# This file was auto-generated by Fern from our API Definition. import typing import urllib.parse from json.decoder import JSONDecodeError from ...core.api_error import ApiError from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ...core.jsonable_encoder import jsonable_encoder from ...core.remove_none_from_dict import remove_none_from_dict from ...errors.unprocessable_entity_error import UnprocessableEntityError from ...types.http_validation_error import HttpValidationError from ...types.llama_parse_supported_file_extensions import LlamaParseSupportedFileExtensions from ...types.parser_languages import ParserLanguages from ...types.parsing_history_item import ParsingHistoryItem from ...types.parsing_job import ParsingJob from ...types.parsing_job_json_result import ParsingJobJsonResult from ...types.parsing_job_markdown_result import ParsingJobMarkdownResult from ...types.parsing_job_structured_result import ParsingJobStructuredResult from ...types.parsing_job_text_result import ParsingJobTextResult from ...types.parsing_mode import ParsingMode from ...types.presigned_url import PresignedUrl try: import pydantic if pydantic.__version__.startswith("1."): raise ImportError import pydantic.v1 as pydantic # type: ignore except ImportError: import pydantic # type: ignore # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class ParsingClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper def get_job_image_result(self, job_id: str, name: str) -> None: """ Get a job by id Parameters: - job_id: str. - name: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_image_result( job_id="string", name="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/image/{name}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_supported_file_extensions(self) -> typing.List[LlamaParseSupportedFileExtensions]: """ Get a list of supported file extensions --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_supported_file_extensions() """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/supported_file_extensions"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[LlamaParseSupportedFileExtensions], _response.json()) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def screenshot( self, *, organization_id: typing.Optional[str] = None, project_id: typing.Optional[str] = None, file: typing.Optional[str] = OMIT, do_not_cache: bool, http_proxy: str, input_s_3_path: str, input_s_3_region: str, input_url: str, invalidate_cache: bool, max_pages: typing.Optional[int] = OMIT, output_s_3_path_prefix: str, output_s_3_region: str, target_pages: str, webhook_url: str, job_timeout_in_seconds: float, job_timeout_extra_time_per_page_in_seconds: float, ) -> ParsingJob: """ Parameters: - organization_id: typing.Optional[str]. - project_id: typing.Optional[str]. - file: typing.Optional[str]. - do_not_cache: bool. - http_proxy: str. - input_s_3_path: str. - input_s_3_region: str. - input_url: str. - invalidate_cache: bool. - max_pages: typing.Optional[int]. - output_s_3_path_prefix: str. - output_s_3_region: str. - target_pages: str. - webhook_url: str. - job_timeout_in_seconds: float. - job_timeout_extra_time_per_page_in_seconds: float. """ _request: typing.Dict[str, typing.Any] = { "do_not_cache": do_not_cache, "http_proxy": http_proxy, "input_s3_path": input_s_3_path, "input_s3_region": input_s_3_region, "input_url": input_url, "invalidate_cache": invalidate_cache, "output_s3_path_prefix": output_s_3_path_prefix, "output_s3_region": output_s_3_region, "target_pages": target_pages, "webhook_url": webhook_url, "job_timeout_in_seconds": job_timeout_in_seconds, "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds, } if file is not OMIT: _request["file"] = file if max_pages is not OMIT: _request["max_pages"] = max_pages _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/screenshot"), params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def upload_file( self, *, organization_id: typing.Optional[str] = None, project_id: typing.Optional[str] = None, file: typing.Optional[str] = OMIT, adaptive_long_table: bool, annotate_links: bool, auto_mode: bool, auto_mode_trigger_on_image_in_page: bool, auto_mode_trigger_on_table_in_page: bool, auto_mode_trigger_on_text_in_page: str, auto_mode_trigger_on_regexp_in_page: str, azure_openai_api_version: str, azure_openai_deployment_name: str, azure_openai_endpoint: str, azure_openai_key: str, bbox_bottom: float, bbox_left: float, bbox_right: float, bbox_top: float, compact_markdown_table: bool, disable_ocr: bool, disable_reconstruction: bool, disable_image_extraction: bool, do_not_cache: bool, do_not_unroll_columns: bool, extract_charts: bool, guess_xlsx_sheet_name: bool, html_make_all_elements_visible: bool, html_remove_fixed_elements: bool, html_remove_navigation_elements: bool, http_proxy: str, input_s_3_path: str, input_s_3_region: str, input_url: str, invalidate_cache: bool, language: typing.List[ParserLanguages], extract_layout: bool, max_pages: typing.Optional[int] = OMIT, output_pdf_of_document: bool, output_s_3_path_prefix: str, output_s_3_region: str, page_prefix: str, page_separator: str, page_suffix: str, preserve_layout_alignment_across_pages: bool, skip_diagonal_text: bool, spreadsheet_extract_sub_tables: bool, structured_output: bool, structured_output_json_schema: str, structured_output_json_schema_name: str, take_screenshot: bool, target_pages: str, vendor_multimodal_api_key: str, vendor_multimodal_model_name: str, model: str, webhook_url: str, preset: str, parse_mode: typing.Optional[ParsingMode] = OMIT, system_prompt: str, system_prompt_append: str, user_prompt: str, job_timeout_in_seconds: float, job_timeout_extra_time_per_page_in_seconds: float, strict_mode_image_extraction: bool, strict_mode_image_ocr: bool, strict_mode_reconstruction: bool, strict_mode_buggy_font: bool, ignore_document_elements_for_layout_detection: bool, output_tables_as_html: bool, use_vendor_multimodal_model: bool, bounding_box: str, gpt_4_o_mode: bool, gpt_4_o_api_key: str, complemental_formatting_instruction: str, content_guideline_instruction: str, premium_mode: bool, is_formatting_instruction: bool, continuous_mode: bool, parsing_instruction: str, fast_mode: bool, formatting_instruction: str, ) -> ParsingJob: """ Upload a file to s3 and create a job. return a job id Parameters: - organization_id: typing.Optional[str]. - project_id: typing.Optional[str]. - file: typing.Optional[str]. - adaptive_long_table: bool. - annotate_links: bool. - auto_mode: bool. - auto_mode_trigger_on_image_in_page: bool. - auto_mode_trigger_on_table_in_page: bool. - auto_mode_trigger_on_text_in_page: str. - auto_mode_trigger_on_regexp_in_page: str. - azure_openai_api_version: str. - azure_openai_deployment_name: str. - azure_openai_endpoint: str. - azure_openai_key: str. - bbox_bottom: float. - bbox_left: float. - bbox_right: float. - bbox_top: float. - compact_markdown_table: bool. - disable_ocr: bool. - disable_reconstruction: bool. - disable_image_extraction: bool. - do_not_cache: bool. - do_not_unroll_columns: bool. - extract_charts: bool. - guess_xlsx_sheet_name: bool. - html_make_all_elements_visible: bool. - html_remove_fixed_elements: bool. - html_remove_navigation_elements: bool. - http_proxy: str. - input_s_3_path: str. - input_s_3_region: str. - input_url: str. - invalidate_cache: bool. - language: typing.List[ParserLanguages]. - extract_layout: bool. - max_pages: typing.Optional[int]. - output_pdf_of_document: bool. - output_s_3_path_prefix: str. - output_s_3_region: str. - page_prefix: str. - page_separator: str. - page_suffix: str. - preserve_layout_alignment_across_pages: bool. - skip_diagonal_text: bool. - spreadsheet_extract_sub_tables: bool. - structured_output: bool. - structured_output_json_schema: str. - structured_output_json_schema_name: str. - take_screenshot: bool. - target_pages: str. - vendor_multimodal_api_key: str. - vendor_multimodal_model_name: str. - model: str. - webhook_url: str. - preset: str. - parse_mode: typing.Optional[ParsingMode]. - system_prompt: str. - system_prompt_append: str. - user_prompt: str. - job_timeout_in_seconds: float. - job_timeout_extra_time_per_page_in_seconds: float. - strict_mode_image_extraction: bool. - strict_mode_image_ocr: bool. - strict_mode_reconstruction: bool. - strict_mode_buggy_font: bool. - ignore_document_elements_for_layout_detection: bool. - output_tables_as_html: bool. - use_vendor_multimodal_model: bool. - bounding_box: str. - gpt_4_o_mode: bool. - gpt_4_o_api_key: str. - complemental_formatting_instruction: str. - content_guideline_instruction: str. - premium_mode: bool. - is_formatting_instruction: bool. - continuous_mode: bool. - parsing_instruction: str. - fast_mode: bool. - formatting_instruction: str. """ _request: typing.Dict[str, typing.Any] = { "adaptive_long_table": adaptive_long_table, "annotate_links": annotate_links, "auto_mode": auto_mode, "auto_mode_trigger_on_image_in_page": auto_mode_trigger_on_image_in_page, "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page, "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page, "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page, "azure_openai_api_version": azure_openai_api_version, "azure_openai_deployment_name": azure_openai_deployment_name, "azure_openai_endpoint": azure_openai_endpoint, "azure_openai_key": azure_openai_key, "bbox_bottom": bbox_bottom, "bbox_left": bbox_left, "bbox_right": bbox_right, "bbox_top": bbox_top, "compact_markdown_table": compact_markdown_table, "disable_ocr": disable_ocr, "disable_reconstruction": disable_reconstruction, "disable_image_extraction": disable_image_extraction, "do_not_cache": do_not_cache, "do_not_unroll_columns": do_not_unroll_columns, "extract_charts": extract_charts, "guess_xlsx_sheet_name": guess_xlsx_sheet_name, "html_make_all_elements_visible": html_make_all_elements_visible, "html_remove_fixed_elements": html_remove_fixed_elements, "html_remove_navigation_elements": html_remove_navigation_elements, "http_proxy": http_proxy, "input_s3_path": input_s_3_path, "input_s3_region": input_s_3_region, "input_url": input_url, "invalidate_cache": invalidate_cache, "language": language, "extract_layout": extract_layout, "output_pdf_of_document": output_pdf_of_document, "output_s3_path_prefix": output_s_3_path_prefix, "output_s3_region": output_s_3_region, "page_prefix": page_prefix, "page_separator": page_separator, "page_suffix": page_suffix, "preserve_layout_alignment_across_pages": preserve_layout_alignment_across_pages, "skip_diagonal_text": skip_diagonal_text, "spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables, "structured_output": structured_output, "structured_output_json_schema": structured_output_json_schema, "structured_output_json_schema_name": structured_output_json_schema_name, "take_screenshot": take_screenshot, "target_pages": target_pages, "vendor_multimodal_api_key": vendor_multimodal_api_key, "vendor_multimodal_model_name": vendor_multimodal_model_name, "model": model, "webhook_url": webhook_url, "preset": preset, "system_prompt": system_prompt, "system_prompt_append": system_prompt_append, "user_prompt": user_prompt, "job_timeout_in_seconds": job_timeout_in_seconds, "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds, "strict_mode_image_extraction": strict_mode_image_extraction, "strict_mode_image_ocr": strict_mode_image_ocr, "strict_mode_reconstruction": strict_mode_reconstruction, "strict_mode_buggy_font": strict_mode_buggy_font, "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection, "output_tables_as_HTML": output_tables_as_html, "use_vendor_multimodal_model": use_vendor_multimodal_model, "bounding_box": bounding_box, "gpt4o_mode": gpt_4_o_mode, "gpt4o_api_key": gpt_4_o_api_key, "complemental_formatting_instruction": complemental_formatting_instruction, "content_guideline_instruction": content_guideline_instruction, "premium_mode": premium_mode, "is_formatting_instruction": is_formatting_instruction, "continuous_mode": continuous_mode, "parsing_instruction": parsing_instruction, "fast_mode": fast_mode, "formatting_instruction": formatting_instruction, } if file is not OMIT: _request["file"] = file if max_pages is not OMIT: _request["max_pages"] = max_pages if parse_mode is not OMIT: _request["parse_mode"] = parse_mode _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"), params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job(self, job_id: str) -> ParsingJob: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_parsing_job_details(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_parsing_job_details( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/details"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_text_result(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> ParsingJobTextResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_text_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/text"), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobTextResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_raw_text_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_raw_text_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/pdf" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_structured_result( self, job_id: str, *, organization_id: typing.Optional[str] = None ) -> ParsingJobStructuredResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_structured_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/structured" ), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobStructuredResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_raw_structured_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_raw_structured_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/structured" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_raw_xlsx_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_raw_xlsx_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/xlsx" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_result(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> ParsingJobMarkdownResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/markdown" ), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobMarkdownResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_raw_md_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_raw_md_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/markdown" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_json_result(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> ParsingJobJsonResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_json_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/json"), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobJsonResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_job_json_raw_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_job_json_raw_result( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/json" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def get_parsing_history_result(self) -> typing.List[ParsingHistoryItem]: """ Get parsing history for user --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.get_parsing_history_result() """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/history"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ParsingHistoryItem], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) def generate_presigned_url(self, job_id: str, filename: str) -> PresignedUrl: """ Generate a presigned URL for a job Parameters: - job_id: str. - filename: str. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.parsing.generate_presigned_url( job_id="string", filename="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/read/{filename}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(PresignedUrl, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) class AsyncParsingClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper async def get_job_image_result(self, job_id: str, name: str) -> None: """ Get a job by id Parameters: - job_id: str. - name: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_image_result( job_id="string", name="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/image/{name}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_supported_file_extensions(self) -> typing.List[LlamaParseSupportedFileExtensions]: """ Get a list of supported file extensions --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_supported_file_extensions() """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/supported_file_extensions"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[LlamaParseSupportedFileExtensions], _response.json()) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def screenshot( self, *, organization_id: typing.Optional[str] = None, project_id: typing.Optional[str] = None, file: typing.Optional[str] = OMIT, do_not_cache: bool, http_proxy: str, input_s_3_path: str, input_s_3_region: str, input_url: str, invalidate_cache: bool, max_pages: typing.Optional[int] = OMIT, output_s_3_path_prefix: str, output_s_3_region: str, target_pages: str, webhook_url: str, job_timeout_in_seconds: float, job_timeout_extra_time_per_page_in_seconds: float, ) -> ParsingJob: """ Parameters: - organization_id: typing.Optional[str]. - project_id: typing.Optional[str]. - file: typing.Optional[str]. - do_not_cache: bool. - http_proxy: str. - input_s_3_path: str. - input_s_3_region: str. - input_url: str. - invalidate_cache: bool. - max_pages: typing.Optional[int]. - output_s_3_path_prefix: str. - output_s_3_region: str. - target_pages: str. - webhook_url: str. - job_timeout_in_seconds: float. - job_timeout_extra_time_per_page_in_seconds: float. """ _request: typing.Dict[str, typing.Any] = { "do_not_cache": do_not_cache, "http_proxy": http_proxy, "input_s3_path": input_s_3_path, "input_s3_region": input_s_3_region, "input_url": input_url, "invalidate_cache": invalidate_cache, "output_s3_path_prefix": output_s_3_path_prefix, "output_s3_region": output_s_3_region, "target_pages": target_pages, "webhook_url": webhook_url, "job_timeout_in_seconds": job_timeout_in_seconds, "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds, } if file is not OMIT: _request["file"] = file if max_pages is not OMIT: _request["max_pages"] = max_pages _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/screenshot"), params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def upload_file( self, *, organization_id: typing.Optional[str] = None, project_id: typing.Optional[str] = None, file: typing.Optional[str] = OMIT, adaptive_long_table: bool, annotate_links: bool, auto_mode: bool, auto_mode_trigger_on_image_in_page: bool, auto_mode_trigger_on_table_in_page: bool, auto_mode_trigger_on_text_in_page: str, auto_mode_trigger_on_regexp_in_page: str, azure_openai_api_version: str, azure_openai_deployment_name: str, azure_openai_endpoint: str, azure_openai_key: str, bbox_bottom: float, bbox_left: float, bbox_right: float, bbox_top: float, compact_markdown_table: bool, disable_ocr: bool, disable_reconstruction: bool, disable_image_extraction: bool, do_not_cache: bool, do_not_unroll_columns: bool, extract_charts: bool, guess_xlsx_sheet_name: bool, html_make_all_elements_visible: bool, html_remove_fixed_elements: bool, html_remove_navigation_elements: bool, http_proxy: str, input_s_3_path: str, input_s_3_region: str, input_url: str, invalidate_cache: bool, language: typing.List[ParserLanguages], extract_layout: bool, max_pages: typing.Optional[int] = OMIT, output_pdf_of_document: bool, output_s_3_path_prefix: str, output_s_3_region: str, page_prefix: str, page_separator: str, page_suffix: str, preserve_layout_alignment_across_pages: bool, skip_diagonal_text: bool, spreadsheet_extract_sub_tables: bool, structured_output: bool, structured_output_json_schema: str, structured_output_json_schema_name: str, take_screenshot: bool, target_pages: str, vendor_multimodal_api_key: str, vendor_multimodal_model_name: str, model: str, webhook_url: str, preset: str, parse_mode: typing.Optional[ParsingMode] = OMIT, system_prompt: str, system_prompt_append: str, user_prompt: str, job_timeout_in_seconds: float, job_timeout_extra_time_per_page_in_seconds: float, strict_mode_image_extraction: bool, strict_mode_image_ocr: bool, strict_mode_reconstruction: bool, strict_mode_buggy_font: bool, ignore_document_elements_for_layout_detection: bool, output_tables_as_html: bool, use_vendor_multimodal_model: bool, bounding_box: str, gpt_4_o_mode: bool, gpt_4_o_api_key: str, complemental_formatting_instruction: str, content_guideline_instruction: str, premium_mode: bool, is_formatting_instruction: bool, continuous_mode: bool, parsing_instruction: str, fast_mode: bool, formatting_instruction: str, ) -> ParsingJob: """ Upload