vectorize_client.api.extraction_api

Vectorize API (Beta)

API for Vectorize services

The version of the OpenAPI document: 0.0.1 Generated by OpenAPI Generator (https://openapi-generator.tech)

Do not edit the class manually.

  1# coding: utf-8
  2
  3"""
  4    Vectorize API (Beta)
  5
  6    API for Vectorize services
  7
  8    The version of the OpenAPI document: 0.0.1
  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: 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
 63        :param organization: (required)
 64        :type organization: str
 65        :param extraction_id: (required)
 66        :type extraction_id: str
 67        :param _request_timeout: timeout setting for this request. If one
 68                                 number provided, it will be total request
 69                                 timeout. It can also be a pair (tuple) of
 70                                 (connection, read) timeouts.
 71        :type _request_timeout: int, tuple(int, int), optional
 72        :param _request_auth: set to override the auth_settings for an a single
 73                              request; this effectively ignores the
 74                              authentication in the spec for a single request.
 75        :type _request_auth: dict, optional
 76        :param _content_type: force content-type for the request.
 77        :type _content_type: str, Optional
 78        :param _headers: set to override the headers for a single
 79                         request; this effectively ignores the headers
 80                         in the spec for a single request.
 81        :type _headers: dict, optional
 82        :param _host_index: set to override the host_index for a single
 83                            request; this effectively ignores the host_index
 84                            in the spec for a single request.
 85        :type _host_index: int, optional
 86        :return: Returns the result object.
 87        """ # noqa: E501
 88
 89        _param = self._get_extraction_result_serialize(
 90            organization=organization,
 91            extraction_id=extraction_id,
 92            _request_auth=_request_auth,
 93            _content_type=_content_type,
 94            _headers=_headers,
 95            _host_index=_host_index
 96        )
 97
 98        _response_types_map: Dict[str, Optional[str]] = {
 99            '200': "ExtractionResultResponse",
100            '400': "GetPipelines400Response",
101            '401': "GetPipelines400Response",
102            '403': "GetPipelines400Response",
103            '404': "GetPipelines400Response",
104            '500': "GetPipelines400Response",
105        }
106        response_data = self.api_client.call_api(
107            *_param,
108            _request_timeout=_request_timeout
109        )
110        response_data.read()
111        return self.api_client.response_deserialize(
112            response_data=response_data,
113            response_types_map=_response_types_map,
114        ).data
115
116
117    @validate_call
118    def get_extraction_result_with_http_info(
119        self,
120        organization: StrictStr,
121        extraction_id: StrictStr,
122        _request_timeout: Union[
123            None,
124            Annotated[StrictFloat, Field(gt=0)],
125            Tuple[
126                Annotated[StrictFloat, Field(gt=0)],
127                Annotated[StrictFloat, Field(gt=0)]
128            ]
129        ] = None,
130        _request_auth: Optional[Dict[StrictStr, Any]] = None,
131        _content_type: Optional[StrictStr] = None,
132        _headers: Optional[Dict[StrictStr, Any]] = None,
133        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
134    ) -> ApiResponse[ExtractionResultResponse]:
135        """Get extraction result
136
137
138        :param organization: (required)
139        :type organization: str
140        :param extraction_id: (required)
141        :type extraction_id: str
142        :param _request_timeout: timeout setting for this request. If one
143                                 number provided, it will be total request
144                                 timeout. It can also be a pair (tuple) of
145                                 (connection, read) timeouts.
146        :type _request_timeout: int, tuple(int, int), optional
147        :param _request_auth: set to override the auth_settings for an a single
148                              request; this effectively ignores the
149                              authentication in the spec for a single request.
150        :type _request_auth: dict, optional
151        :param _content_type: force content-type for the request.
152        :type _content_type: str, Optional
153        :param _headers: set to override the headers for a single
154                         request; this effectively ignores the headers
155                         in the spec for a single request.
156        :type _headers: dict, optional
157        :param _host_index: set to override the host_index for a single
158                            request; this effectively ignores the host_index
159                            in the spec for a single request.
160        :type _host_index: int, optional
161        :return: Returns the result object.
162        """ # noqa: E501
163
164        _param = self._get_extraction_result_serialize(
165            organization=organization,
166            extraction_id=extraction_id,
167            _request_auth=_request_auth,
168            _content_type=_content_type,
169            _headers=_headers,
170            _host_index=_host_index
171        )
172
173        _response_types_map: Dict[str, Optional[str]] = {
174            '200': "ExtractionResultResponse",
175            '400': "GetPipelines400Response",
176            '401': "GetPipelines400Response",
177            '403': "GetPipelines400Response",
178            '404': "GetPipelines400Response",
179            '500': "GetPipelines400Response",
180        }
181        response_data = self.api_client.call_api(
182            *_param,
183            _request_timeout=_request_timeout
184        )
185        response_data.read()
186        return self.api_client.response_deserialize(
187            response_data=response_data,
188            response_types_map=_response_types_map,
189        )
190
191
192    @validate_call
193    def get_extraction_result_without_preload_content(
194        self,
