i(SSKrSSKrSSKrSSKrSSKrSSKJr SSKJr SSK J r SSK J r SSK JrJrJr SSKJrJrJrJrJrJrJr SSKJr SSKrSS KJr SS KJrJ r SS K!J"r"J#r#J$r$J%r% SS K&J'r' SS K(J)r) SSK*J+r+ SSK,J-r- SSK.J/r/ SSK0J1r1 SSK2J3r3J4r4J5r5J6r6J7r7J8r8J9r9J:r:J;r;J\ 4r?Sr@SrASrBSrCS\=S\\=S\\=S\=4SjrD"SS\E5rF"SS\=\ 5rG"S S!\)5rHg)"N)asynccontextmanager)deepcopy)Enum)BufferedIOBase)PathPurePath PurePosixPath)AnyAsyncGeneratorDictListOptionalTupleUnion)urlparse)AbstractFileSystem) asyncio_runrun_jobs)Field PrivateAttrfield_validatormodel_validator)DEFAULT_BASE_URL)BasePydanticReader)get_default_fs)Document)check_extra_params) JobResult) SUPPORTED_FILE_TYPES ResultType ParsingModeFailedPageModeexpand_target_pagesnest_asyncio_errnest_asyncio_msgmake_api_requestpartition_pages extract_tables_from_json_resultsz --- z./api/parsing/job/{job_id}/result/{result_type}z/api/parsing/job/{job_id}z/api/parsing/uploadbase_urlorganization_id project_idreturnc 0nU(aXS'U(aX#S'U(a?US-SRUR5VVs/sH upEUSU3PM snn5-$U$s snnf)Nr*r+?&=)joinitems)r)r*r+ query_paramskvs Y/home/james-whalen/.local/lib/python3.13/site-packages/llama_cloud_services/parse/base.py build_urlr77slL*9&'%/\"#~ASASAU)VAUQCq*AU)V WWW O*WsA! c z^\rSrSrSrS S\S\S\\S\\4U4Sjjjr\S\ \\ 4S S4S j5r S r U=r $) JobFailedExceptionFzParse job failed exception.job_idstatus error_code error_messagec >SUSUSU=(d SSU=(d S3n[TU]U5 XlX lX0lX@lg)NzJob ID: z failed with status: z, Error code: zNo error code foundz, Error message: zNo error message found)super__init__r;r<r=r>)selfr;r<r=r> exception_str __class__s r6rAJobFailedException.__init__Isevh3F8<%>)>?@+G/GH J  '  $* result_jsonr,chUSnUSnURS5nURS5nU"X#XES9$)Nidr<r=r>)r=r>)get)clsrGr;r<r=r>s r6 from_resultJobFailedException.from_result[s?T"X& __\2 #8 6jVVrF)r=r>r;r<NN)__name__ __module__ __qualname____firstlineno____doc__strrrA classmethodr r rL__static_attributes__ __classcell__)rDs@r6r9r9Fsu% %)'+ +++SM +  } ++$Wd38nW9MWWrFr9c$\rSrSrSrSrSrSrSrg)BackoffPatterndzBackoff pattern for polling.constantlinear exponentialN) rOrPrQrRrSCONSTANTLINEAR EXPONENTIALrVr^rFr6rYrYds&H FKrFrYc8\rSrSr%Sr\"SSSS9r\\S'\"\ SS 9r \\S '\"S S S 9r \ \\S '\"S SS 9r \ \\S'\"SSS 9r\\S'\"\R"SS 9r\\S'\"SSS 9r\\S'\"S SS 9r\ \R,\S'\"SSS 9r\\S'\"SSS 9r\\S'\"SS S!S"S#9r\\S$'\"\R8S%S 9r\\S&'\"SS'S 9r\\S('\"SS)S 9r\\S*'\"SS+S 9r \\S,'\"S-S.S 9r!\ \\S/'\"S-S0S 9r"\ \\S1'\"S-S2S 9r#\ \\S3'\"S S4S 9r$\ \\S5'\"S-S6S 9r%\ \\S7'\"S-S8S 9r&\ \\S9'\"S S:S 9r'\ \\S;'\"S S\ \\Sg'\"S-ShS 9r?\ \\Si'\"S SjS 9r@\ \\Sk'\"S-SlS 9rA\ \\Sm'\"S SnS 9rB\ \\So'\"S-SpS 9rC\ \\Sq'\"S SrS 9rD\ \.\Ss'\"S StS 9rE\ \.\Su'\"SvSwS 9rF\ \\Sx'\"S SyS 9rG\ \\Sz'\"S S{S 9rH\ \\S|'\"S-S}S 9rI\ \\S~'\"S-SS 9rJ\ \\S'\"S SS 9rK\ \\S'\"S SS 9rL\ \\S'\"S-SS 9rM\ \\S'\"S-SS 9rN\ \\S'\"S SS 9rO\ \.\S'\"S SS 9rP\ \\S'\"S SS 9rQ\ \\S'\"S SS 9rR\ \\S'\"S SS 9rS\ \T\U\4\S'\"S-SS 9rV\ \\S'\"S SS 9rW\ \\S'\"S-SS 9rX\ \\S'\"S-SS 9rY\ \\S'\"S SS 9rZ\ \[\S'\"S SS 9r\\ \\S'\"S SS 9r]\ \\S'\"S-SS 9r^\ \\S'\"S-SS 9r_\ \\S'\"S-SS 9r`\ \\S'\"S-SS 9ra\ \\S'\"S-SS 9rb\ \\S'\"S-SS 9rc\ \\S'\"S-SS 9rd\ \\S'\"S SS 9re\ \\S'\"S SS 9rf\ \\S'\"S SS 9rg\ \\S'\"S SS 9rh\ \\S'\"S-SS 9ri\ \\S'\"S SS 9rj\ \\S'\"S SS 9rk\ \\S'\"S SS 9rl\ \\S'\"S SS 9rm\ \\S'\"S SS 9rn\ \\S'\"S SS 9ro\ \\S'\"S SS 9rp\ \\S'\"S-SS 9rq\ \\S'\"S-SS 9rr\ \\S'\"S SS 9rs\ \\S'\"S SS 9rt\ \\S'\"S SS 9ru\ \\S'\"S SS 9rv\ \\S'\"S SS 9rw\ \\S'\"S SS 9rx\ \\S'\"S SS 9ry\ \\S'\"S SS 9rz\ \\S'\"S-SS 9r{\ \\S'\"S SS 9r|\ \\S'\"S-SS 9r}\ \\S'\"SSS 