132        _content_type: Optional[StrictStr] = None,
133        _headers: Optional[Dict[StrictStr, Any]] = None,
134        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
135    ) -> ApiResponse[ExtractionResultResponse]:
136        """Get extraction result
137
138        Get extraction result
139
140        :param organization_id: (required)
141        :type organization_id: str
142        :param extraction_id: (required)
143        :type extraction_id: str
144        :param _request_timeout: timeout setting for this request. If one
145                                 number provided, it will be total request
146                                 timeout. It can also be a pair (tuple) of
147                                 (connection, read) timeouts.
148        :type _request_timeout: int, tuple(int, int), optional
149        :param _request_auth: set to override the auth_settings for an a single
150                              request; this effectively ignores the
151                              authentication in the spec for a single request.
152        :type _request_auth: dict, optional
153        :param _content_type: force content-type for the request.
154        :type _content_type: str, Optional
155        :param _headers: set to override the headers for a single
156                         request; this effectively ignores the headers
157                         in the spec for a single request.
158        :type _headers: dict, optional
159        :param _host_index: set to override the host_index for a single
160                            request; this effectively ignores the host_index
161                            in the spec for a single request.
162        :type _host_index: int, optional
163        :return: Returns the result object.
164        """ # noqa: E501
165
166        _param = self._get_extraction_result_serialize(
167            organization_id=organization_id,
168            extraction_id=extraction_id,
169            _request_auth=_request_auth,
170            _content_type=_content_type,
171            _headers=_headers,
172            _host_index=_host_index
173        )
174
175        _response_types_map: Dict[str, Optional[str]] = {
176            '200': "ExtractionResultResponse",
177            '400': "GetPipelines400Response",
178            '401': "GetPipelines400Response",
179            '403': "GetPipelines400Response",
180            '404': "GetPipelines400Response",
181            '500': "GetPipelines400Response",
182        }
183        response_data = self.api_client.call_api(
184            *_param,
185            _request_timeout=_request_timeout
186        )
187        response_data.read()
188        return self.api_client.response_deserialize(
189            response_data=response_data,
190            response_types_map=_response_types_map,
191        )
192
193
194    @validate_call
195    def get_extraction_result_without_preload_content(
196        self,
197        organization_id: StrictStr,
198        extraction_id: StrictStr,
199        _request_timeout: Union[
200            None,
201            Annotated[StrictFloat, Field(gt=0)],
202            Tuple[
203                Annotated[StrictFloat, Field(gt=0)],
204                Annotated[StrictFloat, Field(gt=0)]
205            ]
206        ] = None,
207        _request_auth: Optional[Dict[StrictStr, Any]] = None,
208        _content_type: Optional[StrictStr] = None,
209        _headers: Optional[Dict[StrictStr, Any]] = None,
210        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
211    ) -> RESTResponseType:
212        """Get extraction result
213
214        Get extraction result
215
216        :param organization_id: (required)
217        :type organization_id: str
218        :param extraction_id: (required)
219        :type extraction_id: str
220        :param _request_timeout: timeout setting for this request. If one
221                                 number provided, it will be total request
222                                 timeout. It can also be a pair (tuple) of
223                                 (connection, read) timeouts.
224        :type _request_timeout: int, tuple(int, int), optional
225        :param _request_auth: set to override the auth_settings for an a single
226                              request; this effectively ignores the
227                              authentication in the spec for a single request.
228        :type _request_auth: dict, optional
229        :param _content_type: force content-type for the request.
230        :type _content_type: str, Optional
231        :param _headers: set to override the headers for a single
232                         request; this effectively ignores the headers
233                         in the spec for a single request.
234        :type _headers: dict, optional
235        :param _host_index: set to override the host_index for a single
236                            request; this effectively ignores the host_index
237                            in the spec for a single request.
238        :type _host_index: int, optional
239        :return: Returns the result object.
240        """ # noqa: E501
241
242        _param = self._get_extraction_result_serialize(
243            organization_id=organization_id,
244            extraction_id=extraction_id,
245            _request_auth=_request_auth,
246            _content_type=_content_type,
247            _headers=_headers,
248            _host_index=_host_index
249        )
250
251        _response_types_map: Dict[str, Optional[str]] = {
252            '200': "ExtractionResultResponse",
253            '400': "GetPipelines400Response",
254            '401': "GetPipelines400Response",
255            '403': "GetPipelines400Response",
256            '404': "GetPipelines400Response",
257            '500': "GetPipelines400Response",
258        }
259        response_data = self.api_client.call_api(
260            *_param,
261            _request_timeout=_request_timeout
262        )
263        return response_data.response
264
265
266    def _get_extraction_result_serialize(
267        self,
268        organization_id,
269        extraction_id,
270        _request_auth,
271        _content_type,
272        _headers,
273        _host_index,
274    ) -> RequestSerialized:
275
276        _host = None
277
278        _collection_formats: Dict[str, str] = {
279        }
280
281        _path_params: Dict[str, str] = {}
282        _query_params: List[Tuple[str, str]] = []
283        _header_params: Dict[str, Optional[str]] = _headers or {}
284        _form_params: List[Tuple[str, str]] = []
285        _files: Dict[
286            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
287        ] = {}
288        _body_params: Optional[bytes] = None
289
290        # process the path parameters
291        if organization_id is not None:
292            _path_params['organizationId'] = organization_id
293        if extraction_id is not None:
294            _path_params['extractionId'] = extraction_id
295        # process the query parameters
296        # process the header parameters
297        # process the form parameters
298        # process the body parameter
299
300
301        # set the HTTP header `Accept`
302        if 'Accept' not in _header_params:
303            _header_params['Accept'] = self.api_client.select_header_accept(
304                [
305                    'application/json'
306                ]
307            )
308
309
310        # authentication setting
311        _auth_settings: List[str] = [
312            'bearerAuth'
313        ]
314
315        return self.api_client.param_serialize(
316            method='GET',
317            resource_path='/org/{organizationId}/extraction/{extractionId}',
318            path_params=_path_params,
319            query_params=_query_params,
320            header_params=_header_params,
321            body=_body_params,
322            post_params=_form_params,
323            files=_files,
324            auth_settings=_auth_settings,
325            collection_formats=_collection_formats,
326            _host=_host,
327            _request_auth=_request_auth
328        )
329
330
331
332
333    @validate_call
334    def start_extraction(
335        self,
336        organization_id: StrictStr,
337        start_extraction_request: StartExtractionRequest,
338        _request_timeout: Union[
339            None,
340            Annotated[StrictFloat, Field(gt=0)],
341            Tuple[
342                Annotated[StrictFloat, Field(gt=0)],
343                Annotated[StrictFloat, Field(gt=0)]
344            ]
345        ] = None,
346        _request_auth: Optional[Dict[StrictStr, Any]] = None,
347        _content_type: Optional[StrictStr] = None,
348        _headers: Optional[Dict[StrictStr, Any]] = None,
349        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
350    ) -> StartExtractionResponse:
351        """Start content extraction from a file
352
353        Start content extraction from a file
354
355        :param organization_id: (required)
356        :type organization_id: str
357        :param start_extraction_request: (required)
358        :type start_extraction_request: StartExtractionRequest
359        :param _request_timeout: timeout setting for this request. If one
360                                 number provided, it will be total request
361                                 timeout. It can also be a pair (tuple) of
362                                 (connection, read) timeouts.
363        :type _request_timeout: int, tuple(int, int), optional
364        :param _request_auth: set to override the auth_settings for an a single
365                              request; this effectively ignores the
366                              authentication in the spec for a single request.
367        :type _request_auth: dict, optional
368        :param _content_type: force content-type for the request.
369        :type _content_type: str, Optional
370        :param _headers: set to override the headers for a single
371                         request; this effectively ignores the headers
372                         in the spec for a single request.
373        :type _headers: dict, optional
374        :param _host_index: set to override the host_index for a single
375                            request; this effectively ignores the host_index
376                            in the spec for a single request.
377        :type _host_index: int, optional
378        :return: Returns the result object.
379        """ # noqa: E501
380
381        _param = self._start_extraction_serialize(
382            organization_id=organization_id,
383            start_extraction_request=start_extraction_request,
384            _request_auth=_request_auth,
385            _content_type=_content_type,
386            _headers=_headers,
387            _host_index=_host_index
388        )
389
390        _response_types_map: Dict[str, Optional[str]] = {
391            '200': "StartExtractionResponse",
392            '400': "GetPipelines400Response",
393            '401': "GetPipelines400Response",
394            '403': "GetPipelines400Response",
395            '404': "GetPipelines400Response",
396            '500': "GetPipelines400Response",
397        }
398        response_data = self.api_client.call_api(
399            *_param,
400            _request_timeout=_request_timeout
401        )
402        response_data.read()
403        return self.api_client.response_deserialize(
404            response_data=response_data,
405            response_types_map=_response_types_map,
