# 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_crop_box import LlamaParseCropBox from ...types.llama_parse_input_options import LlamaParseInputOptions from ...types.llama_parse_output_options import LlamaParseOutputOptions from ...types.llama_parse_page_ranges import LlamaParsePageRanges from ...types.llama_parse_processing_control import LlamaParseProcessingControl from ...types.llama_parse_tier_options import LlamaParseTierOptions from ...types.llama_parse_webhook_configuration import LlamaParseWebhookConfiguration from ...types.markdown_result import MarkdownResult from ...types.parsing_job import ParsingJob from ...types.structured_result import StructuredResult from ...types.text_result import TextResult 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 AlphaClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper def upload_file_by_id_api_v_2_alpha_1_parse_post( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, client_name: typing.Optional[str] = OMIT, crop_box: typing.Optional[LlamaParseCropBox] = OMIT, disable_cache: typing.Optional[bool] = OMIT, file_id: str, input_options: typing.Optional[LlamaParseInputOptions] = OMIT, output_options: typing.Optional[LlamaParseOutputOptions] = OMIT, page_ranges: typing.Optional[LlamaParsePageRanges] = OMIT, parse_options: LlamaParseTierOptions, processing_control: typing.Optional[LlamaParseProcessingControl] = OMIT, webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]] = OMIT, ) -> ParsingJob: """ Parse an already uploaded file by file ID. Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - client_name: typing.Optional[str]. - crop_box: typing.Optional[LlamaParseCropBox]. Document crop box boundaries - disable_cache: typing.Optional[bool]. - file_id: str. ID of an existing file in the project to parse - input_options: typing.Optional[LlamaParseInputOptions]. Input format-specific parsing options - output_options: typing.Optional[LlamaParseOutputOptions]. Output format and styling options - page_ranges: typing.Optional[LlamaParsePageRanges]. Page range selection options - parse_options: LlamaParseTierOptions. Parsing tier and related configuration options - processing_control: typing.Optional[LlamaParseProcessingControl]. Job processing control and failure handling - webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]]. List of webhook configurations for notifications --- from llama_cloud import (LlamaParseAgenticOptions, LlamaParseCropBox, LlamaParseEmbeddedImagesOptions, LlamaParseExportPdfOptions, LlamaParseFastOptions, LlamaParseHtmlOptions, LlamaParseIgnoreOptions, LlamaParseInputOptions, LlamaParseJobFailureConditions, LlamaParseMarkdownOptions, LlamaParseOcrParameters, LlamaParseOutputOptions, LlamaParsePageRanges, LlamaParsePages, LlamaParsePdfOptions, LlamaParsePresentationOptions, LlamaParseProcessingControl, LlamaParseScreenshotsOptions, LlamaParseSpatialTextOptions, LlamaParseSpreadsheetOptions, LlamaParseTables, LlamaParseTablesAsSpreadsheetOptions, LlamaParseTierOptions, LlamaParseTierOptionsVersion, LlamaParseTimeouts, TierName) from llama_cloud.client import LlamaCloud client = LlamaCloud(token="YOUR_TOKEN", ) client.alpha.upload_file_by_id_api_v_2_alpha_1_parse_post(crop_box=LlamaParseCropBox(), file_id="string", input_options=LlamaParseInputOptions(html=LlamaParseHtmlOptions(), pdf=LlamaParsePdfOptions(), presentation=LlamaParsePresentationOptions(), spreadsheet=LlamaParseSpreadsheetOptions(), ), output_options=LlamaParseOutputOptions(embedded_images=LlamaParseEmbeddedImagesOptions(), export_pdf=LlamaParseExportPdfOptions(), markdown=LlamaParseMarkdownOptions(pages=LlamaParsePages(), tables=LlamaParseTables(), ), screenshots=LlamaParseScreenshotsOptions(), spatial_text=LlamaParseSpatialTextOptions(pages=LlamaParsePages(), ), tables_as_spreadsheet=LlamaParseTablesAsSpreadsheetOptions(), ), page_ranges=LlamaParsePageRanges(), parse_options=LlamaParseTierOptions(agentic_options=LlamaParseAgenticOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), fast_options=LlamaParseFastOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), tier=TierName.FAST, version=LlamaParseTierOptionsVersion.2025_11_18, ), processing_control=LlamaParseProcessingControl(job_failure_conditions=LlamaParseJobFailureConditions(), timeouts=LlamaParseTimeouts(), ), ) """ _request: typing.Dict[str, typing.Any] = {"file_id": file_id, "parse_options": parse_options} if