195        organization: StrictStr,
196        extraction_id: StrictStr,
197        _request_timeout: Union[
198            None,
199            Annotated[StrictFloat, Field(gt=0)],
200            Tuple[
201                Annotated[StrictFloat, Field(gt=0)],
202                Annotated[StrictFloat, Field(gt=0)]
203            ]
204        ] = None,
205        _request_auth: Optional[Dict[StrictStr, Any]] = None,
206        _content_type: Optional[StrictStr] = None,
207        _headers: Optional[Dict[StrictStr, Any]] = None,
208        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
209    ) -> RESTResponseType:
210        """Get extraction result
211
212
213        :param organization: (required)
214        :type organization: str
215        :param extraction_id: (required)
216        :type extraction_id: str
217        :param _request_timeout: timeout setting for this request. If one
218                                 number provided, it will be total request
219                                 timeout. It can also be a pair (tuple) of
220                                 (connection, read) timeouts.
221        :type _request_timeout: int, tuple(int, int), optional
222        :param _request_auth: set to override the auth_settings for an a single
223                              request; this effectively ignores the
224                              authentication in the spec for a single request.
225        :type _request_auth: dict, optional
226        :param _content_type: force content-type for the request.
227        :type _content_type: str, Optional
228        :param _headers: set to override the headers for a single
229                         request; this effectively ignores the headers
230                         in the spec for a single request.
231        :type _headers: dict, optional
232        :param _host_index: set to override the host_index for a single
233                            request; this effectively ignores the host_index
234                            in the spec for a single request.
235        :type _host_index: int, optional
236        :return: Returns the result object.
237        """ # noqa: E501
238
239        _param = self._get_extraction_result_serialize(
240            organization=organization,
241            extraction_id=extraction_id,
242            _request_auth=_request_auth,
243            _content_type=_content_type,
244            _headers=_headers,
245            _host_index=_host_index
246        )
247
248        _response_types_map: Dict[str, Optional[str]] = {
249            '200': "ExtractionResultResponse",
250            '400': "GetPipelines400Response",
251            '401': "GetPipelines400Response",
252            '403': "GetPipelines400Response",
253            '404': "GetPipelines400Response",
254            '500': "GetPipelines400Response",
255        }
256        response_data = self.api_client.call_api(
257            *_param,
258            _request_timeout=_request_timeout
259        )
260        return response_data.response
261
262
263    def _get_extraction_result_serialize(
264        self,
265        organization,
266        extraction_id,
267        _request_auth,
268        _content_type,
269        _headers,
270        _host_index,
271    ) -> RequestSerialized:
272
273        _host = None
274
275        _collection_formats: Dict[str, str] = {
276        }
277
278        _path_params: Dict[str, str] = {}
279        _query_params: List[Tuple[str, str]] = []
280        _header_params: Dict[str, Optional[str]] = _headers or {}
281        _form_params: List[Tuple[str, str]] = []
282        _files: Dict[
283            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
284        ] = {}
285        _body_params: Optional[bytes] = None
286
287        # process the path parameters
288        if organization is not None:
289            _path_params['organization'] = organization
290        if extraction_id is not None:
291            _path_params['extractionId'] = extraction_id
292        # process the query parameters
293        # process the header parameters
294        # process the form parameters
295        # process the body parameter
296
297
298        # set the HTTP header `Accept`
299        if 'Accept' not in _header_params:
300            _header_params['Accept'] = self.api_client.select_header_accept(
301                [
302                    'application/json'
303                ]
304            )
305
306
307        # authentication setting
308        _auth_settings: List[str] = [
309            'bearerAuth'
310        ]
311
312        return self.api_client.param_serialize(
313            method='GET',
314            resource_path='/org/{organization}/extraction/{extractionId}',
315            path_params=_path_params,
316            query_params=_query_params,
317            header_params=_header_params,
318            body=_body_params,
319            post_params=_form_params,
320            files=_files,
321            auth_settings=_auth_settings,
322            collection_formats=_collection_formats,
323            _host=_host,
324            _request_auth=_request_auth
325        )
326
327
328
329
330    @validate_call
331    def start_extraction(
332        self,
333        organization: StrictStr,
334        start_extraction_request: StartExtractionRequest,
335        _request_timeout: Union[
336            None,
337            Annotated[StrictFloat, Field(gt=0)],
338            Tuple[
339                Annotated[StrictFloat, Field(gt=0)],
340                Annotated[StrictFloat, Field(gt=0)]
341            ]
342        ] = None,
343        _request_auth: Optional[Dict[StrictStr, Any]] = None,
344        _content_type: Optional[StrictStr] = None,
345        _headers: Optional[Dict[StrictStr, Any]] = None,
346        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
347    ) -> StartExtractionResponse:
348        """Start content extraction from a file
349
350
351        :param organization: (required)
352        :type organization: str
353        :param start_extraction_request: (required)
354        :type start_extraction_request: StartExtractionRequest
355        :param _request_timeout: timeout setting for this request. If one
356                                 number provided, it will be total request
357                                 timeout. It can also be a pair (tuple) of
358                                 (connection, read) timeouts.