406        ).data
407
408
409    @validate_call
410    def start_extraction_with_http_info(
411        self,
412        organization_id: StrictStr,
413        start_extraction_request: StartExtractionRequest,
414        _request_timeout: Union[
415            None,
416            Annotated[StrictFloat, Field(gt=0)],
417            Tuple[
418                Annotated[StrictFloat, Field(gt=0)],
419                Annotated[StrictFloat, Field(gt=0)]
420            ]
421        ] = None,
422        _request_auth: Optional[Dict[StrictStr, Any]] = None,
423        _content_type: Optional[StrictStr] = None,
424        _headers: Optional[Dict[StrictStr, Any]] = None,
425        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
426    ) -> ApiResponse[StartExtractionResponse]:
427        """Start content extraction from a file
428
429        Start content extraction from a file
430
431        :param organization_id: (required)
432        :type organization_id: str
433        :param start_extraction_request: (required)
434        :type start_extraction_request: StartExtractionRequest
435        :param _request_timeout: timeout setting for this request. If one
436                                 number provided, it will be total request
437                                 timeout. It can also be a pair (tuple) of
438                                 (connection, read) timeouts.
439        :type _request_timeout: int, tuple(int, int), optional
440        :param _request_auth: set to override the auth_settings for an a single
441                              request; this effectively ignores the
442                              authentication in the spec for a single request.
443        :type _request_auth: dict, optional
444        :param _content_type: force content-type for the request.
445        :type _content_type: str, Optional
446        :param _headers: set to override the headers for a single
447                         request; this effectively ignores the headers
448                         in the spec for a single request.
449        :type _headers: dict, optional
450        :param _host_index: set to override the host_index for a single
451                            request; this effectively ignores the host_index
452                            in the spec for a single request.
453        :type _host_index: int, optional
454        :return: Returns the result object.
455        """ # noqa: E501
456
457        _param = self._start_extraction_serialize(
458            organization_id=organization_id,
459            start_extraction_request=start_extraction_request,
460            _request_auth=_request_auth,
461            _content_type=_content_type,
462            _headers=_headers,
463            _host_index=_host_index
464        )
465
466        _response_types_map: Dict[str, Optional[str]] = {
467            '200': "StartExtractionResponse",
468            '400': "GetPipelines400Response",
469            '401': "GetPipelines400Response",
470            '403': "GetPipelines400Response",
471            '404': "GetPipelines400Response",
472            '500': "GetPipelines400Response",
473        }
474        response_data = self.api_client.call_api(
475            *_param,
476            _request_timeout=_request_timeout
477        )
478        response_data.read()
479        return self.api_client.response_deserialize(
480            response_data=response_data,
481            response_types_map=_response_types_map,
482        )
483
484
485    @validate_call
486    def start_extraction_without_preload_content(
487        self,
488        organization_id: StrictStr,
489        start_extraction_request: StartExtractionRequest,
490        _request_timeout: Union[
491            None,
492            Annotated[StrictFloat, Field(gt=0)],
493            Tuple[
494                Annotated[StrictFloat, Field(gt=0)],
495                Annotated[StrictFloat, Field(gt=0)]
496            ]
497        ] = None,
498        _request_auth: Optional[Dict[StrictStr, Any]] = None,
499        _content_type: Optional[StrictStr] = None,
500        _headers: Optional[Dict[StrictStr, Any]] = None,
501        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
502    ) -> RESTResponseType:
503        """Start content extraction from a file
504
505        Start content extraction from a file
506
507        :param organization_id: (required)
508        :type organization_id: str
509        :param start_extraction_request: (required)
510        :type start_extraction_request: StartExtractionRequest
511        :param _request_timeout: timeout setting for this request. If one
512                                 number provided, it will be total request
513                                 timeout. It can also be a pair (tuple) of
514                                 (connection, read) timeouts.
515        :type _request_timeout: int, tuple(int, int), optional
516        :param _request_auth: set to override the auth_settings for an a single
517                              request; this effectively ignores the
518                              authentication in the spec for a single request.
519        :type _request_auth: dict, optional
520        :param _content_type: force content-type for the request.
521        :type _content_type: str, Optional
522        :param _headers: set to override the headers for a single
523                         request; this effectively ignores the headers
524                         in the spec for a single request.
525        :type _headers: dict, optional
526        :param _host_index: set to override the host_index for a single
527                            request; this effectively ignores the host_index
528                            in the spec for a single request.
529        :type _host_index: int, optional
530        :return: Returns the result object.
531        """ # noqa: E501
532
533        _param = self._start_extraction_serialize(
534            organization_id=organization_id,
535            start_extraction_request=start_extraction_request,
536            _request_auth=_request_auth,
537            _content_type=_content_type,
538            _headers=_headers,
539            _host_index=_host_index
540        )
541
542        _response_types_map: Dict[str, Optional[str]] = {
543            '200': "StartExtractionResponse",
544            '400': "GetPipelines400Response",
545            '401': "GetPipelines400Response",
546            '403': "GetPipelines400Response",
547            '404': "GetPipelines400Response",
548            '500': "GetPipelines400Response",
549        }
550        response_data = self.api_client.call_api(
551            *_param,
552            _request_timeout=_request_timeout
553        )
554        return response_data.response
555
556
557    def _start_extraction_serialize(
558        self,
559        organization_id,
560        start_extraction_request,
561        _request_auth,
562        _content_type,
563        _headers,
564        _host_index,
565    ) -> RequestSerialized:
566
567        _host = None
568
569        _collection_formats: Dict[str, str] = {
570        }
571
572        _path_params: Dict[str, str] = {}
573        _query_params: List[Tuple[str, str]] = []
574        _header_params: Dict[str, Optional[str]] = _headers or {}
575        _form_params: List[Tuple[str, str]] = []
576        _files: Dict[
577            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
578        ] = {}
579        _body_params: Optional[bytes] = None
580
581        # process the path parameters
582        if organization_id is not None:
583            _path_params['organizationId'] = organization_id
584        # process the query parameters
585        # process the header parameters
586        # process the form parameters
587        # process the body parameter
588        if start_extraction_request is not None:
589            _body_params = start_extraction_request
590
591
592        # set the HTTP header `Accept`
593        if 'Accept' not in _header_params:
594            _header_params['Accept'] = self.api_client.select_header_accept(
595                [
596                    'application/json'
597                ]
598            )
599
600        # set the HTTP header `Content-Type`
601        if _content_type:
602            _header_params['Content-Type'] = _content_type
603        else:
604            _default_content_type = (
605                self.api_client.select_header_content_type(
606                    [
607                        'application/json'
608                    ]
609                )
610            )
611            if _default_content_type is not None:
612                _header_params['Content-Type'] = _default_content_type
613
614        # authentication setting
615        _auth_settings: List[str] = [
616            'bearerAuth'
617        ]
618
619        return self.api_client.param_serialize(
620            method='POST',
621            resource_path='/org/{organizationId}/extraction',
622            path_params=_path_params,
623            query_params=_query_params,
624            header_params=_header_params,
625            body=_body_params,
626            post_params=_form_params,
627            files=_files,
628            auth_settings=_auth_settings,
629            collection_formats=_collection_formats,
630            _host=_host,
631            _request_auth=_request_auth
632        )
class ExtractionApi:
 30class ExtractionApi:
 31    """NOTE: This class is auto generated by OpenAPI Generator
 32    Ref: https://openapi-generator.tech
 33
 34    Do not edit the class manually.
 35    """
 36
 37    def __init__(self, api_client=None) -> None:
 38        if api_client is None:
 39            api_client = ApiClient.get_default()
 40        self.api_client = api_client
 41
 42
 43    @validate_call
 44    def get_extraction_result(
 45        self,
 46        organization_id: StrictStr,
 47        extraction_id: StrictStr,
 48        _request_timeout: Union[
 49            None,
 50            Annotated[StrictFloat, Field(gt=0)],
 51            Tuple[
 52                Annotated[StrictFloat, Field(gt=0)],
 53                Annotated[StrictFloat, Field(gt=0)]
 54            ]
 55        ] = None,
 56        _request_auth: Optional[Dict[StrictStr, Any]] = None,
 57        _content_type: Optional[StrictStr] = None,
 58        _headers: Optional[Dict[StrictStr, Any]] = None,
 59        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
 60    ) -> ExtractionResultResponse:
 61        """Get extraction result
 62
 63        Get extraction result
 64
 65        :param organization_id: (required)
 66        :type organization_id: str
 67        :param extraction_id: (required)
 68        :type extraction_id: str
 69        :param _request_timeout: timeout setting for this request. If one
 70                                 number provided, it will be total request
 71                                 timeout. It can also be a pair (tuple) of
 72                                 (connection, read) timeouts.
 73        :type _request_timeout: int, tuple(int, int), optional
 74        :param _request_auth: set to override the auth_settings for an a single
 75                              request; this effectively ignores the
 76                              authentication in the spec for a single request.
 77        :type _request_auth: dict, optional
 78        :param _content_type: force content-type for the request.
 79        :type _content_type: str, Optional