a file to s3 and create a job. return a job id Parameters: - organization_id: typing.Optional[str]. - project_id: typing.Optional[str]. - file: typing.Optional[str]. - adaptive_long_table: bool. - annotate_links: bool. - auto_mode: bool. - auto_mode_trigger_on_image_in_page: bool. - auto_mode_trigger_on_table_in_page: bool. - auto_mode_trigger_on_text_in_page: str. - auto_mode_trigger_on_regexp_in_page: str. - azure_openai_api_version: str. - azure_openai_deployment_name: str. - azure_openai_endpoint: str. - azure_openai_key: str. - bbox_bottom: float. - bbox_left: float. - bbox_right: float. - bbox_top: float. - compact_markdown_table: bool. - disable_ocr: bool. - disable_reconstruction: bool. - disable_image_extraction: bool. - do_not_cache: bool. - do_not_unroll_columns: bool. - extract_charts: bool. - guess_xlsx_sheet_name: bool. - html_make_all_elements_visible: bool. - html_remove_fixed_elements: bool. - html_remove_navigation_elements: bool. - http_proxy: str. - input_s_3_path: str. - input_s_3_region: str. - input_url: str. - invalidate_cache: bool. - language: typing.List[ParserLanguages]. - extract_layout: bool. - max_pages: typing.Optional[int]. - output_pdf_of_document: bool. - output_s_3_path_prefix: str. - output_s_3_region: str. - page_prefix: str. - page_separator: str. - page_suffix: str. - preserve_layout_alignment_across_pages: bool. - skip_diagonal_text: bool. - spreadsheet_extract_sub_tables: bool. - structured_output: bool. - structured_output_json_schema: str. - structured_output_json_schema_name: str. - take_screenshot: bool. - target_pages: str. - vendor_multimodal_api_key: str. - vendor_multimodal_model_name: str. - model: str. - webhook_url: str. - preset: str. - parse_mode: typing.Optional[ParsingMode]. - system_prompt: str. - system_prompt_append: str. - user_prompt: str. - job_timeout_in_seconds: float. - job_timeout_extra_time_per_page_in_seconds: float. - strict_mode_image_extraction: bool. - strict_mode_image_ocr: bool. - strict_mode_reconstruction: bool. - strict_mode_buggy_font: bool. - ignore_document_elements_for_layout_detection: bool. - output_tables_as_html: bool. - use_vendor_multimodal_model: bool. - bounding_box: str. - gpt_4_o_mode: bool. - gpt_4_o_api_key: str. - complemental_formatting_instruction: str. - content_guideline_instruction: str. - premium_mode: bool. - is_formatting_instruction: bool. - continuous_mode: bool. - parsing_instruction: str. - fast_mode: bool. - formatting_instruction: str. """ _request: typing.Dict[str, typing.Any] = { "adaptive_long_table": adaptive_long_table, "annotate_links": annotate_links, "auto_mode": auto_mode, "auto_mode_trigger_on_image_in_page": auto_mode_trigger_on_image_in_page, "auto_mode_trigger_on_table_in_page": auto_mode_trigger_on_table_in_page, "auto_mode_trigger_on_text_in_page": auto_mode_trigger_on_text_in_page, "auto_mode_trigger_on_regexp_in_page": auto_mode_trigger_on_regexp_in_page, "azure_openai_api_version": azure_openai_api_version, "azure_openai_deployment_name": azure_openai_deployment_name, "azure_openai_endpoint": azure_openai_endpoint, "azure_openai_key": azure_openai_key, "bbox_bottom": bbox_bottom, "bbox_left": bbox_left, "bbox_right": bbox_right, "bbox_top": bbox_top, "compact_markdown_table": compact_markdown_table, "disable_ocr": disable_ocr, "disable_reconstruction": disable_reconstruction, "disable_image_extraction": disable_image_extraction, "do_not_cache": do_not_cache, "do_not_unroll_columns": do_not_unroll_columns, "extract_charts": extract_charts, "guess_xlsx_sheet_name": guess_xlsx_sheet_name, "html_make_all_elements_visible": html_make_all_elements_visible, "html_remove_fixed_elements": html_remove_fixed_elements, "html_remove_navigation_elements": html_remove_navigation_elements, "http_proxy": http_proxy, "input_s3_path": input_s_3_path, "input_s3_region": input_s_3_region, "input_url": input_url, "invalidate_cache": invalidate_cache, "language": language, "extract_layout": extract_layout, "output_pdf_of_document": output_pdf_of_document, "output_s3_path_prefix": output_s_3_path_prefix, "output_s3_region": output_s_3_region, "page_prefix": page_prefix, "page_separator": page_separator, "page_suffix": page_suffix, "preserve_layout_alignment_across_pages": preserve_layout_alignment_across_pages, "skip_diagonal_text": skip_diagonal_text, "spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables, "structured_output": structured_output, "structured_output_json_schema": structured_output_json_schema, "structured_output_json_schema_name": structured_output_json_schema_name, "take_screenshot": take_screenshot, "target_pages": target_pages, "vendor_multimodal_api_key": vendor_multimodal_api_key, "vendor_multimodal_model_name": vendor_multimodal_model_name, "model": model, "webhook_url": webhook_url, "preset": preset, "system_prompt": system_prompt, "system_prompt_append": system_prompt_append, "user_prompt": user_prompt, "job_timeout_in_seconds": job_timeout_in_seconds, "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds, "strict_mode_image_extraction": strict_mode_image_extraction, "strict_mode_image_ocr": strict_mode_image_ocr, "strict_mode_reconstruction": strict_mode_reconstruction, "strict_mode_buggy_font": strict_mode_buggy_font, "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection, "output_tables_as_HTML": output_tables_as_html, "use_vendor_multimodal_model": use_vendor_multimodal_model, "bounding_box": bounding_box, "gpt4o_mode": gpt_4_o_mode, "gpt4o_api_key": gpt_4_o_api_key, "complemental_formatting_instruction": complemental_formatting_instruction, "content_guideline_instruction": content_guideline_instruction, "premium_mode": premium_mode, "is_formatting_instruction": is_formatting_instruction, "continuous_mode": continuous_mode, "parsing_instruction": parsing_instruction, "fast_mode": fast_mode, "formatting_instruction": formatting_instruction, } if