9r~\ \\S'\"S-SS 9r\ \\S'\"SS9\S\\\4S\\\44Sj55r\"SSSS9\S\S\4Sj55r\"S SSS9\S\S\4Sj55r\"S S-S9r\T\R,S 4\S'\S\R,4Sj5r\S\\R,S 44Sj5rS\S\4SjrS\S\4SjrGS S\S\ \S\ \S\ \S\4 SjjrS\.S\.4SjrGS!S\S&\S,\S\\\44SjjrGS"S\S\ \S\ \S&\ \S$\ \S\\\\\\444 SjjrGS S\S\ \S\ \S&\ \S\S\\\\\444 GSjjrGS"S\S\ \S\ \S&\ \S$\ \S\\\\\\444 GSjjrGS#S\S\ \S\ \S,\S$\ \S\\4 GSjjrGS$S\T\\\4S\ \S\ \S\\4GSjjrGS$S\T\\\4S\ \S\ \S\\4GSjjrGS S\GS\S\ \S\ \S$\ \S\\4 GSjjrGS$S\T\\\4S\ \S\ \S\T\GSGS44GSjjrGS$S\T\\\4S\ \S\ \S\T\GSGS44GS jjrGS$S\S\ \S$\ \S\\4GS jjrGS%S\T\\\4S\ \S\\4GS jjrGS%S\T\\\4S\ \S\\4GS jjrGS%S\T\\\4S\ \S\\4GS jjrGS\\GS\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\GS\S\\4GSjrGS\\S\\4GSjrS\T\\\4S\T\\\44GSjrS\T\\\4S\T\\\44GSjrGSrg (& LlamaParselzA smart-parser for files.z#The API key for the LlamaParse API.T)default descriptionvalidate_defaultapi_keyz&The base URL of the Llama Parsing API.)rfrgr)Nz+The organization ID for the LlamaParse API.r*z&The project ID for the LlamaParse API.r+z8The interval in seconds to check if the parsing is done.check_intervalzcControls the backoff pattern when retrying failed requests: 'constant', 'linear', or 'exponential'.backoff_patternzNMaximum interval in seconds between polling attempts when checking job status.max_check_intervalz2A custom HTTPX client to use for sending requests. custom_clientz?Whether or not to ignore and skip errors raised during parsing. ignore_errorsizAThe maximum timeout in seconds to wait for the parsing to finish. max_timeoutrz>The number of workers to use sending API requests for parsing.)rfgtltrg num_workerszThe result type for the parser. result_typez*Show progress when parsing multiple files. show_progressz1Whether to split by page using the page separator split_by_pagez-Whether to print the progress of the parsing.verboseFzNIf set to true, LlamaParse will try to detect long table and adapt the output.adaptive_long_tablez:Annotate links found in the document to extract their URL.annotate_linkszIf set to true, the parser will automatically select the best mode to extract text from documents based on the rules provide. Will use the 'accurate' default mode by default and will upgrade page that match the rule to Premium mode. auto_modezA JSON string containing the configuration for the auto mode. If set, the parser will use the provided configuration for the auto mode.auto_mode_configuration_jsonzdIf auto_mode is set to true, the parser will upgrade the page that contain an image to Premium mode."auto_mode_trigger_on_image_in_pagezcIf auto_mode is set to true, the parser will upgrade the page that contain a table to Premium mode."auto_mode_trigger_on_table_in_pagezdIf auto_mode is set to true, the parser will upgrade the page that contain the text to Premium mode.!auto_mode_trigger_on_text_in_pagezdIf auto_mode is set to true, the parser will upgrade the page that match the regexp to Premium mode.#auto_mode_trigger_on_regexp_in_pagezAzure Openai API Versionazure_openai_api_versionzAzure Openai Deployment Nameazure_openai_deployment_namezAzure Openai Endpointazure_openai_endpointzAzure Openai Keyazure_openai_keyzThe bottom margin of the bounding box to use to extract text from documents expressed as a float between 0 and 1 representing the percentage of the page height. bbox_bottomzThe left margin of the bounding box to use to extract text from documents expressed as a float between 0 and 1 representing the