 80        :param _headers: set to override the headers for a single
 81                         request; this effectively ignores the headers
 82                         in the spec for a single request.
 83        :type _headers: dict, optional
 84        :param _host_index: set to override the host_index for a single
 85                            request; this effectively ignores the host_index
 86                            in the spec for a single request.
 87        :type _host_index: int, optional
 88        :return: Returns the result object.
 89        """ # noqa: E501
 90
 91        _param = self._get_extraction_result_serialize(
 92            organization_id=organization_id,
 93            extraction_id=extraction_id,
 94            _request_auth=_request_auth,
 95            _content_type=_content_type,
 96            _headers=_headers,
 97            _host_index=_host_index
 98        )
 99
100        _response_types_map: Dict[str, Optional[str]] = {
101            '200': "ExtractionResultResponse",
102            '400': "GetPipelines400Response",
103            '401': "GetPipelines400Response",
104            '403': "GetPipelines400Response",
105            '404': "GetPipelines400Response",
106            '500': "GetPipelines400Response",
107        }
108        response_data = self.api_client.call_api(
109            *_param,
110            _request_timeout=_request_timeout
111        )
112        response_data.read()
113        return self.api_client.response_deserialize(
114            response_data=response_data,
115            response_types_map=_response_types_map,
116        ).data
117
118
119    @validate_call
120    def get_extraction_result_with_http_info(
121        self,
122        organization_id: StrictStr,
123        extraction_id: StrictStr,
124        _request_timeout: Union[
125            None,
126            Annotated[StrictFloat, Field(gt=0)],
127            Tuple[
128                Annotated[StrictFloat, Field(gt=0)],
129                Annotated[StrictFloat, Field(gt=0)]
130            ]
131        ] = None,
132        _request_auth: Optional[Dict[StrictStr, Any]] = None,
133        _content_type: Optional[StrictStr] = None,
134        _headers: Optional[Dict[StrictStr, Any]] = None,
135        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
136    ) -> ApiResponse[ExtractionResultResponse]:
137        """Get extraction result
138
139        Get extraction result
140
141        :param organization_id: (required)
142        :type organization_id: str
143        :param extraction_id: (required)
144        :type extraction_id: str
145        :param _request_timeout: timeout setting for this request. If one
146                                 number provided, it will be total request
147                                 timeout. It can also be a pair (tuple) of
148                                 (connection, read) timeouts.
149        :type _request_timeout: int, tuple(int, int), optional
150        :param _request_auth: set to override the auth_settings for an a single
151                              request; this effectively ignores the
152                              authentication in the spec for a single request.
153        :type _request_auth: dict, optional
154        :param _content_type: force content-type for the request.
155        :type _content_type: str, Optional
156        :param _headers: set to override the headers for a single
157                         request; this effectively ignores the headers
158                         in the spec for a single request.
159        :type _headers: dict, optional
160        :param _host_index: set to override the host_index for a single
161                            request; this effectively ignores the host_index
162                            in the spec for a single request.
163        :type _host_index: int, optional
164        :return: Returns the result object.
165        """ # noqa: E501
166
167        _param = self._get_extraction_result_serialize(
168            organization_id=organization_id,
169            extraction_id=extraction_id,
170            _request_auth=_request_auth,
171            _content_type=_content_type,
172            _headers=_headers,
173            _host_index=_host_index
174        )
175
176        _response_types_map: Dict[str, Optional[str]] = {
177            '200': "ExtractionResultResponse",
178            '400': "GetPipelines400Response",
179            '401': "GetPipelines400Response",
180            '403': "GetPipelines400Response",
181            '404': "GetPipelines400Response",
182            '500': "GetPipelines400Response",
183        }
184        response_data = self.api_client.call_api(
185            *_param,
186            _request_timeout=_request_timeout
187        )
188        response_data.read()
189        return self.api_client.response_deserialize(
190            response_data=response_data,
191            response_types_map=_response_types_map,
192        )
193
194
195    @validate_call
196    def get_extraction_result_without_preload_content(
197        self,
198        organization_id: StrictStr,
199        extraction_id: StrictStr,
200        _request_timeout: Union[
201            None,
202            Annotated[StrictFloat, Field(gt=0)],
203            Tuple[
204                Annotated[StrictFloat, Field(gt=0)],
205                Annotated[StrictFloat, Field(gt=0)]
206            ]
207        ] = None,
208        _request_auth: Optional[Dict[StrictStr, Any]] = None,
209        _content_type: Optional[StrictStr] = None,
210        _headers: Optional[Dict[StrictStr, Any]] = None,
211        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
212    ) -> RESTResponseType:
213        """Get extraction result
214
215        Get extraction result
216
217        :param organization_id: (required)
218        :type organization_id: str
219        :param extraction_id: (required)
220        :type extraction_id: str
221        :param _request_timeout: timeout setting for this request. If one
222                                 number provided, it will be total request
223                                 timeout. It can also be a pair (tuple) of
224                                 (connection, read) timeouts.
225        :type _request_timeout: int, tuple(int, int), optional
226        :param _request_auth: set to override the auth_settings for an a single
227                              request; this effectively ignores the
228                              authentication in the spec for a single request.
229        :type _request_auth: dict, optional
230        :param _content_type: force content-type for the request.
231        :type _content_type: str, Optional
232        :param _headers: set to override the headers for a single
233                         request; this effectively ignores the headers
234                         in the spec for a single request.
235        :type _headers: dict, optional
236        :param _host_index: set to override the host_index for a single
237                            request; this effectively ignores the host_index
238                            in the spec for a single request.
239        :type _host_index: int, optional
240        :return: Returns the result object.
241        """ # noqa: E501
242
243        _param = self._get_extraction_result_serialize(
244            organization_id=organization_id,
245            extraction_id=extraction_id,
246            _request_auth=_request_auth,
247            _content_type=_content_type,
248            _headers=_headers,
249            _host_index=_host_index
250        )
251
252        _response_types_map: Dict[str, Optional[str]] = {
253            '200': "ExtractionResultResponse",
254            '400': "GetPipelines400Response",
255            '401': "GetPipelines400Response",
256            '403': "GetPipelines400Response",
257            '404': "GetPipelines400Response",
258            '500': "GetPipelines400Response",
259        }
260        response_data = self.api_client.call_api(
261            *_param,
262            _request_timeout=_request_timeout
263        )
264        return response_data.response
265
266
267    def _get_extraction_result_serialize(
268        self,
269        organization_id,
270        extraction_id,
271        _request_auth,
272        _content_type,
273        _headers,
274        _host_index,
275    ) -> RequestSerialized:
276
277        _host = None
278
279        _collection_formats: Dict[str, str] = {
280        }
281
282        _path_params: Dict[str, str] = {}
283        _query_params: List[Tuple[str, str]] = []
284        _header_params: Dict[str, Optional[str]] = _headers or {}
285        _form_params: List[Tuple[str, str]] = []
286        _files: Dict[
287            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
288        ] = {}
289        _body_params: Optional[bytes] = None
290
291        # process the path parameters
292        if organization_id is not None:
293            _path_params['organizationId'] = organization_id
294        if extraction_id is not None:
295            _path_params['extractionId'] = extraction_id
296        # process the query parameters
297        # process the header parameters
298        # process the form parameters
299        # process the body parameter
300
301
302        # set the HTTP header `Accept`
303        if 'Accept' not in _header_params:
304            _header_params['Accept'] = self.api_client.select_header_accept(
305                [
306                    'application/json'
307                ]
308            )
309
310
311        # authentication setting
312        _auth_settings: List[str] = [
313            'bearerAuth'
314        ]
315
316        return self.api_client.param_serialize(
317            method='GET',
318            resource_path='/org/{organizationId}/extraction/{extractionId}',
319            path_params=_path_params,
320            query_params=_query_params,
321            header_params=_header_params,
322            body=_body_params,
323            post_params=_form_params,
324            files=_files,
325            auth_settings=_auth_settings,
326            collection_formats=_collection_formats,
327            _host=_host,
328            _request_auth=_request_auth
329        )
330
331
332
333
334    @validate_call
335    def start_extraction(
336        self,
337        organization_id: StrictStr,
338        start_extraction_request: StartExtractionRequest,
339        _request_timeout: Union[
340            None,
341            Annotated[StrictFloat, Field(gt=0)],
342            Tuple[
343                Annotated[StrictFloat, Field(gt=0)],
344                Annotated[StrictFloat, Field(gt=0)]
345            ]
346        ] = None,
347        _request_auth: Optional[Dict[StrictStr, Any]] = None,
348        _content_type: Optional[StrictStr] = None,
349        _headers: Optional[Dict[StrictStr, Any]] = None,
350        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
351    ) -> StartExtractionResponse:
352        """Start content extraction from a file
353
354        Start content extraction from a file
355
356        :param organization_id: (required)
357        :type organization_id: str
358        :param start_extraction_request: (required)
359        :type start_extraction_request: StartExtractionRequest
360        :param _request_timeout: timeout setting for this request. If one
361                                 number provided, it will be total request
362                                 timeout. It can also be a pair (tuple) of