359        :type _request_timeout: int, tuple(int, int), optional
360        :param _request_auth: set to override the auth_settings for an a single
361                              request; this effectively ignores the
362                              authentication in the spec for a single request.
363        :type _request_auth: dict, optional
364        :param _content_type: force content-type for the request.
365        :type _content_type: str, Optional
366        :param _headers: set to override the headers for a single
367                         request; this effectively ignores the headers
368                         in the spec for a single request.
369        :type _headers: dict, optional
370        :param _host_index: set to override the host_index for a single
371                            request; this effectively ignores the host_index
372                            in the spec for a single request.
373        :type _host_index: int, optional
374        :return: Returns the result object.
375        """ # noqa: E501
376
377        _param = self._start_extraction_serialize(
378            organization=organization,
379            start_extraction_request=start_extraction_request,
380            _request_auth=_request_auth,
381            _content_type=_content_type,
382            _headers=_headers,
383            _host_index=_host_index
384        )
385
386        _response_types_map: Dict[str, Optional[str]] = {
387            '200': "StartExtractionResponse",
388            '400': "GetPipelines400Response",
389            '401': "GetPipelines400Response",
390            '403': "GetPipelines400Response",
391            '404': "GetPipelines400Response",
392            '500': "GetPipelines400Response",
393        }
394        response_data = self.api_client.call_api(
395            *_param,
396            _request_timeout=_request_timeout
397        )
398        response_data.read()
399        return self.api_client.response_deserialize(
400            response_data=response_data,
401            response_types_map=_response_types_map,
402        ).data
403
404
405    @validate_call
406    def start_extraction_with_http_info(
407        self,
408        organization: StrictStr,
409        start_extraction_request: StartExtractionRequest,
410        _request_timeout: Union[
411            None,
412            Annotated[StrictFloat, Field(gt=0)],
413            Tuple[
414                Annotated[StrictFloat, Field(gt=0)],
415                Annotated[StrictFloat, Field(gt=0)]
416            ]
417        ] = None,
418        _request_auth: Optional[Dict[StrictStr, Any]] = None,
419        _content_type: Optional[StrictStr] = None,
420        _headers: Optional[Dict[StrictStr, Any]] = None,
421        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
422    ) -> ApiResponse[StartExtractionResponse]:
423        """Start content extraction from a file
424
425
426        :param organization: (required)
427        :type organization: str
428        :param start_extraction_request: (required)
429        :type start_extraction_request: StartExtractionRequest
430        :param _request_timeout: timeout setting for this request. If one
431                                 number provided, it will be total request
432                                 timeout. It can also be a pair (tuple) of
433                                 (connection, read) timeouts.
434        :type _request_timeout: int, tuple(int, int), optional
435        :param _request_auth: set to override the auth_settings for an a single
436                              request; this effectively ignores the
437                              authentication in the spec for a single request.
438        :type _request_auth: dict, optional
439        :param _content_type: force content-type for the request.
440        :type _content_type: str, Optional
441        :param _headers: set to override the headers for a single
442                         request; this effectively ignores the headers
443                         in the spec for a single request.
444        :type _headers: dict, optional
445        :param _host_index: set to override the host_index for a single
446                            request; this effectively ignores the host_index
447                            in the spec for a single request.
448        :type _host_index: int, optional
449        :return: Returns the result object.
450        """ # noqa: E501
451
452        _param = self._start_extraction_serialize(
453            organization=organization,
454            start_extraction_request=start_extraction_request,
455            _request_auth=_request_auth,
456            _content_type=_content_type,
457            _headers=_headers,
458            _host_index=_host_index
459        )
460
461        _response_types_map: Dict[str, Optional[str]] = {
462            '200': "StartExtractionResponse",
463            '400': "GetPipelines400Response",
464            '401': "GetPipelines400Response",
465            '403': "GetPipelines400Response",
466            '404': "GetPipelines400Response",
467            '500': "GetPipelines400Response",
468        }
469        response_data = self.api_client.call_api(
470            *_param,
471            _request_timeout=_request_timeout
472        )
473        response_data.read()
474        return self.api_client.response_deserialize(
475            response_data=response_data,
476            response_types_map=_response_types_map,
477        )
478
479
480    @validate_call
481    def start_extraction_without_preload_content(
482        self,
483        organization: StrictStr,
484        start_extraction_request: StartExtractionRequest,
485        _request_timeout: Union[
486            None,
487            Annotated[StrictFloat, Field(gt=0)],
488            Tuple[
489                Annotated[StrictFloat, Field(gt=0)],
490                Annotated[StrictFloat, Field(gt=0)]
491            ]
492        ] = None,
493        _request_auth: Optional[Dict[StrictStr, Any]] = None,
494        _content_type: Optional[StrictStr] = None,
495        _headers: Optional[Dict[StrictStr, Any]] = None,
496        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
497    ) -> RESTResponseType:
498        """Start content extraction from a file
499
500
501        :param organization: (required)
502        :type organization: str
503        :param start_extraction_request: (required)