client_name is not OMIT: _request["client_name"] = client_name if crop_box is not OMIT: _request["crop_box"] = crop_box if disable_cache is not OMIT: _request["disable_cache"] = disable_cache if input_options is not OMIT: _request["input_options"] = input_options if output_options is not OMIT: _request["output_options"] = output_options if page_ranges is not OMIT: _request["page_ranges"] = page_ranges if processing_control is not OMIT: _request["processing_control"] = processing_control if webhook_configurations is not OMIT: _request["webhook_configurations"] = webhook_configurations _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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_base_64( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, base_64_file: str, client_name: typing.Optional[str] = OMIT, crop_box: typing.Optional[LlamaParseCropBox] = OMIT, disable_cache: typing.Optional[bool] = OMIT, filename: typing.Optional[str] = OMIT, input_options: typing.Optional[LlamaParseInputOptions] = OMIT, output_options: typing.Optional[LlamaParseOutputOptions] = OMIT, page_ranges: typing.Optional[LlamaParsePageRanges] = OMIT, parse_options: LlamaParseTierOptions, processing_control: typing.Optional[LlamaParseProcessingControl] = OMIT, webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]] = OMIT, ) -> ParsingJob: """ Upload a file using base64 encoded content in JSON request. Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - base_64_file: str. Base64 encoded file content for parsing - client_name: typing.Optional[str]. - crop_box: typing.Optional[LlamaParseCropBox]. Document crop box boundaries - disable_cache: typing.Optional[bool]. - filename: typing.Optional[str]. - input_options: typing.Optional[LlamaParseInputOptions]. Input format-specific parsing options - output_options: typing.Optional[LlamaParseOutputOptions]. Output format and styling options - page_ranges: typing.Optional[LlamaParsePageRanges]. Page range selection options - parse_options: LlamaParseTierOptions. Parsing tier and related configuration options - processing_control: typing.Optional[LlamaParseProcessingControl]. Job processing control and failure handling - webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]]. List of webhook configurations for notifications --- from llama_cloud import (LlamaParseAgenticOptions, LlamaParseCropBox, LlamaParseEmbeddedImagesOptions, LlamaParseExportPdfOptions, LlamaParseFastOptions, LlamaParseHtmlOptions, LlamaParseIgnoreOptions, LlamaParseInputOptions, LlamaParseJobFailureConditions, LlamaParseMarkdownOptions, LlamaParseOcrParameters, LlamaParseOutputOptions, LlamaParsePageRanges, LlamaParsePages, LlamaParsePdfOptions, LlamaParsePresentationOptions, LlamaParseProcessingControl, LlamaParseScreenshotsOptions, LlamaParseSpatialTextOptions, LlamaParseSpreadsheetOptions, LlamaParseTables, LlamaParseTablesAsSpreadsheetOptions, LlamaParseTierOptions, LlamaParseTierOptionsVersion, LlamaParseTimeouts, TierName) from llama_cloud.client import LlamaCloud client = LlamaCloud(token="YOUR_TOKEN", ) client.alpha.upload_file_base_64(base_64_file="string", crop_box=LlamaParseCropBox(), input_options=LlamaParseInputOptions(html=LlamaParseHtmlOptions(), pdf=LlamaParsePdfOptions(), presentation=LlamaParsePresentationOptions(), spreadsheet=LlamaParseSpreadsheetOptions(), ), output_options=LlamaParseOutputOptions(embedded_images=LlamaParseEmbeddedImagesOptions(), export_pdf=LlamaParseExportPdfOptions(), markdown=LlamaParseMarkdownOptions(pages=LlamaParsePages(), tables=LlamaParseTables(), ), screenshots=LlamaParseScreenshotsOptions(), spatial_text=LlamaParseSpatialTextOptions(pages=LlamaParsePages(), ), tables_as_spreadsheet=LlamaParseTablesAsSpreadsheetOptions(), ), page_ranges=LlamaParsePageRanges(), parse_options=LlamaParseTierOptions(agentic_options=LlamaParseAgenticOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), fast_options=LlamaParseFastOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), tier=TierName.FAST, version=LlamaParseTierOptionsVersion.2025_11_18, ), processing_control=LlamaParseProcessingControl(job_failure_conditions=LlamaParseJobFailureConditions(), timeouts=LlamaParseTimeouts(), ), ) """ _request: typing.Dict[str, typing.Any] = {"base64_file": base_64_file, "parse_options": parse_options} if client_name is not OMIT: _request["client_name"] = client_name if crop_box is not OMIT: _request["crop_box"] = crop_box if disable_cache is not OMIT: _request["disable_cache"] = disable_cache if filename is not OMIT: _request["filename"] = filename if input_options is not OMIT: _request["input_options"] = input_options if output_options is not OMIT: _request["output_options"] = output_options if page_ranges is not OMIT: _request["page_ranges"] = page_ranges if processing_control is not OMIT: _request["processing_control"] = processing_control if webhook_configurations is not OMIT: _request["webhook_configurations"] = webhook_configurations _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse/base64"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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_markdown_template(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> MarkdownResult: """ Get a job's markdown result by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.alpha.get_markdown_template( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v2alpha1/parse/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(MarkdownResult, _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_structured_template(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> StructuredResult: """ Get a job's structured result by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.alpha.get_structured_template( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v2alpha1/parse/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(StructuredResult, _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_text_template(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> TextResult: """ Get a job's text result by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.alpha.get_text_template( job_id="string", ) """ _response = self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v2alpha1/parse/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(TextResult, _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_multipart( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None ) -> ParsingJob: """ Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. --- from llama_cloud.client import LlamaCloud client = LlamaCloud( token="YOUR_TOKEN", ) client.alpha.upload_file_multipart() """ _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse/upload"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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 upload_file_by_url( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, client_name: typing.Optional[str] = OMIT, crop_box: typing.Optional[LlamaParseCropBox] = OMIT, disable_cache: typing.Optional[bool] = OMIT, http_proxy: typing.Optional[str] = OMIT, input_options: typing.Optional[LlamaParseInputOptions] = OMIT, output_options: typing.Optional[LlamaParseOutputOptions] = OMIT, page_ranges: typing.Optional[LlamaParsePageRanges] = OMIT, parse_options: LlamaParseTierOptions, processing_control: typing.Optional[LlamaParseProcessingControl] = OMIT, source_url: str, webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]] = OMIT, ) -> ParsingJob: """ Parse a document from a URL. Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - client_name: typing.Optional[str]. - crop_box: typing.Optional[LlamaParseCropBox]. Document crop box boundaries - disable_cache: typing.Optional[bool]. - http_proxy: typing.Optional[str]. - input_options: typing.Optional[LlamaParseInputOptions]. Input format-specific parsing options - output_options: typing.Optional[LlamaParseOutputOptions]. Output format and styling options - page_ranges: typing.Optional[LlamaParsePageRanges]. Page range selection options - parse_options: LlamaParseTierOptions. Parsing tier and related configuration options - processing_control: typing.Optional[LlamaParseProcessingControl]. Job processing control and failure handling - source_url: str. Source URL to fetch document from - webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]]. List of webhook configurations for notifications --- from llama_cloud import (LlamaParseAgenticOptions, LlamaParseCropBox, LlamaParseEmbeddedImagesOptions, LlamaParseExportPdfOptions, LlamaParseFastOptions, LlamaParseHtmlOptions, LlamaParseIgnoreOptions, LlamaParseInputOptions, LlamaParseJobFailureConditions, LlamaParseMarkdownOptions, LlamaParseOcrParameters, LlamaParseOutputOptions, LlamaParsePageRanges, LlamaParsePages, LlamaParsePdfOptions, LlamaParsePresentationOptions, LlamaParseProcessingControl, LlamaParseScreenshotsOptions, LlamaParseSpatialTextOptions, LlamaParseSpreadsheetOptions, LlamaParseTables, LlamaParseTablesAsSpreadsheetOptions, LlamaParseTierOptions, LlamaParseTierOptionsVersion, LlamaParseTimeouts, TierName) from