percentage of the page width. bbox_leftzThe right margin of the bounding box to use to extract text from documents expressed as a float between 0 and 1 representing the percentage of the page width. bbox_rightzThe top margin of the bounding box to use to extract text from documents expressed as a float between 0 and 1 representing the percentage of the page height.bbox_topzaIf set to true, the parser will output compact markdown table (without trailing spaces in cells).compact_markdown_tablezhParse documents continuously, leading to better results on documents where tables span across two pages.continuous_modezbDisable the OCR on the document. LlamaParse will only extract the copyable text from the document. disable_ocrz]If set to true, the parser will not extract images from the document. Make the parser faster.disable_image_extractionzIf set to true, the document will not be cached. This mean that you will be re-charged it you reprocess them as they will not be cached. do_not_cachezIf set to true, the parser will keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most case.do_not_unroll_columnszEIf set to true, the parser will extract/tag charts from the document.extract_chartszgIf set to true, the parser will extract the layout information of the document. Cost 1 credit per page.extract_layoutzNote: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction. fast_modez2Whether to guess the sheet names of the xlsx file.guess_xlsx_sheet_nameszIf set to true, the parser will use high resolution OCR to extract text from images. This will increase the accuracy of the parsing job, but reduce the speed. high_res_ocrzmIf set to true, when parsing HTML the parser will consider all elements display not element as display block.html_make_all_elements_visiblezgIf set to true, when parsing HTML the parser will remove fixed elements. Useful to hide cookie banners.html_remove_fixed_elementszsIf set to true, when parsing HTML the parser will remove navigation elements. Useful to hide menus, header, footer.html_remove_navigation_elementszX(optional) If set with input_url will use the specified http proxy to download the file. http_proxyznIf set to true, the parser will ignore document elements for layout detection and only rely on a vision model.-ignore_document_elements_for_layout_detectionz@The region of the input S3 bucket if input_s3_path is specified.input_s3_regionzIf set to true, the cache will be ignored and the document re-processes. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice.invalidate_cachezjThe extra time in seconds to wait for the parsing to finish per page. Get added to job_timeout_in_seconds.*job_timeout_extra_time_per_page_in_secondszThe maximum timeout in seconds to wait for the parsing to finish. Override default timeout of 30 minutes. Minimum is 120 seconds.job_timeout_in_secondsenz"The language of the text to parse.languagezeThe separator to use to split the header of the markdown table into multiple lines. Default is:
)markdown_table_multiline_header_separatorzThe maximum number of pages to extract text from documents. If set to 0 or not set, all pages will be that should be extracted will be extracted (can work in combination with targetPages). max_pageszIf set to true, the parser will merge tables across pages in the markdown output. This is useful for documents with tables that span across multiple pages.%merge_tables_across_pages_in_markdownz\If set to true, the parser will also output a PDF of the document. (except for spreadsheets)output_pdf_of_documentzAn S3 path prefix to store the output of the parsing job. If set, the parser will upload the output to S3. The bucket need to be accessible from the LlamaIndex organization.output_s3_path_prefixzHThe AWS region of the output S3 bucket defined in output_s3_path_prefix.output_s3_regionzFIf set to true, the parser will output tables as HTML in the markdown.output_tables_as_HTMLzIf set to true, the parser will use a dedicated approach to extract tables with outlined cells. This is useful for documents with spreadsheet-like tables where cells are outlined with borders. This could lead to false positives, so use with caution.outlined_table_extractionzThe error tolerance for the number of pages with error in a doc (percentage express as 0-1). If we fail to parse a greater percentage of pages than the tolerance value we fail the job.page_error_tolerancezA templated prefix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number. page_prefixzA templated page separator to use to split the text. If it contain `{page_number}`,it will be replaced by the next page number. If not set will the default separator '\n---\n' will be used.page_separatorzA templated suffix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number. page_suffixzBThe parsing mode to use, see ParsingMode enum for possible values parse_modez(Use our best parser mode if set to True. premium_modezThe preset to use for the parser. If set, the parser will use the preset configuration. See LlamaParse documentation for available presets. Preset override most other parameters.presetz1Preserve grid alignment across page in text mode.&preserve_layout_alignment_across_pageszIf set, the parser will try to preserve very small text lines. This can be useful for documents containing vector graphics with very small text lines that may not be recognized by OCR or a vision model (such as in CAD drawings).preserve_very_small_textzThe mode to use to replace the failed page, see FailedPageMode enum for possible value. If set, the parser will replace the failed page with the specified mode. If not set, the default mode (raw_text) will be used.replace_failed_page_modezYA prefix to add before error message in failed pages. If not set, no prefix will be used.-replace_failed_page_with_error_message_prefixzXA suffix to add after error message in failed pages. If not set, no suffix will be used.-replace_failed_page_with_error_message_suffixzlIf set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).skip_diagonal_textzvIf set to true, the parser will extract sub-tables from the spreadsheet when possible (more than one table per sheet).spreadsheet_extract_sub_tableszfIf set to true, the parser will fail if it can't extract text from a document because of a buggy font.strict_mode_buggy_fontzTIf set to true, the parser will fail if it can't extract an image from the document.strict_mode_image_extractionzPIf set to true, the parser will fail if it can't OCR an image from the document.strict_mode_image_ocrzdIf set to true, the parser will fail if it can't reconstruct a table or a heading from the document.strict_mode_reconstructionzYIf set to true, the parser will output structured data based on the provided JSON Schema.structured_outputzA JSON Schema to use to structure the output