504        :type start_extraction_request: StartExtractionRequest
505        :param _request_timeout: timeout setting for this request. If one
506                                 number provided, it will be total request
507                                 timeout. It can also be a pair (tuple) of
508                                 (connection, read) timeouts.
509        :type _request_timeout: int, tuple(int, int), optional
510        :param _request_auth: set to override the auth_settings for an a single
511                              request; this effectively ignores the
512                              authentication in the spec for a single request.
513        :type _request_auth: dict, optional
514        :param _content_type: force content-type for the request.
515        :type _content_type: str, Optional
516        :param _headers: set to override the headers for a single
517                         request; this effectively ignores the headers
518                         in the spec for a single request.
519        :type _headers: dict, optional
520        :param _host_index: set to override the host_index for a single
521                            request; this effectively ignores the host_index
522                            in the spec for a single request.
523        :type _host_index: int, optional
524        :return: Returns the result object.
525        """ # noqa: E501
526
527        _param = self._start_extraction_serialize(
528            organization=organization,
529            start_extraction_request=start_extraction_request,
530            _request_auth=_request_auth,
531            _content_type=_content_type,
532            _headers=_headers,
533            _host_index=_host_index
534        )
535
536        _response_types_map: Dict[str, Optional[str]] = {
537            '200': "StartExtractionResponse",
538            '400': "GetPipelines400Response",
539            '401': "GetPipelines400Response",
540            '403': "GetPipelines400Response",
541            '404': "GetPipelines400Response",
542            '500': "GetPipelines400Response",
543        }
544        response_data = self.api_client.call_api(
545            *_param,
546            _request_timeout=_request_timeout
547        )
548        return response_data.response
549
550
551    def _start_extraction_serialize(
552        self,
553        organization,
554        start_extraction_request,
555        _request_auth,
556        _content_type,
557        _headers,
558        _host_index,
559    ) -> RequestSerialized:
560
561        _host = None
562
563        _collection_formats: Dict[str, str] = {
564        }
565
566        _path_params: Dict[str, str] = {}
567        _query_params: List[Tuple[str, str]] = []
568        _header_params: Dict[str, Optional[str]] = _headers or {}
569        _form_params: List[Tuple[str, str]] = []
570        _files: Dict[
571            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
572        ] = {}
573        _body_params: Optional[bytes] = None
574
575        # process the path parameters
576        if organization is not None:
577            _path_params['organization'] = organization
578        # process the query parameters
579        # process the header parameters
580        # process the form parameters
581        # process the body parameter
582        if start_extraction_request is not None:
583            _body_params = start_extraction_request
584
585
586        # set the HTTP header `Accept`
587        if 'Accept' not in _header_params:
588            _header_params['Accept'] = self.api_client.select_header_accept(
589                [
590                    'application/json'
591                ]
592            )
593
594        # set the HTTP header `Content-Type`
595        if _content_type:
596            _header_params['Content-Type'] = _content_type
597        else:
598            _default_content_type = (
599                self.api_client.select_header_content_type(
600                    [
601                        'application/json'
602                    ]
603                )
604            )
605            if _default_content_type is not None:
606                _header_params['Content-Type'] = _default_content_type
607
608        # authentication setting
609        _auth_settings: List[str] = [
610            'bearerAuth'
611        ]
612
613        return self.api_client.param_serialize(
614            method='POST',
615            resource_path='/org/{organization}/extraction',
616            path_params=_path_params,
617            query_params=_query_params,
618            header_params=_header_params,
619            body=_body_params,
620            post_params=_form_params,
621            files=_files,
622            auth_settings=_auth_settings,
623            collection_formats=_collection_formats,
624            _host=_host,
625            _request_auth=_request_auth
626        )
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: 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
 64        :param organization: (required)
 65        :type organization: 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=organization,
 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: 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
139        :param organization: (required)
140        :type organization: str
141        :param extraction_id: (required)
142        :type extraction_id: str
143        :param _request_timeout: timeout setting for this request. If one
144                                 number provided, it will be total request
145                                 timeout. It can also be a pair (tuple) of
146                                 (connection, read) timeouts.
147        :type _request_timeout: int, tuple(int, int), optional
148        :param _request_auth: set to override the auth_settings for an a single
149                              request; this effectively ignores the
150                              authentication in the spec for a single request.
151        :type _request_auth: dict, optional
152        :param _content_type: force content-type for the request.
153        :type _content_type: str, Optional
154        :param _headers: set to override the headers for a single
155                         request; this effectively ignores the headers
156                         in the spec for a single request.