llama_cloud.client import LlamaCloud client = LlamaCloud(token="YOUR_TOKEN", ) client.alpha.upload_file_by_url(crop_box=LlamaParseCropBox(), input_options=LlamaParseInputOptions(html=LlamaParseHtmlOptions(), pdf=LlamaParsePdfOptions(), presentation=LlamaParsePresentationOptions(), spreadsheet=LlamaParseSpreadsheetOptions(), ), output_options=LlamaParseOutputOptions(embedded_images=LlamaParseEmbeddedImagesOptions(), export_pdf=LlamaParseExportPdfOptions(), markdown=LlamaParseMarkdownOptions(pages=LlamaParsePages(), tables=LlamaParseTables(), ), screenshots=LlamaParseScreenshotsOptions(), spatial_text=LlamaParseSpatialTextOptions(pages=LlamaParsePages(), ), tables_as_spreadsheet=LlamaParseTablesAsSpreadsheetOptions(), ), page_ranges=LlamaParsePageRanges(), parse_options=LlamaParseTierOptions(agentic_options=LlamaParseAgenticOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), fast_options=LlamaParseFastOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), tier=TierName.FAST, version=LlamaParseTierOptionsVersion.2025_11_18, ), processing_control=LlamaParseProcessingControl(job_failure_conditions=LlamaParseJobFailureConditions(), timeouts=LlamaParseTimeouts(), ), source_url="string", ) """ _request: typing.Dict[str, typing.Any] = {"parse_options": parse_options, "source_url": source_url} if client_name is not OMIT: _request["client_name"] = client_name if crop_box is not OMIT: _request["crop_box"] = crop_box if disable_cache is not OMIT: _request["disable_cache"] = disable_cache if http_proxy is not OMIT: _request["http_proxy"] = http_proxy if input_options is not OMIT: _request["input_options"] = input_options if output_options is not OMIT: _request["output_options"] = output_options if page_ranges is not OMIT: _request["page_ranges"] = page_ranges if processing_control is not OMIT: _request["processing_control"] = processing_control if webhook_configurations is not OMIT: _request["webhook_configurations"] = webhook_configurations _response = self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse/url"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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) class AsyncAlphaClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper async def upload_file_by_id_api_v_2_alpha_1_parse_post( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, client_name: typing.Optional[str] = OMIT, crop_box: typing.Optional[LlamaParseCropBox] = OMIT, disable_cache: typing.Optional[bool] = OMIT, file_id: str, input_options: typing.Optional[LlamaParseInputOptions] = OMIT, output_options: typing.Optional[LlamaParseOutputOptions] = OMIT, page_ranges: typing.Optional[LlamaParsePageRanges] = OMIT, parse_options: LlamaParseTierOptions, processing_control: typing.Optional[LlamaParseProcessingControl] = OMIT, webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]] = OMIT, ) -> ParsingJob: """ Parse an already uploaded file by file ID. Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - client_name: typing.Optional[str]. - crop_box: typing.Optional[LlamaParseCropBox]. Document crop box boundaries - disable_cache: typing.Optional[bool]. - file_id: str. ID of an existing file in the project to parse - input_options: typing.Optional[LlamaParseInputOptions]. Input format-specific parsing options - output_options: typing.Optional[LlamaParseOutputOptions]. Output format and styling options - page_ranges: typing.Optional[LlamaParsePageRanges]. Page range selection options - parse_options: LlamaParseTierOptions. Parsing tier and related configuration options - processing_control: typing.Optional[LlamaParseProcessingControl]. Job processing control and failure handling - webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]]. List of webhook configurations for notifications --- from llama_cloud import (LlamaParseAgenticOptions, LlamaParseCropBox, LlamaParseEmbeddedImagesOptions, LlamaParseExportPdfOptions, LlamaParseFastOptions, LlamaParseHtmlOptions, LlamaParseIgnoreOptions, LlamaParseInputOptions, LlamaParseJobFailureConditions, LlamaParseMarkdownOptions, LlamaParseOcrParameters, LlamaParseOutputOptions, LlamaParsePageRanges, LlamaParsePages, LlamaParsePdfOptions, LlamaParsePresentationOptions, LlamaParseProcessingControl, LlamaParseScreenshotsOptions, LlamaParseSpatialTextOptions, LlamaParseSpreadsheetOptions, LlamaParseTables, LlamaParseTablesAsSpreadsheetOptions, LlamaParseTierOptions, LlamaParseTierOptionsVersion, LlamaParseTimeouts, TierName) from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud(token="YOUR_TOKEN", ) await client.alpha.upload_file_by_id_api_v_2_alpha_1_parse_post(crop_box=LlamaParseCropBox(), file_id="string", input_options=LlamaParseInputOptions(html=LlamaParseHtmlOptions(), pdf=LlamaParsePdfOptions(), presentation=LlamaParsePresentationOptions(), spreadsheet=LlamaParseSpreadsheetOptions(), ), output_options=LlamaParseOutputOptions(embedded_images=LlamaParseEmbeddedImagesOptions(), export_pdf=LlamaParseExportPdfOptions(), markdown=LlamaParseMarkdownOptions(pages=LlamaParsePages(), tables=LlamaParseTables(), ), screenshots=LlamaParseScreenshotsOptions(), spatial_text=LlamaParseSpatialTextOptions(pages=LlamaParsePages(), ), tables_as_spreadsheet=LlamaParseTablesAsSpreadsheetOptions(), ), page_ranges=LlamaParsePageRanges(), parse_options=LlamaParseTierOptions(agentic_options=LlamaParseAgenticOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), fast_options=LlamaParseFastOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), tier=TierName.FAST, version=LlamaParseTierOptionsVersion.2025_11_18, ), processing_control=LlamaParseProcessingControl(job_failure_conditions=LlamaParseJobFailureConditions(), timeouts=LlamaParseTimeouts(), ), ) """ _request: typing.Dict[str, typing.Any] = {"file_id": file_id, "parse_options": parse_options} if client_name is not OMIT: _request["client_name"] = client_name if crop_box is not OMIT: _request["crop_box"] = crop_box if disable_cache is not OMIT: _request["disable_cache"] = disable_cache if input_options is not OMIT: _request["input_options"] = input_options if output_options is not OMIT: _request["output_options"] = output_options if page_ranges is not OMIT: _request["page_ranges"] = page_ranges if processing_control is not OMIT: _request["processing_control"] = processing_control if webhook_configurations is not OMIT: _request["webhook_configurations"] = webhook_configurations _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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_base_64( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, base_64_file: str, client_name: typing.Optional[str] = OMIT, crop_box: typing.Optional[LlamaParseCropBox] = OMIT, disable_cache: typing.Optional[bool] = OMIT, filename: typing.Optional[str] = OMIT, input_options: typing.Optional[LlamaParseInputOptions] = OMIT, output_options: typing.Optional[LlamaParseOutputOptions] = OMIT, page_ranges: typing.Optional[LlamaParsePageRanges] = OMIT, parse_options: LlamaParseTierOptions, processing_control: typing.Optional[LlamaParseProcessingControl] = OMIT, webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]] = OMIT, ) -> ParsingJob: """ Upload a file using base64 encoded content in JSON request. Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - base_64_file: str. Base64 encoded file content for parsing - client_name: typing.Optional[str]. - crop_box: typing.Optional[LlamaParseCropBox]. Document crop box boundaries - disable_cache: typing.Optional[bool]. - filename: typing.Optional[str]. - input_options: typing.Optional[LlamaParseInputOptions]. Input format-specific parsing options - output_options: typing.Optional[LlamaParseOutputOptions]. Output format and styling options - page_ranges: typing.Optional[LlamaParsePageRanges]. Page range selection options - parse_options: LlamaParseTierOptions. Parsing tier and related configuration options - processing_control: typing.Optional[LlamaParseProcessingControl]. Job processing control and failure handling - webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]]. List of webhook configurations for notifications --- from llama_cloud import (LlamaParseAgenticOptions, LlamaParseCropBox, LlamaParseEmbeddedImagesOptions, LlamaParseExportPdfOptions, LlamaParseFastOptions, LlamaParseHtmlOptions, LlamaParseIgnoreOptions, LlamaParseInputOptions, LlamaParseJobFailureConditions, LlamaParseMarkdownOptions, LlamaParseOcrParameters, LlamaParseOutputOptions, LlamaParsePageRanges, LlamaParsePages, LlamaParsePdfOptions, LlamaParsePresentationOptions, LlamaParseProcessingControl, LlamaParseScreenshotsOptions, LlamaParseSpatialTextOptions, LlamaParseSpreadsheetOptions, LlamaParseTables, LlamaParseTablesAsSpreadsheetOptions, LlamaParseTierOptions, LlamaParseTierOptionsVersion, LlamaParseTimeouts, TierName) from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud(token="YOUR_TOKEN", ) await