363                                 (connection, read) timeouts.
364        :type _request_timeout: int, tuple(int, int), optional
365        :param _request_auth: set to override the auth_settings for an a single
366                              request; this effectively ignores the
367                              authentication in the spec for a single request.
368        :type _request_auth: dict, optional
369        :param _content_type: force content-type for the request.
370        :type _content_type: str, Optional
371        :param _headers: set to override the headers for a single
372                         request; this effectively ignores the headers
373                         in the spec for a single request.
374        :type _headers: dict, optional
375        :param _host_index: set to override the host_index for a single
376                            request; this effectively ignores the host_index
377                            in the spec for a single request.
378        :type _host_index: int, optional
379        :return: Returns the result object.
380        """ # noqa: E501
381
382        _param = self._start_extraction_serialize(
383            organization_id=organization_id,
384            start_extraction_request=start_extraction_request,
385            _request_auth=_request_auth,
386            _content_type=_content_type,
387            _headers=_headers,
388            _host_index=_host_index
389        )
390
391        _response_types_map: Dict[str, Optional[str]] = {
392            '200': "StartExtractionResponse",
393            '400': "GetPipelines400Response",
394            '401': "GetPipelines400Response",
395            '403': "GetPipelines400Response",
396            '404': "GetPipelines400Response",
397            '500': "GetPipelines400Response",
398        }
399        response_data = self.api_client.call_api(
400            *_param,
401            _request_timeout=_request_timeout
402        )
403        response_data.read()
404        return self.api_client.response_deserialize(
405            response_data=response_data,
406            response_types_map=_response_types_map,
407        ).data
408
409
410    @validate_call
411    def start_extraction_with_http_info(
412        self,
413        organization_id: StrictStr,
414        start_extraction_request: StartExtractionRequest,
415        _request_timeout: Union[
416            None,
417            Annotated[StrictFloat, Field(gt=0)],
418            Tuple[
419                Annotated[StrictFloat, Field(gt=0)],
420                Annotated[StrictFloat, Field(gt=0)]
421            ]
422        ] = None,
423        _request_auth: Optional[Dict[StrictStr, Any]] = None,
424        _content_type: Optional[StrictStr] = None,
425        _headers: Optional[Dict[StrictStr, Any]] = None,
426        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
427    ) -> ApiResponse[StartExtractionResponse]:
428        """Start content extraction from a file
429
430        Start content extraction from a file
431
432        :param organization_id: (required)
433        :type organization_id: str
434        :param start_extraction_request: (required)
435        :type start_extraction_request: StartExtractionRequest
436        :param _request_timeout: timeout setting for this request. If one
437                                 number provided, it will be total request
438                                 timeout. It can also be a pair (tuple) of
439                                 (connection, read) timeouts.
440        :type _request_timeout: int, tuple(int, int), optional
441        :param _request_auth: set to override the auth_settings for an a single
442                              request; this effectively ignores the
443                              authentication in the spec for a single request.
444        :type _request_auth: dict, optional
445        :param _content_type: force content-type for the request.
446        :type _content_type: str, Optional
447        :param _headers: set to override the headers for a single
448                         request; this effectively ignores the headers
449                         in the spec for a single request.
450        :type _headers: dict, optional
451        :param _host_index: set to override the host_index for a single
452                            request; this effectively ignores the host_index
453                            in the spec for a single request.
454        :type _host_index: int, optional
455        :return: Returns the result object.
456        """ # noqa: E501
457
458        _param = self._start_extraction_serialize(
459            organization_id=organization_id,
460            start_extraction_request=start_extraction_request,
461            _request_auth=_request_auth,
462            _content_type=_content_type,
463            _headers=_headers,
464            _host_index=_host_index
465        )
466
467        _response_types_map: Dict[str, Optional[str]] = {
468            '200': "StartExtractionResponse",
469            '400': "GetPipelines400Response",
470            '401': "GetPipelines400Response",
471            '403': "GetPipelines400Response",
472            '404': "GetPipelines400Response",
473            '500': "GetPipelines400Response",
474        }
475        response_data = self.api_client.call_api(
476            *_param,
477            _request_timeout=_request_timeout
478        )
479        response_data.read()
480        return self.api_client.response_deserialize(
481            response_data=response_data,
482            response_types_map=_response_types_map,
483        )
484
485
486    @validate_call
487    def start_extraction_without_preload_content(
488        self,
489        organization_id: StrictStr,
490        start_extraction_request: StartExtractionRequest,
491        _request_timeout: Union[
492            None,
493            Annotated[StrictFloat, Field(gt=0)],
494            Tuple[
495                Annotated[StrictFloat, Field(gt=0)],
496                Annotated[StrictFloat, Field(gt=0)]
497            ]
498        ] = None,
499        _request_auth: Optional[Dict[StrictStr, Any]] = None,
500        _content_type: Optional[StrictStr] = None,
501        _headers: Optional[Dict[StrictStr, Any]] = None,
502        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
503    ) -> RESTResponseType:
504        """Start content extraction from a file
505
506        Start content extraction from a file
507
508        :param organization_id: (required)
509        :type organization_id: str
510        :param start_extraction_request: (required)
511        :type start_extraction_request: StartExtractionRequest
512        :param _request_timeout: timeout setting for this request. If one
513                                 number provided, it will be total request
514                                 timeout. It can also be a pair (tuple) of
515                                 (connection, read) timeouts.
516        :type _request_timeout: int, tuple(int, int), optional
517        :param _request_auth: set to override the auth_settings for an a single
518                              request; this effectively ignores the
519                              authentication in the spec for a single request.
520        :type _request_auth: dict, optional
521        :param _content_type: force content-type for the request.
522        :type _content_type: str, Optional
523        :param _headers: set to override the headers for a single
524                         request; this effectively ignores the headers
525                         in the spec for a single request.
526        :type _headers: dict, optional
527        :param _host_index: set to override the host_index for a single
528                            request; this effectively ignores the host_index
529                            in the spec for a single request.
530        :type _host_index: int, optional
531        :return: Returns the result object.
532        """ # noqa: E501
533
534        _param = self._start_extraction_serialize(
535            organization_id=organization_id,
536            start_extraction_request=start_extraction_request,
537            _request_auth=_request_auth,
538            _content_type=_content_type,
539            _headers=_headers,
540            _host_index=_host_index
541        )
542
543        _response_types_map: Dict[str, Optional[str]] = {
544            '200': "StartExtractionResponse",
545            '400': "GetPipelines400Response",
546            '401': "GetPipelines400Response",
547            '403': "GetPipelines400Response",
548            '404': "GetPipelines400Response",
549            '500': "GetPipelines400Response",
550        }
551        response_data = self.api_client.call_api(
552            *_param,
553            _request_timeout=_request_timeout
554        )
555        return response_data.response
556
557
558    def _start_extraction_serialize(
559        self,
560        organization_id,
561        start_extraction_request,
562        _request_auth,
563        _content_type,
564        _headers,
565        _host_index,
566    ) -> RequestSerialized:
567
568        _host = None
569
570        _collection_formats: Dict[str, str] = {
571        }
572
573        _path_params: Dict[str, str] = {}
574        _query_params: List[Tuple[str, str]] = []
575        _header_params: Dict[str, Optional[str]] = _headers or {}
576        _form_params: List[Tuple[str, str]] = []
577        _files: Dict[
578            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
579        ] = {}
580        _body_params: Optional[bytes] = None
581
582        # process the path parameters
583        if organization_id is not None:
584            _path_params['organizationId'] = organization_id
585        # process the query parameters
586        # process the header parameters
587        # process the form parameters
588        # process the body parameter
589        if start_extraction_request is not None:
590            _body_params = start_extraction_request
591
592
593        # set the HTTP header `Accept`
594        if 'Accept' not in _header_params:
595            _header_params['Accept'] = self.api_client.select_header_accept(
596                [
597                    'application/json'
598                ]
599            )
600
601        # set the HTTP header `Content-Type`
602        if _content_type:
603            _header_params['Content-Type'] = _content_type
604        else:
605            _default_content_type = (
606                self.api_client.select_header_content_type(
607                    [
608                        'application/json'
609                    ]
610                )
611            )
612            if _default_content_type is not None:
613                _header_params['Content-Type'] = _default_content_type
614
615        # authentication setting
616        _auth_settings: List[str] = [
617            'bearerAuth'
618        ]
619
620        return self.api_client.param_serialize(
621            method='POST',
622            resource_path='/org/{organizationId}/extraction',
623            path_params=_path_params,
624            query_params=_query_params,
625            header_params=_header_params,
626            body=_body_params,
627            post_params=_form_params,
628            files=_files,
629            auth_settings=_auth_settings,
630            collection_formats=_collection_formats,
631            _host=_host,
632            _request_auth=_request_auth
633        )