157        :type _headers: dict, optional
158        :param _host_index: set to override the host_index for a single
159                            request; this effectively ignores the host_index
160                            in the spec for a single request.
161        :type _host_index: int, optional
162        :return: Returns the result object.
163        """ # noqa: E501
164
165        _param = self._get_extraction_result_serialize(
166            organization=organization,
167            extraction_id=extraction_id,
168            _request_auth=_request_auth,
169            _content_type=_content_type,
170            _headers=_headers,
171            _host_index=_host_index
172        )
173
174        _response_types_map: Dict[str, Optional[str]] = {
175            '200': "ExtractionResultResponse",
176            '400': "GetPipelines400Response",
177            '401': "GetPipelines400Response",
178            '403': "GetPipelines400Response",
179            '404': "GetPipelines400Response",
180            '500': "GetPipelines400Response",
181        }
182        response_data = self.api_client.call_api(
183            *_param,
184            _request_timeout=_request_timeout
185        )
186        response_data.read()
187        return self.api_client.response_deserialize(
188            response_data=response_data,
189            response_types_map=_response_types_map,
190        )
191
192
193    @validate_call
194    def get_extraction_result_without_preload_content(
195        self,
196        organization: StrictStr,
197        extraction_id: StrictStr,
198        _request_timeout: Union[
199            None,
200            Annotated[StrictFloat, Field(gt=0)],
201            Tuple[
202                Annotated[StrictFloat, Field(gt=0)],
203                Annotated[StrictFloat, Field(gt=0)]
204            ]
205        ] = None,
206        _request_auth: Optional[Dict[StrictStr, Any]] = None,
207        _content_type: Optional[StrictStr] = None,
208        _headers: Optional[Dict[StrictStr, Any]] = None,
209        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
210    ) -> RESTResponseType:
211        """Get extraction result
212
213
214        :param organization: (required)
215        :type organization: str
216        :param extraction_id: (required)
217        :type extraction_id: str
218        :param _request_timeout: timeout setting for this request. If one
219                                 number provided, it will be total request
220                                 timeout. It can also be a pair (tuple) of
221                                 (connection, read) timeouts.
222        :type _request_timeout: int, tuple(int, int), optional
223        :param _request_auth: set to override the auth_settings for an a single
224                              request; this effectively ignores the
225                              authentication in the spec for a single request.
226        :type _request_auth: dict, optional
227        :param _content_type: force content-type for the request.
228        :type _content_type: str, Optional
229        :param _headers: set to override the headers for a single
230                         request; this effectively ignores the headers
231                         in the spec for a single request.
232        :type _headers: dict, optional
233        :param _host_index: set to override the host_index for a single
234                            request; this effectively ignores the host_index
235                            in the spec for a single request.
236        :type _host_index: int, optional
237        :return: Returns the result object.
238        """ # noqa: E501
239
240        _param = self._get_extraction_result_serialize(
241            organization=organization,
242            extraction_id=extraction_id,
243            _request_auth=_request_auth,
244            _content_type=_content_type,
245            _headers=_headers,
246            _host_index=_host_index
247        )
248
249        _response_types_map: Dict[str, Optional[str]] = {
250            '200': "ExtractionResultResponse",
251            '400': "GetPipelines400Response",
252            '401': "GetPipelines400Response",
253            '403': "GetPipelines400Response",
254            '404': "GetPipelines400Response",
255            '500': "GetPipelines400Response",
256        }
257        response_data = self.api_client.call_api(
258            *_param,
259            _request_timeout=_request_timeout
260        )
261        return response_data.response
262
263
264    def _get_extraction_result_serialize(
265        self,
266        organization,
267        extraction_id,
268        _request_auth,
269        _content_type,
270        _headers,
271        _host_index,
272    ) -> RequestSerialized:
273
274        _host = None
275
276        _collection_formats: Dict[str, str] = {
277        }
278
279        _path_params: Dict[str, str] = {}
280        _query_params: List[Tuple[str, str]] = []
281        _header_params: Dict[str, Optional[str]] = _headers or {}
282        _form_params: List[Tuple[str, str]] = []
283        _files: Dict[
284            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
285        ] = {}
286        _body_params: Optional[bytes] = None
287
288        # process the path parameters
289        if organization is not None:
290            _path_params['organization'] = organization
291        if extraction_id is not None:
292            _path_params['extractionId'] = extraction_id
293        # process the query parameters
294        # process the header parameters
295        # process the form parameters
296        # process the body parameter
297
298
299        # set the HTTP header `Accept`
300        if 'Accept' not in _header_params:
301            _header_params['Accept'] = self.api_client.select_header_accept(
302                [
303                    'application/json'
304                ]
305            )
306
307
308        # authentication setting
309        _auth_settings: List[str] = [
310            'bearerAuth'
311        ]
312
313        return self.api_client.param_serialize(
314            method='GET',
315            resource_path='/org/{organization}/extraction/{extractionId}',
316            path_params=_path_params,
317            query_params=_query_params,
318            header_params=_header_params,
319            body=_body_params,
320            post_params=_form_params,