client.alpha.upload_file_base_64(base_64_file="string", crop_box=LlamaParseCropBox(), input_options=LlamaParseInputOptions(html=LlamaParseHtmlOptions(), pdf=LlamaParsePdfOptions(), presentation=LlamaParsePresentationOptions(), spreadsheet=LlamaParseSpreadsheetOptions(), ), output_options=LlamaParseOutputOptions(embedded_images=LlamaParseEmbeddedImagesOptions(), export_pdf=LlamaParseExportPdfOptions(), markdown=LlamaParseMarkdownOptions(pages=LlamaParsePages(), tables=LlamaParseTables(), ), screenshots=LlamaParseScreenshotsOptions(), spatial_text=LlamaParseSpatialTextOptions(pages=LlamaParsePages(), ), tables_as_spreadsheet=LlamaParseTablesAsSpreadsheetOptions(), ), page_ranges=LlamaParsePageRanges(), parse_options=LlamaParseTierOptions(agentic_options=LlamaParseAgenticOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), fast_options=LlamaParseFastOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), tier=TierName.FAST, version=LlamaParseTierOptionsVersion.2025_11_18, ), processing_control=LlamaParseProcessingControl(job_failure_conditions=LlamaParseJobFailureConditions(), timeouts=LlamaParseTimeouts(), ), ) """ _request: typing.Dict[str, typing.Any] = {"base64_file": base_64_file, "parse_options": parse_options} if client_name is not OMIT: _request["client_name"] = client_name if crop_box is not OMIT: _request["crop_box"] = crop_box if disable_cache is not OMIT: _request["disable_cache"] = disable_cache if filename is not OMIT: _request["filename"] = filename if input_options is not OMIT: _request["input_options"] = input_options if output_options is not OMIT: _request["output_options"] = output_options if page_ranges is not OMIT: _request["page_ranges"] = page_ranges if processing_control is not OMIT: _request["processing_control"] = processing_control if webhook_configurations is not OMIT: _request["webhook_configurations"] = webhook_configurations _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse/base64"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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_markdown_template( self, job_id: str, *, organization_id: typing.Optional[str] = None ) -> MarkdownResult: """ Get a job's markdown result by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.alpha.get_markdown_template( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v2alpha1/parse/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(MarkdownResult, _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_structured_template( self, job_id: str, *, organization_id: typing.Optional[str] = None ) -> StructuredResult: """ Get a job's structured result by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.alpha.get_structured_template( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v2alpha1/parse/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(StructuredResult, _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_text_template(self, job_id: str, *, organization_id: typing.Optional[str] = None) -> TextResult: """ Get a job's text result by id Parameters: - job_id: str. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.alpha.get_text_template( job_id="string", ) """ _response = await self._client_wrapper.httpx_client.request( "GET", urllib.parse.urljoin( f"{self._client_wrapper.get_base_url()}/", f"api/v2alpha1/parse/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(TextResult, _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_multipart( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None ) -> ParsingJob: """ Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. --- from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud( token="YOUR_TOKEN", ) await client.alpha.upload_file_multipart() """ _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse/upload"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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 upload_file_by_url( self, *, project_id: typing.Optional[str] = None, organization_id: typing.Optional[str] = None, client_name: typing.Optional[str] = OMIT, crop_box: typing.Optional[LlamaParseCropBox] = OMIT, disable_cache: typing.Optional[bool] = OMIT, http_proxy: typing.Optional[str] = OMIT, input_options: typing.Optional[LlamaParseInputOptions] = OMIT, output_options: typing.Optional[LlamaParseOutputOptions] = OMIT, page_ranges: typing.Optional[LlamaParsePageRanges] = OMIT, parse_options: LlamaParseTierOptions, processing_control: typing.Optional[LlamaParseProcessingControl] = OMIT, source_url: str, webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]] = OMIT, ) -> ParsingJob: """ Parse a document from a URL. Parameters: - project_id: typing.Optional[str]. - organization_id: typing.Optional[str]. - client_name: typing.Optional[str]. - crop_box: typing.Optional[LlamaParseCropBox]. Document crop box boundaries - disable_cache: typing.Optional[bool]. - http_proxy: typing.Optional[str]. - input_options: typing.Optional[LlamaParseInputOptions]. Input format-specific parsing options - output_options: typing.Optional[LlamaParseOutputOptions]. Output format and styling options - page_ranges: typing.Optional[LlamaParsePageRanges]. Page range selection options - parse_options: LlamaParseTierOptions. Parsing tier and related configuration options - processing_control: typing.Optional[LlamaParseProcessingControl]. Job processing control and failure handling - source_url: str. Source URL to fetch document from - webhook_configurations: typing.Optional[typing.List[LlamaParseWebhookConfiguration]]. List of webhook configurations for notifications --- from llama_cloud import (LlamaParseAgenticOptions, LlamaParseCropBox, LlamaParseEmbeddedImagesOptions, LlamaParseExportPdfOptions, LlamaParseFastOptions, LlamaParseHtmlOptions, LlamaParseIgnoreOptions, LlamaParseInputOptions, LlamaParseJobFailureConditions, LlamaParseMarkdownOptions, LlamaParseOcrParameters, LlamaParseOutputOptions, LlamaParsePageRanges, LlamaParsePages, LlamaParsePdfOptions, LlamaParsePresentationOptions, LlamaParseProcessingControl, LlamaParseScreenshotsOptions, LlamaParseSpatialTextOptions, LlamaParseSpreadsheetOptions, LlamaParseTables, LlamaParseTablesAsSpreadsheetOptions, LlamaParseTierOptions, LlamaParseTierOptionsVersion, LlamaParseTimeouts, TierName) from llama_cloud.client import AsyncLlamaCloud client = AsyncLlamaCloud(token="YOUR_TOKEN", ) await client.alpha.upload_file_by_url(crop_box=LlamaParseCropBox(), input_options=LlamaParseInputOptions(html=LlamaParseHtmlOptions(), pdf=LlamaParsePdfOptions(), presentation=LlamaParsePresentationOptions(), spreadsheet=LlamaParseSpreadsheetOptions(), ), output_options=LlamaParseOutputOptions(embedded_images=LlamaParseEmbeddedImagesOptions(), export_pdf=LlamaParseExportPdfOptions(), markdown=LlamaParseMarkdownOptions(pages=LlamaParsePages(), tables=LlamaParseTables(), ), screenshots=LlamaParseScreenshotsOptions(), spatial_text=LlamaParseSpatialTextOptions(pages=LlamaParsePages(), ), tables_as_spreadsheet=LlamaParseTablesAsSpreadsheetOptions(), ), page_ranges=LlamaParsePageRanges(), parse_options=LlamaParseTierOptions(agentic_options=LlamaParseAgenticOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), fast_options=LlamaParseFastOptions(ignore=LlamaParseIgnoreOptions(), ocr_parameters=LlamaParseOcrParameters(), ), tier=TierName.FAST, version=LlamaParseTierOptionsVersion.2025_11_18, ), processing_control=LlamaParseProcessingControl(job_failure_conditions=LlamaParseJobFailureConditions(), timeouts=LlamaParseTimeouts(), ), source_url="string", ) """ _request: typing.Dict[str, typing.Any] = {"parse_options": parse_options, "source_url": source_url} if client_name is not OMIT: _request["client_name"] = client_name if crop_box is not OMIT: _request["crop_box"] = crop_box if disable_cache is not OMIT: _request["disable_cache"] = disable_cache if http_proxy is not OMIT: _request["http_proxy"] = http_proxy if input_options is not OMIT: _request["input_options"] = input_options if output_options is not OMIT: _request["output_options"] = output_options if page_ranges is not OMIT: _request["page_ranges"] = page_ranges if processing_control is not OMIT: _request["processing_control"] = processing_control if webhook_configurations is not OMIT: _request["webhook_configurations"] = webhook_configurations _response = await self._client_wrapper.httpx_client.request( "POST", urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v2alpha1/parse/url"), params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_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)