NOTE: This class is auto generated by OpenAPI Generator Ref: https://openapi-generator.tech

Do not edit the class manually.

ExtractionApi(api_client=None)
37    def __init__(self, api_client=None) -> None:
38        if api_client is None:
39            api_client = ApiClient.get_default()
40        self.api_client = api_client
api_client
@validate_call
def get_extraction_result( self, organization_id: typing.Annotated[str, Strict(strict=True)], extraction_id: typing.Annotated[str, Strict(strict=True)], _request_timeout: Union[NoneType, Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Tuple[Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])]]] = None, _request_auth: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _content_type: Optional[Annotated[str, Strict(strict=True)]] = None, _headers: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _host_index: typing.Annotated[int, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Ge(ge=0), Le(le=0)])] = 0) -> vectorize_client.models.extraction_result_response.ExtractionResultResponse:
 43    @validate_call
 44    def get_extraction_result(
 45        self,
 46        organization_id: StrictStr,
 47        extraction_id: StrictStr,
 48        _request_timeout: Union[
 49            None,
 50            Annotated[StrictFloat, Field(gt=0)],
 51            Tuple[
 52                Annotated[StrictFloat, Field(gt=0)],
 53                Annotated[StrictFloat, Field(gt=0)]
 54            ]
 55        ] = None,
 56        _request_auth: Optional[Dict[StrictStr, Any]] = None,
 57        _content_type: Optional[StrictStr] = None,
 58        _headers: Optional[Dict[StrictStr, Any]] = None,
 59        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
 60    ) -> ExtractionResultResponse:
 61        """Get extraction result
 62
 63        Get extraction result
 64
 65        :param organization_id: (required)
 66        :type organization_id: str
 67        :param extraction_id: (required)
 68        :type extraction_id: str
 69        :param _request_timeout: timeout setting for this request. If one
 70                                 number provided, it will be total request
 71                                 timeout. It can also be a pair (tuple) of
 72                                 (connection, read) timeouts.
 73        :type _request_timeout: int, tuple(int, int), optional
 74        :param _request_auth: set to override the auth_settings for an a single
 75                              request; this effectively ignores the
 76                              authentication in the spec for a single request.
 77        :type _request_auth: dict, optional
 78        :param _content_type: force content-type for the request.
 79        :type _content_type: str, Optional
 80        :param _headers: set to override the headers for a single
 81                         request; this effectively ignores the headers
 82                         in the spec for a single request.
 83        :type _headers: dict, optional
 84        :param _host_index: set to override the host_index for a single
 85                            request; this effectively ignores the host_index
 86                            in the spec for a single request.
 87        :type _host_index: int, optional
 88        :return: Returns the result object.
 89        """ # noqa: E501
 90
 91        _param = self._get_extraction_result_serialize(
 92            organization_id=organization_id,
 93            extraction_id=extraction_id,
 94            _request_auth=_request_auth,
 95            _content_type=_content_type,
 96            _headers=_headers,
 97            _host_index=_host_index
 98        )
 99
100        _response_types_map: Dict[str, Optional[str]] = {
101            '200': "ExtractionResultResponse",
102            '400': "GetPipelines400Response",
103            '401': "GetPipelines400Response",
104            '403': "GetPipelines400Response",
105            '404': "GetPipelines400Response",
106            '500': "GetPipelines400Response",
107        }
108        response_data = self.api_client.call_api(
109            *_param,
110            _request_timeout=_request_timeout
111        )
112        response_data.read()
113        return self.api_client.response_deserialize(
114            response_data=response_data,
115            response_types_map=_response_types_map,
116        ).data