321            files=_files,
322            auth_settings=_auth_settings,
323            collection_formats=_collection_formats,
324            _host=_host,
325            _request_auth=_request_auth
326        )
327
328
329
330
331    @validate_call
332    def start_extraction(
333        self,
334        organization: StrictStr,
335        start_extraction_request: StartExtractionRequest,
336        _request_timeout: Union[
337            None,
338            Annotated[StrictFloat, Field(gt=0)],
339            Tuple[
340                Annotated[StrictFloat, Field(gt=0)],
341                Annotated[StrictFloat, Field(gt=0)]
342            ]
343        ] = None,
344        _request_auth: Optional[Dict[StrictStr, Any]] = None,
345        _content_type: Optional[StrictStr] = None,
346        _headers: Optional[Dict[StrictStr, Any]] = None,
347        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
348    ) -> StartExtractionResponse:
349        """Start content extraction from a file
350
351
352        :param organization: (required)
353        :type organization: str
354        :param start_extraction_request: (required)
355        :type start_extraction_request: StartExtractionRequest
356        :param _request_timeout: timeout setting for this request. If one
357                                 number provided, it will be total request
358                                 timeout. It can also be a pair (tuple) of
359                                 (connection, read) timeouts.
360        :type _request_timeout: int, tuple(int, int), optional
361        :param _request_auth: set to override the auth_settings for an a single
362                              request; this effectively ignores the
363                              authentication in the spec for a single request.
364        :type _request_auth: dict, optional
365        :param _content_type: force content-type for the request.
366        :type _content_type: str, Optional
367        :param _headers: set to override the headers for a single
368                         request; this effectively ignores the headers
369                         in the spec for a single request.
370        :type _headers: dict, optional
371        :param _host_index: set to override the host_index for a single
372                            request; this effectively ignores the host_index
373                            in the spec for a single request.
374        :type _host_index: int, optional
375        :return: Returns the result object.
376        """ # noqa: E501
377
378        _param = self._start_extraction_serialize(
379            organization=organization,
380            start_extraction_request=start_extraction_request,
381            _request_auth=_request_auth,
382            _content_type=_content_type,
383            _headers=_headers,
384            _host_index=_host_index
385        )
386
387        _response_types_map: Dict[str, Optional[str]] = {
388            '200': "StartExtractionResponse",
389            '400': "GetPipelines400Response",
390            '401': "GetPipelines400Response",
391            '403': "GetPipelines400Response",
392            '404': "GetPipelines400Response",
393            '500': "GetPipelines400Response",
394        }
395        response_data = self.api_client.call_api(
396            *_param,
397            _request_timeout=_request_timeout
398        )
399        response_data.read()
400        return self.api_client.response_deserialize(
401            response_data=response_data,
402            response_types_map=_response_types_map,
403        ).data
404
405
406    @validate_call
407    def start_extraction_with_http_info(
408        self,
409        organization: StrictStr,
410        start_extraction_request: StartExtractionRequest,
411        _request_timeout: Union[
412            None,
413            Annotated[StrictFloat, Field(gt=0)],
414            Tuple[
415                Annotated[StrictFloat, Field(gt=0)],
416                Annotated[StrictFloat, Field(gt=0)]
417            ]
418        ] = None,
419        _request_auth: Optional[Dict[StrictStr, Any]] = None,
420        _content_type: Optional[StrictStr] = None,
421        _headers: Optional[Dict[StrictStr, Any]] = None,
422        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
423    ) -> ApiResponse[StartExtractionResponse]:
424        """Start content extraction from a file
425
426
427        :param organization: (required)
428        :type organization: str
429        :param start_extraction_request: (required)
430        :type start_extraction_request: StartExtractionRequest
431        :param _request_timeout: timeout setting for this request. If one
432                                 number provided, it will be total request
433                                 timeout. It can also be a pair (tuple) of
434                                 (connection, read) timeouts.
435        :type _request_timeout: int, tuple(int, int), optional
436        :param _request_auth: set to override the auth_settings for an a single
437                              request; this effectively ignores the
438                              authentication in the spec for a single request.
439        :type _request_auth: dict, optional
440        :param _content_type: force content-type for the request.
441        :type _content_type: str, Optional
442        :param _headers: set to override the headers for a single
443                         request; this effectively ignores the headers
444                         in the spec for a single request.
445        :type _headers: dict, optional
446        :param _host_index: set to override the host_index for a single
447                            request; this effectively ignores the host_index
448                            in the spec for a single request.
449        :type _host_index: int, optional
450        :return: Returns the result object.
451        """ # noqa: E501
452
453        _param = self._start_extraction_serialize(
454            organization=organization,
455            start_extraction_request=start_extraction_request,
456            _request_auth=_request_auth,
457            _content_type=_content_type,
458            _headers=_headers,
459            _host_index=_host_index
460        )
461
462        _response_types_map: Dict[str, Optional[str]] = {
463            '200': "StartExtractionResponse",