of the parsing job. If set, the parser will output structured data based on the provided JSON Schema.structured_output_json_schemazThe named JSON Schema to use to structure the output of the parsing job. For convenience / testing, LlamaParse provides a few named JSON Schema that can be used directly. Use 'imFeelingLucky' to let llamaParse dream the schema."structured_output_json_schema_namezPThe system prompt. Replace llamaParse default system prompt, may impact accuracy system_promptz*String to append to default system prompt.system_prompt_appendz8Whether to take screenshot of each page of the document.take_screenshotzThe target pages to extract text from documents. Describe as a comma separated list of page numbers. The first page of the document is page 0 target_pagesz7The user prompt. Replace llamaParse default user prompt user_promptz#The API key for the multimodal API.vendor_multimodal_api_keyz-The model name for the vendor multimodal API.vendor_multimodal_model_namez;The document model name to be used with `parse_with_agent`.modelzbUR>U S'UR@bUR@U S'URBbURBU S'URDbURDU S'URFbURFU S'URHbURHU S'URJ(aURJU S'URL(a[OS5 URLU S'URP(a[OS5 URPU S 'URR(aURRU S!'URT(aURTU S"'URV(aURVU S#'URX(aURXU S$'URZ(aURZU S%'UR\(aUR\U S&'UR^(aUR^U S''UR`(aUR`U S('URb(a[OS)5 URbU S*'URd(aURdU S+'URf(aURfU S,'URh(aURhU S-'URj(aURjU S.'URl(aURlU S/'URnbURnU S0'URp(aURpU S1'UbSn[U5U S2'UbSn[U5U S3'URrbURrU S4'URt(aURtU S5'URv(a[OS)5 URvU S6'URxbURxU S7'URzbURzU S8'UR|(aUR|U S9'UR~bUR~U S:'UR(aURU S;'URbURU S<'URbURU S='UR(aURU S>'UR(aURU S?'URbURU S@'URbURU SA'UR(aURU SB'UR(aURU SC'UR(aURU SD'URbURU SE'URbURU SF'URbURU SG'URbURU SH'URbURU SI'URbURU SJ'UR(a[OSK5 URU SL'UR(aURU SM'UR(aURU SN'UR(aURU SO'UR(aURU SP'URbURU SQ'URbURRU SR'URbURU SS'URbURU ST'UR(aURU SU'UR(aURU SV'UR(aURU SW'UR(aURU SX'UR(aURU SY'UR(aURU SZ'UR(aURU S['URbURU S\'URbURU S]'URbURU S^'URbURU S_'UR(aURU S`'UbXMSa'OURbURU Sa'URbURU Sb'UR(aURU Sc'URbURU Sd'URbURU Se'URbURU Sf'URbURU Sg'URbURU Sh'URbURU Si'UR(aURU Sj'URbURU Sk'[[URUR5n[URSlXRX]Sm9IShvN nUR5 UR5SnUbUR5 $$N;![Ra*nSoURR3n[#U5UeSnAff=f!UbUR5 ff=f7f)pN file_name;file_name must be provided in extra_info when passing bytesrfilerjz8Currently, only the following file types are supported: z Current file type: rbzJfile_input must be either a file path string, file bytes, or buffer objectTfrom_python_packager{r|r}r~rrrrrrrrrrrrrzWARNING: complemental_formatting_instruction is deprecated and may be remove in a future release. Use system_prompt, system_prompt_append or user_prompt instead.rzWARNING: content_guideline_instruction is deprecated and may be remove in a future release. Use system_prompt, system_prompt_append or user_prompt instead.rrrrrrrrrzWARNING: formatting_instruction is deprecated and may be remove in a future release. Use system_prompt, system_prompt_append or user_prompt instead.rrrrrrrr input_url input_s3_pathrrrrrrrrrrrrrrrrrrrrrrrzkWARNING: parsing_instruction is deprecated. Use system_prompt, system_prompt_append or user_prompt instead.rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrPOST)rfilesrrIzFailed to parse the file: )rr rbytesrr mimetypes guess_typerTrr rrpathsplitextlowerrrropenbasenamer{r|r}r~rrrrrrrrrrrrrrprintrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrvaluerrrrrrrrrrrrrrrrrrrrrrrrrr7JOB_UPLOAD_ROUTEr*r+r&rrqraise_for_statusjsoncloserHTTPStatusErrorresponsetext)rBrrrrr file_handlerrr mime_typerfile_extrrresperrmsgs r6 _create_jobLlamaParse._create_jobs  "&"4"4Z"@"@Jd &*ooj&A&A t j5."9 : :J!