Get extraction result

Get extraction result

Parameters
  • organization_id: (required)
  • extraction_id: (required)
  • _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.
  • _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.
  • _content_type: force content-type for the request.
  • _headers: set to override the headers for a single request; this effectively ignores the headers in the spec for a single request.
  • _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.
Returns

Returns the result object.

@validate_call
def get_extraction_result_with_http_info( self, organization_id: typing.Annotated[str, Strict(strict=True)], extraction_id: typing.Annotated[str, Strict(strict=True)], _request_timeout: Union[NoneType, Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Tuple[Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])]]] = None, _request_auth: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _content_type: Optional[Annotated[str, Strict(strict=True)]] = None, _headers: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _host_index: typing.Annotated[int, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Ge(ge=0), Le(le=0)])] = 0) -> vectorize_client.api_response.ApiResponse[ExtractionResultResponse]:
119    @validate_call
120    def get_extraction_result_with_http_info(
121        self,
122        organization_id: StrictStr,
123        extraction_id: StrictStr,
124        _request_timeout: Union[
125            None,
126            Annotated[StrictFloat, Field(gt=0)],
127            Tuple[
128                Annotated[StrictFloat, Field(gt=0)],
129                Annotated[StrictFloat, Field(gt=0)]
130            ]
131        ] = None,
132        _request_auth: Optional[Dict[StrictStr, Any]] = None,
133        _content_type: Optional[StrictStr] = None,
134        _headers: Optional[Dict[StrictStr, Any]] = None,
135        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
136    ) -> ApiResponse[ExtractionResultResponse]:
137        """Get extraction result
138
139        Get extraction result
140
141        :param organization_id: (required)
142        :type organization_id: str
143        :param extraction_id: (required)
144        :type extraction_id: str
145        :param _request_timeout: timeout setting for this request. If one
146                                 number provided, it will be total request
147                                 timeout. It can also be a pair (tuple) of
148                                 (connection, read) timeouts.
149        :type _request_timeout: int, tuple(int, int), optional
150        :param _request_auth: set to override the auth_settings for an a single
151                              request; this effectively ignores the
152                              authentication in the spec for a single request.
153        :type _request_auth: dict, optional
154        :param _content_type: force content-type for the request.
155        :type _content_type: str, Optional
156        :param _headers: set to override the headers for a single
157                         request; this effectively ignores the headers
158                         in the spec for a single request.
159        :type _headers: dict, optional
160        :param _host_index: set to override the host_index for a single
161                            request; this effectively ignores the host_index
162                            in the spec for a single request.
163        :type _host_index: int, optional
164        :return: Returns the result object.
165        """ # noqa: E501
166
167        _param = self._get_extraction_result_serialize(
168            organization_id=organization_id,
169            extraction_id=extraction_id,
170            _request_auth=_request_auth,
171            _content_type=_content_type,
172            _headers=_headers,
173            _host_index=_host_index
174        )
175
176        _response_types_map: Dict[str, Optional[str]] = {
177            '200': "ExtractionResultResponse",
178            '400': "GetPipelines400Response",
179            '401': "GetPipelines400Response",
180            '403': "GetPipelines400Response",
181            '404': "GetPipelines400Response",
182            '500': "GetPipelines400Response",
183        }
184        response_data = self.api_client.call_api(
185            *_param,
186            _request_timeout=_request_timeout
187        )
188        response_data.read()
189        return self.api_client.response_deserialize(
190            response_data=response_data,
191            response_types_map=_response_types_map,
192        )

Get extraction result

Get extraction result

Parameters
  • organization_id: (required)
  • extraction_id: (required)
  • _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.
  • _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.
  • _content_type: force content-type for the request.
  • _headers: set to override the headers for a single request; this effectively ignores the headers in the spec for a single request.
  • _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.
Returns

Returns the result object.