464            '400': "GetPipelines400Response",
465            '401': "GetPipelines400Response",
466            '403': "GetPipelines400Response",
467            '404': "GetPipelines400Response",
468            '500': "GetPipelines400Response",
469        }
470        response_data = self.api_client.call_api(
471            *_param,
472            _request_timeout=_request_timeout
473        )
474        response_data.read()
475        return self.api_client.response_deserialize(
476            response_data=response_data,
477            response_types_map=_response_types_map,
478        )
479
480
481    @validate_call
482    def start_extraction_without_preload_content(
483        self,
484        organization: StrictStr,
485        start_extraction_request: StartExtractionRequest,
486        _request_timeout: Union[
487            None,
488            Annotated[StrictFloat, Field(gt=0)],
489            Tuple[
490                Annotated[StrictFloat, Field(gt=0)],
491                Annotated[StrictFloat, Field(gt=0)]
492            ]
493        ] = None,
494        _request_auth: Optional[Dict[StrictStr, Any]] = None,
495        _content_type: Optional[StrictStr] = None,
496        _headers: Optional[Dict[StrictStr, Any]] = None,
497        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
498    ) -> RESTResponseType:
499        """Start content extraction from a file
500
501
502        :param organization: (required)
503        :type organization: str
504        :param start_extraction_request: (required)
505        :type start_extraction_request: StartExtractionRequest
506        :param _request_timeout: timeout setting for this request. If one
507                                 number provided, it will be total request
508                                 timeout. It can also be a pair (tuple) of
509                                 (connection, read) timeouts.
510        :type _request_timeout: int, tuple(int, int), optional
511        :param _request_auth: set to override the auth_settings for an a single
512                              request; this effectively ignores the
513                              authentication in the spec for a single request.
514        :type _request_auth: dict, optional
515        :param _content_type: force content-type for the request.
516        :type _content_type: str, Optional
517        :param _headers: set to override the headers for a single
518                         request; this effectively ignores the headers
519                         in the spec for a single request.
520        :type _headers: dict, optional
521        :param _host_index: set to override the host_index for a single
522                            request; this effectively ignores the host_index
523                            in the spec for a single request.
524        :type _host_index: int, optional
525        :return: Returns the result object.
526        """ # noqa: E501
527
528        _param = self._start_extraction_serialize(
529            organization=organization,
530            start_extraction_request=start_extraction_request,
531            _request_auth=_request_auth,
532            _content_type=_content_type,
533            _headers=_headers,
534            _host_index=_host_index
535        )
536
537        _response_types_map: Dict[str, Optional[str]] = {
538            '200': "StartExtractionResponse",
539            '400': "GetPipelines400Response",
540            '401': "GetPipelines400Response",
541            '403': "GetPipelines400Response",
542            '404': "GetPipelines400Response",
543            '500': "GetPipelines400Response",
544        }
545        response_data = self.api_client.call_api(
546            *_param,
547            _request_timeout=_request_timeout
548        )
549        return response_data.response
550
551
552    def _start_extraction_serialize(
553        self,
554        organization,
555        start_extraction_request,
556        _request_auth,
557        _content_type,
558        _headers,
559        _host_index,
560    ) -> RequestSerialized:
561
562        _host = None
563
564        _collection_formats: Dict[str, str] = {
565        }
566
567        _path_params: Dict[str, str] = {}
568        _query_params: List[Tuple[str, str]] = []
569        _header_params: Dict[str, Optional[str]] = _headers or {}
570        _form_params: List[Tuple[str, str]] = []
571        _files: Dict[
572            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
573        ] = {}
574        _body_params: Optional[bytes] = None
575
576        # process the path parameters
577        if organization is not None:
578            _path_params['organization'] = organization
579        # process the query parameters
580        # process the header parameters
581        # process the form parameters
582        # process the body parameter
583        if start_extraction_request is not None:
584            _body_params = start_extraction_request
585
586
587        # set the HTTP header `Accept`
588        if 'Accept' not in _header_params:
589            _header_params['Accept'] = self.api_client.select_header_accept(
590                [
591                    'application/json'
592                ]
593            )
594
595        # set the HTTP header `Content-Type`
596        if _content_type:
597            _header_params['Content-Type'] = _content_type
598        else:
599            _default_content_type = (
600                self.api_client.select_header_content_type(
601                    [
602                        'application/json'
603                    ]
604                )
605            )
606            if _default_content_type is not None:
607                _header_params['Content-Type'] = _default_content_type
608
609        # authentication setting
610        _auth_settings: List[str] = [
611            'bearerAuth'
612        ]
613
614        return self.api_client.param_serialize(
615            method='POST',
616            resource_path='/org/{organization}/extraction',
617            path_params=_path_params,
618            query_params=_query_params,
619            header_params=_header_params,
620            body=_body_params,
621            post_params=_form_params,
622            files=_files,
623            auth_settings=_auth_settings,
624            collection_formats=_collection_formats,
625            _host=_host,
626            _request_auth=_request_auth
627        )