> Q#;/I!,,Y7:IiY?@E  "E  &E  S$ x$H I IJIww'' 215;;=H33NOcNde**25",,Y7:I'~'B''*d3Kbgg..y9;RSE\  "&* "#  # #*.*B*BD& '   %)%8%8D! " >> $D   , , 8373T3TD/ 0  2 277 4   2 277 4   1 1 =66 3   3 3 ?88 5   ( ( 4/3/L/LD+ ,  , , 8373T3TD/ 0  % % 1,0,F,FD( )  ,'+'<'> % $D  ?? &!%D  == $#}}D   & &-1-H-HD) *  3 3 t  88 5   - - n 594V4VD0 1   &*&:&:D" #   "&"2"2D   ( (/3/L/LD+ ,   #'#4#4D  % %,0,F,FD( )   %)%8%8D! "   %)%8%8D! " >> $D   & & g .2-H-HD) *  & &-1-H-HD) *  . .595X5XD1 2   #'#4#4D  * *151P1PD- .  / /44 1  ?? &!%D   = =BB ?   E #ID   $E$' $6D !    +&*&:&:D" #  '+'<'> % $D   & &-1-H-HD) *  % % 1,0,F,FD( )  ,'+'<'(>D$ %  - - 9484V4VD0 1  2 2 >77 4     )$($6$6D !  $ $ 0+/+D+DD' (   &*&:&:D" # ! -#9    *#'#4#4D    '"&"2"2D   + +262R2RD. /  ) ) 5040N0ND, -  , , 8373T3TD/ 0 :: ! JJDM    '"&"2"2D   9 9 E>> ;     (#'#4#4D ??!%D     )$($6$6D ! $,d.B.BDOOTC)$,,M]M]ejvvD  ! ! #99;t$ &!!#'w$$ *.s||/@/@.ABCC.c ) *&!!#'sIru6Att&tu6tu0%uuuu33u6current_intervalcFUR[R:XaU$UR[R:Xa"[ US-[ UR 55$UR[R:Xa"[ US-[ UR 55$U$)zCalculate the next backoff interval based on the backoff pattern. Args: current_interval: The current interval in seconds Returns: The next interval in seconds rj)rlrYr_r`minfloatrnra)rBr5s r6_calculate_backoffLlamaParse._calculate_backoffs   >#:#: :# #  ! !^%:%: :'!+U43J3J-KL L  ! !^%?%? ?'!+U43J3J-KL LrFr;c # [R"5nSnSn[UR5nURn[R "U5IShvN US- nUR [RUS95IShvN n U R5 U R5n U Sn U S:Xa:UR [RXS95IShvN n U R5$U S:Xab[R"5n X- UR:a[S U35eU(aUS -S:Xa [S S SS 9 URU5nO[ R#U 5eGM3GNNN![$R&[$R([$R*[$R,[$R.[$R0[$R2[$R44atnUS- n[R"5n X- UR:a[S U35UeU(aUS -S:Xa[SUS3SS9 URU5nSnANSnAff=f7f)NrTrj)r;r<SUCCESS)r;rwPENDINGz Timeout while parsing the file: .re)endflushz HTTP error: z...)rB)timer9rkrasynciosleeprJJOB_STATUS_ROUTEformatr'r(JOB_RESULT_URLrqrr$r:r9rLr ConnectError ReadError WriteErrorConnectTimeout ReadTimeout WriteTimeoutr*RemoteProtocolError)rBr;rwrzstarttries error_countr5rrrGr< parsed_resultrAr1s r6_get_job_resultLlamaParse._get_job_results3  "'(;(;"< + Mmm$4555 %zz*:*A*A*A*PQQ'')$kkm $X.Y&*0**&--V-U+%M)--//y())+C{T%5%55'*J6((STT52:?cr6'+'>'>?O'P$,88EE-5Q %""  $$!!""%%))  Mq iik;!1!11#:6(CurzQ&se3/"$(#:#:;K#L + MsI*6A*I% I-%I**I-c# URcURUUUUS9IShvN /nU$URUUUUUS9IShvN nU$N$N7f)N)rrrwrrwrv)r'_parse_one_unpartitioned_parse_one_partitioned)rBrrrrwrv job_resultss r6 _parse_oneLlamaParse._parse_oneHs    '33) + 4K !% ; ;'' !<!Ks!#AA AA A A create_kwargsc# UR"U4X#S.UD6IShvN nUR(a[SU-5 URXd=(d URR URS9IShvN nXg4$NeN 7f)z-Create one parse job and wait for the result.rrNz(Started parsing the file under job_id %srz)r3rzr$rTrwr%)rBrrrrwr]r;rs r6rX#LlamaParse._parse_one_unpartitionedcs''  ", 7D   << *000DNNB~~-++65 -1,I,I) * 5 5.3WAelQ6F5G+H -J-'#*CT-=-=-C-C *//"7"77!,J'+';';T\\(<("J NNF/ 0;w'(4/ MEGnn$(>Hw ,'"& q||/FF"N  sA7I9HI1H2A4I'8H$H  AH$%I&H$H"H$9III H$"H$$ I.I II I  IIc^# TRXX5S9IShvN VVs/sHupgUPM nnnTR=(d [n [U R U4SjU55U=(d 0S9/n TR (aTR U 5$U $Ns snnf![aHn [U[5(aUOSn [SU S3U 5 TR(a/sSn A $U eSn A ff=f7f)Load data from the input path.)rrvNc3T># UHoTRRv M g7fN)rwr%).0rrBs r6 )LlamaParse._aload_data..s#(EL6t//556Ws%(r,metadataError while parsing the file '':) r[r_DEFAULT_SEPARATORrr1ry _get_sub_docsrrrTr$rp) rBrrrrzrv_rrro separatordocsrs file_reprs ` r6 _aload_dataLlamaParse._aload_datas  ,0??b,;,&&&MA& ++A/AI"(EL((-2 D!!))$// #&* %/ 3%?