@validate_call
def get_extraction_result_without_preload_content( self, organization_id: typing.Annotated[str, Strict(strict=True)], extraction_id: typing.Annotated[str, Strict(strict=True)], _request_timeout: Union[NoneType, Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Tuple[Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])]]] = None, _request_auth: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _content_type: Optional[Annotated[str, Strict(strict=True)]] = None, _headers: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _host_index: typing.Annotated[int, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Ge(ge=0), Le(le=0)])] = 0) -> urllib3.response.HTTPResponse:
195    @validate_call
196    def get_extraction_result_without_preload_content(
197        self,
198        organization_id: StrictStr,
199        extraction_id: StrictStr,
200        _request_timeout: Union[
201            None,
202            Annotated[StrictFloat, Field(gt=0)],
203            Tuple[
204                Annotated[StrictFloat, Field(gt=0)],
205                Annotated[StrictFloat, Field(gt=0)]
206            ]
207        ] = None,
208        _request_auth: Optional[Dict[StrictStr, Any]] = None,
209        _content_type: Optional[StrictStr] = None,
210        _headers: Optional[Dict[StrictStr, Any]] = None,
211        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
212    ) -> RESTResponseType:
213        """Get extraction result
214
215        Get extraction result
216
217        :param organization_id: (required)
218        :type organization_id: str
219        :param extraction_id: (required)
220        :type extraction_id: str
221        :param _request_timeout: timeout setting for this request. If one
222                                 number provided, it will be total request
223                                 timeout. It can also be a pair (tuple) of
224                                 (connection, read) timeouts.
225        :type _request_timeout: int, tuple(int, int), optional
226        :param _request_auth: set to override the auth_settings for an a single
227                              request; this effectively ignores the
228                              authentication in the spec for a single request.
229        :type _request_auth: dict, optional
230        :param _content_type: force content-type for the request.
231        :type _content_type: str, Optional
232        :param _headers: set to override the headers for a single
233                         request; this effectively ignores the headers
234                         in the spec for a single request.
235        :type _headers: dict, optional
236        :param _host_index: set to override the host_index for a single
237                            request; this effectively ignores the host_index
238                            in the spec for a single request.
239        :type _host_index: int, optional
240        :return: Returns the result object.
241        """ # noqa: E501
242
243        _param = self._get_extraction_result_serialize(
244            organization_id=organization_id,
245            extraction_id=extraction_id,
246            _request_auth=_request_auth,
247            _content_type=_content_type,
248            _headers=_headers,
249            _host_index=_host_index
250        )
251
252        _response_types_map: Dict[str, Optional[str]] = {
253            '200': "ExtractionResultResponse",
254            '400': "GetPipelines400Response",
255            '401': "GetPipelines400Response",
256            '403': "GetPipelines400Response",
257            '404': "GetPipelines400Response",
258            '500': "GetPipelines400Response",
259        }
260        response_data = self.api_client.call_api(
261            *_param,
262            _request_timeout=_request_timeout
263        )
264        return response_data.response

Get extraction result

Get extraction result

Parameters
  • organization_id: (required)
  • extraction_id: (required)
  • _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.
  • _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.
  • _content_type: force content-type for the request.
  • _headers: set to override the headers for a single request; this effectively ignores the headers in the spec for a single request.
  • _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.
Returns

Returns the result object.

@validate_call
def start_extraction( self, organization_id: typing.Annotated[str, Strict(strict=True)], start_extraction_request: vectorize_client.models.start_extraction_request.StartExtractionRequest, _request_timeout: Union[NoneType, Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Tuple[Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])]]] = None, _request_auth: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _content_type: Optional[Annotated[str, Strict(strict=True)]] = None, _headers: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _host_index: typing.Annotated[int, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Ge(ge=0), Le(le=0)])] = 0) -> vectorize_client.models.start_extraction_response.StartExtractionResponse:
334    @validate_call
335    def start_extraction(
336        self,
337        organization_id: StrictStr,
338        start_extraction_request: StartExtractionRequest,
339        _request_timeout: Union[
340            None,
341            Annotated[StrictFloat, Field(gt=0)],
342            Tuple[
343                Annotated[StrictFloat, Field(gt=0)],
344                Annotated[StrictFloat, Field(gt=0)]
345            ]
346        ] = None,
347        _request_auth: Optional[Dict[StrictStr, Any]] = None,
348        _content_type: Optional[StrictStr] = None,
349        _headers: Optional[Dict[StrictStr, Any]] = None,
350        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
351    ) -> StartExtractionResponse:
352        """Start content extraction from a file
353
354        Start content extraction from a file
355
356        :param organization_id: (required)
357        :type organization_id: str
358        :param start_extraction_request: (required)
359        :type start_extraction_request: StartExtractionRequest
360        :param _request_timeout: timeout setting for this request. If one
361                                 number provided, it will be total request
362                                 timeout. It can also be a pair (tuple) of
363                                 (connection, read) timeouts.
364        :type _request_timeout: int, tuple(int, int), optional
365        :param _request_auth: set to override the auth_settings for an a single
366                              request; this effectively ignores the
367                              authentication in the spec for a single request.
368        :type _request_auth: dict, optional
369        :param _content_type: force content-type for the request.
370        :type _content_type: str, Optional
371        :param _headers: set to override the headers for a single
372                         request; this effectively ignores the headers
373                         in the spec for a single request.
374        :type _headers: dict, optional
375        :param _host_index: set to override the host_index for a single
376                            request; this effectively ignores the host_index
377                            in the spec for a single request.
378        :type _host_index: int, optional
379        :return: Returns the result object.
380        """ # noqa: E501
381
382        _param = self._start_extraction_serialize(
383            organization_id=organization_id,
384            start_extraction_request=start_extraction_request,
385            _request_auth=_request_auth,
386            _content_type=_content_type,
387            _headers=_headers,
388            _host_index=_host_index
389        )
390
391        _response_types_map: Dict[str, Optional[str]] = {
392            '200': "StartExtractionResponse",
393            '400': "GetPipelines400Response",
394            '401': "GetPipelines400Response",
395            '403': "GetPipelines400Response",
396            '404': "GetPipelines400Response",
397            '500': "GetPipelines400Response",
398        }
399        response_data = self.api_client.call_api(
400            *_param,
401            _request_timeout=_request_timeout
402        )
403        response_data.read()
404        return self.api_client.response_deserialize(
405            response_data=response_data,
406            response_types_map=_response_types_map,
407        ).data

Start content extraction from a file

Start content extraction from a file

Parameters
  • organization_id: (required)
  • start_extraction_request: (required)
  • _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.
  • _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.
  • _content_type: force content-type for the request.
  • _headers: set to override the headers for a single request; this effectively ignores the headers in the spec for a single request.
  • _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.
Returns

Returns the result object.