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: 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: 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
 64        :param organization: (required)
 65        :type organization: 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=organization,
 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

Get extraction result

Parameters
  • organization: (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: 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]:
118    @validate_call
119    def get_extraction_result_with_http_info(
120        self,
121        organization: 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
139        :param organization: (required)
140        :type organization: str
141        :param extraction_id: (required)
142        :type extraction_id: str
143        :param _request_timeout: timeout setting for this request. If one
144                                 number provided, it will be total request
145                                 timeout. It can also be a pair (tuple) of
146                                 (connection, read) timeouts.
147        :type _request_timeout: int, tuple(int, int), optional
148        :param _request_auth: set to override the auth_settings for an a single
149                              request; this effectively ignores the
150                              authentication in the spec for a single request.
151        :type _request_auth: dict, optional
152        :param _content_type: force content-type for the request.
153        :type _content_type: str, Optional
154        :param _headers: set to override the headers for a single
155                         request; this effectively ignores the headers
156                         in the spec for a single request.
157        :type _headers: dict, optional
158        :param _host_index: set to override the host_index for a single
159                            request; this effectively ignores the host_index
160                            in the spec for a single request.
161        :type _host_index: int, optional
162        :return: Returns the result object.
163        """ # noqa: E501
164
165        _param = self._get_extraction_result_serialize(
166            organization=organization,
167            extraction_id=extraction_id,
168            _request_auth=_request_auth,
169            _content_type=_content_type,
170            _headers=_headers,
171            _host_index=_host_index
172        )
173
174        _response_types_map: Dict[str, Optional[str]] = {
175            '200': "ExtractionResultResponse",
176            '400': "GetPipelines400Response",
177            '401': "GetPipelines400Response",
178            '403': "GetPipelines400Response",
179            '404': "GetPipelines400Response",
180            '500': "GetPipelines400Response",
181        }
182        response_data = self.api_client.call_api(
183            *_param,
184            _request_timeout=_request_timeout
185        )
186        response_data.read()
187        return self.api_client.response_deserialize(
188            response_data=response_data,
189            response_types_map=_response_types_map,
190        )

Get extraction result

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

Get extraction result

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

Start content extraction from a file

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

Start content extraction from a file

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

Start content extraction from a file

Parameters
  • organization: (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.