file is not OMIT: _request["file"] = file if max_pages is not OMIT: _request["max_pages"] = max_pages if parse_mode is not OMIT: _request["parse_mode"] = parse_mode _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"), params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}), json=jsonable_encoder(_request), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job(self, job_id: str) -> ParsingJob: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJob, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_parsing_job_details(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_parsing_job_details( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/details"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_text_result( self, job_id: str, *, organization_id: typing.Optional[str] = None ) -> ParsingJobTextResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_text_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/text"), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobTextResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_raw_text_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_raw_text_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/pdf" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_structured_result( self, job_id: str, *, organization_id: typing.Optional[str] = None ) -> ParsingJobStructuredResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_structured_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/structured" ), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobStructuredResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_raw_structured_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_raw_structured_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/structured" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_raw_xlsx_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_raw_xlsx_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/xlsx" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_result( self, job_id: str, *, organization_id: typing.Optional[str] = None ) -> ParsingJobMarkdownResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/markdown" ), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobMarkdownResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_raw_md_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_raw_md_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/markdown" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_json_result( self, job_id: str, *, organization_id: typing.Optional[str] = None ) -> ParsingJobJsonResult: """ Get a job by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_json_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/json"), params=remove_none_from_dict({"organization_id": organization_id}), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(ParsingJobJsonResult, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_job_json_raw_result(self, job_id: str) -> typing.Any: """ Get a job by id Parameters: - job_id: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_job_json_raw_result( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/result/raw/json" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.Any, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def get_parsing_history_result(self) -> typing.List[ParsingHistoryItem]: """ Get parsing history for user --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.get_parsing_history_result() """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/history"), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(typing.List[ParsingHistoryItem], _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json) async def generate_presigned_url(self, job_id: str, filename: str) -> PresignedUrl: """ Generate a presigned URL for a job Parameters: - job_id: str. - filename: str. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.parsing.generate_presigned_url( job_id="string", filename="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/read/{filename}" ), headers=self._client_wrapper.get_headers(), timeout=60, ) if 200 <= _response.status_code < 300: return pydantic.parse_obj_as(PresignedUrl, _response.json()) # type: ignore if _response.status_code == 422: raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore try: _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, body=_response.text) raise ApiError(status_code=_response.status_code, body=_response_json)