@validate_call
def start_extraction_with_http_info( self, organization_id: typing.Annotated[str, Strict(strict=True)], start_extraction_request: vectorize_client.models.start_extraction_request.StartExtractionRequest, _request_timeout: Union[NoneType, Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Tuple[Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])]]] = None, _request_auth: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _content_type: Optional[Annotated[str, Strict(strict=True)]] = None, _headers: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _host_index: typing.Annotated[int, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Ge(ge=0), Le(le=0)])] = 0) -> vectorize_client.api_response.ApiResponse[StartExtractionResponse]:
410    @validate_call
411    def start_extraction_with_http_info(
412        self,
413        organization_id: StrictStr,
414        start_extraction_request: StartExtractionRequest,
415        _request_timeout: Union[
416            None,
417            Annotated[StrictFloat, Field(gt=0)],
418            Tuple[
419                Annotated[StrictFloat, Field(gt=0)],
420                Annotated[StrictFloat, Field(gt=0)]
421            ]
422        ] = None,
423        _request_auth: Optional[Dict[StrictStr, Any]] = None,
424        _content_type: Optional[StrictStr] = None,
425        _headers: Optional[Dict[StrictStr, Any]] = None,
426        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
427    ) -> ApiResponse[StartExtractionResponse]:
428        """Start content extraction from a file
429
430        Start content extraction from a file
431
432        :param organization_id: (required)
433        :type organization_id: str
434        :param start_extraction_request: (required)
435        :type start_extraction_request: StartExtractionRequest
436        :param _request_timeout: timeout setting for this request. If one
437                                 number provided, it will be total request
438                                 timeout. It can also be a pair (tuple) of
439                                 (connection, read) timeouts.
440        :type _request_timeout: int, tuple(int, int), optional
441        :param _request_auth: set to override the auth_settings for an a single
442                              request; this effectively ignores the
443                              authentication in the spec for a single request.
444        :type _request_auth: dict, optional
445        :param _content_type: force content-type for the request.
446        :type _content_type: str, Optional
447        :param _headers: set to override the headers for a single
448                         request; this effectively ignores the headers
449                         in the spec for a single request.
450        :type _headers: dict, optional
451        :param _host_index: set to override the host_index for a single
452                            request; this effectively ignores the host_index
453                            in the spec for a single request.
454        :type _host_index: int, optional
455        :return: Returns the result object.
456        """ # noqa: E501
457
458        _param = self._start_extraction_serialize(
459            organization_id=organization_id,
460            start_extraction_request=start_extraction_request,
461            _request_auth=_request_auth,
462            _content_type=_content_type,
463            _headers=_headers,
464            _host_index=_host_index
465        )
466
467        _response_types_map: Dict[str, Optional[str]] = {
468            '200': "StartExtractionResponse",
469            '400': "GetPipelines400Response",
470            '401': "GetPipelines400Response",
471            '403': "GetPipelines400Response",
472            '404': "GetPipelines400Response",
473            '500': "GetPipelines400Response",
474        }
475        response_data = self.api_client.call_api(
476            *_param,
477            _request_timeout=_request_timeout
478        )
479        response_data.read()
480        return self.api_client.response_deserialize(
481            response_data=response_data,
482            response_types_map=_response_types_map,
483        )

Start content extraction from a file

Start content extraction from a file

Parameters
  • organization_id: (required)
  • start_extraction_request: (required)
  • _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.
  • _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.
  • _content_type: force content-type for the request.
  • _headers: set to override the headers for a single request; this effectively ignores the headers in the spec for a single request.
  • _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.
Returns

Returns the result object.

@validate_call
def start_extraction_without_preload_content( self, organization_id: typing.Annotated[str, Strict(strict=True)], start_extraction_request: vectorize_client.models.start_extraction_request.StartExtractionRequest, _request_timeout: Union[NoneType, Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Tuple[Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])], Annotated[float, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Gt(gt=0)])]]] = None, _request_auth: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _content_type: Optional[Annotated[str, Strict(strict=True)]] = None, _headers: Optional[Dict[Annotated[str, Strict(strict=True)], Any]] = None, _host_index: typing.Annotated[int, Strict(strict=True), FieldInfo(annotation=NoneType, required=True, metadata=[Ge(ge=0), Le(le=0)])] = 0) -> urllib3.response.HTTPResponse:
486    @validate_call
487    def start_extraction_without_preload_content(
488        self,
489        organization_id: StrictStr,
490        start_extraction_request: StartExtractionRequest,
491        _request_timeout: Union[
492            None,
493            Annotated[StrictFloat, Field(gt=0)],
494            Tuple[
495                Annotated[StrictFloat, Field(gt=0)],
496                Annotated[StrictFloat, Field(gt=0)]
497            ]
498        ] = None,
499        _request_auth: Optional[Dict[StrictStr, Any]] = None,
500        _content_type: Optional[StrictStr] = None,
501        _headers: Optional[Dict[StrictStr, Any]] = None,
502        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
503    ) -> RESTResponseType:
504        """Start content extraction from a file
505
506        Start content extraction from a file
507
508        :param organization_id: (required)
509        :type organization_id: str
510        :param start_extraction_request: (required)
511        :type start_extraction_request: StartExtractionRequest
512        :param _request_timeout: timeout setting for this request. If one
513                                 number provided, it will be total request
514                                 timeout. It can also be a pair (tuple) of
515                                 (connection, read) timeouts.
516        :type _request_timeout: int, tuple(int, int), optional
517        :param _request_auth: set to override the auth_settings for an a single
518                              request; this effectively ignores the
519                              authentication in the spec for a single request.
520        :type _request_auth: dict, optional
521        :param _content_type: force content-type for the request.
522        :type _content_type: str, Optional
523        :param _headers: set to override the headers for a single
524                         request; this effectively ignores the headers
525                         in the spec for a single request.
526        :type _headers: dict, optional
527        :param _host_index: set to override the host_index for a single
528                            request; this effectively ignores the host_index
529                            in the spec for a single request.
530        :type _host_index: int, optional
531        :return: Returns the result object.
532        """ # noqa: E501
533
534        _param = self._start_extraction_serialize(
535            organization_id=organization_id,
536            start_extraction_request=start_extraction_request,
537            _request_auth=_request_auth,
538            _content_type=_content_type,
539            _headers=_headers,
540            _host_index=_host_index
541        )
542
543        _response_types_map: Dict[str, Optional[str]] = {
544            '200': "StartExtractionResponse",
545            '400': "GetPipelines400Response",
546            '401': "GetPipelines400Response",
547            '403': "GetPipelines400Response",
548            '404': "GetPipelines400Response",
549            '500': "GetPipelines400Response",
550        }
551        response_data = self.api_client.call_api(
552            *_param,
553            _request_timeout=_request_timeout
554        )
555        return response_data.response

Start content extraction from a file

Start content extraction from a file

Parameters
  • organization_id: (required)
  • start_extraction_request: (required)
  • _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.
  • _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.
  • _content_type: force content-type for the request.
  • _headers: set to override the headers for a single request; this effectively ignores the headers in the spec for a single request.
  • _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.
Returns

Returns the result object.