%? EUI 29+R@! D!!   sgC8B#BB#BA*B#C8B#C8B#B## C5-;C0(C5)C8.C00C55C8c # [U[[[[[ 45(a"UR XX0RS9IShvN $[U[5(aUVs/sH8nUR UUUUR=(a UR(+SS9PM: nn[UURSURS9IShvN nUVVs/sH owHoPM M snn$[S5eNs snfN3s snnf![a)n [[U 5;a[[5eU eSn A ff=f7f)zLoad data from the input path. File(s) which were partitioned before parsing will be loaded as a single re-assembled Document. )rrrzNrj)rrrzrv Parsing filesrd:The input file_path must be a string or a list of strings.)rrTr rrrrrzlistrxrrv RuntimeErrorr$r%r) rBrrrfrmrosublistitemrss r6 aload_dataLlamaParse.aload_datasI i#}dE>!R S S))R*  4 ( (# #A  ) LLC1C1C-C ! !#    ( ,,("&"4"4 !-4HGGHHL = I #s1v-&'788G  slAD? C: D?(?C<'D?*#D D D D+D . D?<D?D D D<$D77D<<D?c[URXUS95$![a)n[[ U5;a[[ 5eUeSnAff=f)rvrN)rrrr$rTr%rBrrrrss r6 load_dataLlamaParse.load_datasL tyLM M 3q6)"#344   A$A  Arc2# URUUU[RRUS9IShvN nUVVs/sHIupx[ UUUUR UR URUR=(d [S9PMK snn$N]s snnf7f)NrWr;rrrrir)rr) r[r rjr%rrir)rrr) rBrrrrrvrZr;rrs r6 _aparse_oneLlamaParse._aparse_one&s!OO  "--# ,  "'2  '2" #% ||#22H6H '2     s!/BB BAB BBrc# [U[[[[[ 45(ar[U[[ 45(aU(aSU;a [ S5eUSnO [U5nURXX#S9IShvN n[U5S:XaUS$U$[U[5(a/nUHfn[U[[ 45(a.U(aSU;a [ S5eURUS5 MLUR[U55 Mh /n[[U5V Vs/sHupURUXiUUSS9PM snn URSURS 9IShvN HnURU5 M U$[ S 5eGNs snn fN2![ a)n ["[U 5;a[![$5eU eSn A ff=f7f) a] Parse the file and return a JobResult object instead of Document objects. This method is similar to aload_data but returns JobResult objects that provide direct access to the various output formats (text, markdown, json, etc.) Args: file_path: Path to the file to parse. Can be a string, path, bytes, file-like object, or a list of these. extra_info: Additional metadata to include in the result. fs: Optional filesystem to use for reading files. Returns: JobResult object or list of JobResult objects if either multiple files were provided or file(s) were partitioned before parsing. rrr_Nrjr)rrrvrcrdr)rrTr rrrrrrlrrkr enumeratervrxextendrr$r%) rBrrrrr file_namesrrZirss r6aparseLlamaParse.aparseBs* i#}dE>!R S S)e^%<==![ %B$U'{3  N ++,F!$F q 06!9 %%c!f-K $,%.i$8 %9DA((&M'1!() )%9 !,,."&"4"4%F &&v. #"L W( $  #s1v-&'788G  sUBG$F#BG$%F.8!F&  F.9F,:F. G$&F.. G!8$GG!!G$c[URXUS95$![a)n[[ U5;a[[ 5eUeSnAff=f)a) Parse the file and return a JobResult object instead of Document objects. This method is similar to load_data but returns JobResult objects that provide direct access to the various output formats (text, markdown, json, etc.) Args: file_path: Path to the file to parse. Can be a string, path, bytes, file-like object, or a list of these. extra_info: Additional metadata to include in the result. fs: Optional filesystem to use for reading files. Returns: JobResult object or list of JobResult objects if multiple files were provided rN)rrrr$rTr%rs r6parseLlamaParse.parsesL( t{{9R{HI I 3q6)"#344  rc# URUU[RRUS9IShvN n/nUHCupgXgS'[ U[ [ 45(d[U5US'URU5 ME U$NQ![aHn[ U[5(aUOSn [SU S3U5 UR(a/sSnA$UeSnAff=f7f)rv)rrwrvNr;rr~rr) r[r rjr%rrrrTrkrr$rp) rBrrrvrZror;rrrsrs r6 _aget_jsonLlamaParse._aget_jsons  $%&OO11' !0!KG&1"'-8$!)e^-DEE.1)nJ{+z* '2 N %/ 3%?%? EUI 29+R@! D!!   sKC-BBABCB C;C C CCCCc# [U[[[[[ 45(aUR XS9IShvN $[U[5(adUVs/sHo0R X2S9PM nn[UURSURS9IShvN nUVVs/sH ofHowPM M snn$[S5eNs snfN3s snnf![a)n[[U5;a[[5eUeSnAff=f7f)rv)rNrrdz\The input file_path must be a string, Path, bytes, BufferedIOBase, or a list of these types.)rrTr rrrrrrrvrxrr$r%r) rBrrrrmrorrrss r6 aget_jsonLlamaParse.aget_jsons i#}dE>!R S SJJ J  4 ( (GPQy!OOAO=yDQ  ( ,,("&"4"4 !-4HGGHHn 'KQI #s1v-&'788G  sj=D CD C 5D 8#CC C%C9C< D  D CC D !$DD  D c[URX55$![a)n[[ U5;a[[ 5eUeSnAff=f)zParse the input path.N)rrrr$rTr%)rBrrrss r6get_json_resultLlamaParse.get_json_resultsH  t~~iDE E 3q6)"#344   A$A  Ac$URX5$)rv)r)rBrrs r6get_jsonLlamaParse.get_jsons ##I::rFrq download_path asset_keyc # [RRU5(d[R"U5 URn/nUGH]nUSnUSGHJnUR (a'[ SUR5SUSSX35 XGHn U Sn [RRX'SU 35n U RS 5(dU RS 5(dU S - n XS 'XyS'URS S 5U S'USU S'[U S5n URSUSU 3n [USXRS9IS hvN nUR5 U R!UR"5 S S S 5 UR%U 5 GM GMM GM` U$NY!,(df  N2=f![&a/n[ SUS3U5 UR((a/sS nA$UeS nAff=f7f)z:Download assets (images or charts) from the parsed result.r;riz> z for page pagez: namergz.pngz.jpgrrNoriginal_file_path page_numberwb/api/parsing/job/z/result/image/GETrzError while downloading z from the parsed result:)rrexistsmakedirsrrzr$ capitalizer1endswithrJr"r)r&rqr'writecontentrkrrp)rBrqrrrassetsrr;rasset asset_name asset_pathr asset_urlr0rss r6 aget_assetsLlamaParse.aget_assetss ww~~m,, KK &) F%)"7OD|| !5!5!7 8 4<.PRSWSbRcd"&%*6] &(WW\\)XQzl+C& *226::#-#6#6v#>#> *f 4 (2f *0h6G G>"G91G>2H7G99G>>Hc# URXS5IShvN $N![a+n[SU5 UR(a/sSnA$UeSnAff=f7f)'Download images from the parsed result.imagesNzError while downloading images:rrr$rprBrqrrss r6 aget_imagesLlamaParse.aget_images1P ))+hOO OO  3Q 7!!   BA  A AAA AAAAc# URXS5IShvN $N![a+n[SU5 UR(a/sSnA$UeSnAff=f7f)'Download charts from the parsed result.chartsNzError while downloading charts:rrs r6 aget_chartsLlamaParse.aget_charts>rrc[URX55$![a)n[[ U5;a[[ 5eUeSnAff=f)rN)rrrr$rTr%rs r6 get_imagesLlamaParse.get_imagesKJ t// KL L 3q6)"#344  rc[URX55$![a)n[[ U5;a[[ 5eUeSnAff=f)rN)rrrr$rTr%rs r6 get_chartsLlamaParse.get_chartsUrr json_resultsc[RRU5(d[R"U5 [ X5$rx)rrrrr()rBrrs r6 get_tablesLlamaParse.get_tables_s,ww~~m,, KK &/ LLrFc`# [R"URX5IShvN $N7frx)rD to_threadr)rBrqrs r6 aget_tablesLlamaParse.aget_tablesds$&&t SSSSs %.,.c # [RRU5(d[R"U5 URn/nUHnUSnUR (a [ S5 [RRX&S35n0nXxS'XhS'URSS5US'[US5n URS US 3n [US XRS 9IShvN n U R5 U RU R5 SSS5 UR!U5 M U$NN!,(df  N'=f!["a+n [ S U 5 UR$(a/sSn A $U eSn A ff=f7f)%Download xlsx from the parsed result.r;z> XLSXz.xlsxrrNrrrz/result/raw/xlsxrrzError while downloading xlsx:)rrrrrrzr$r1rJr"r)r&rqr'rrrkrrp) rBrqrr xlsx_listrr; xlsx_pathxlsxrxlsx_urlresrss r6 aget_xlsxLlamaParse.aget_xlsxisY ww~~m,, KK & I%)<<(OGGLL(%8HI (V !'X-3ZZ T-J)*)T*a==/):6(BRS!1x9I9I!C((*GGCKK(+  &-&.   +*  11 5!!   sgAF A5E ?+D;*D9+/D;E 8F9D;; E E FE<4F5F:E<<FFc[URX55$![a)n[[ U5;a[[ 5eUeSnAff=f)rN)rrrr$rTr%rs r6get_xlsxLlamaParse.get_xlsxsH t~~kIJ J 3q6)"#344  rrc/nUR=(d [nUHUnURRU5nUH1n[ U[ UR 5S9nURU5 M3 MW U$)z$Split docs into pages, by separator.r|)rrr,splitrrr}rk)rBrsub_docsrdoc doc_chunks doc_chunksub_docs r6rLlamaParse._get_sub_docssl''=+= C 2J' ""%cll3( (rFc4# [U[5(aURU[RR UR S9IShvN n[USUURURURUR=(d [S9$[U[5(a/nUVs/sH6nURU[RR UR S9PM8 nn[UURSUR S9IShvN n[#U5VVs/sHKupb[XSUURURURUR=(d [S9PMM snn$[%S5eGN:s snfN{s snnf7f)2 Return JobResult object for previously parsed job(s). If the job is still pending, the result will not be returned until it is completed. Args: job_id: Job ID or list of multiple Job IDs to be retrieved. Returns: JobResult object or list of JobResult objects if multiple job IDs were provided. r`Nrerrcrdz7The input job_id must be a string or a list of strings.)rrTrTr rjr%rzrrir)rrrrrrvrxrr)rBr;rroid_rmrs r6 aget_resultLlamaParse.aget_results fc " "// --t||0F! ||#22H6H  % %G"!C$$S*//*?*?$V! %((*"00 G "+7!3 "4IA!9 % LL!]]<<#'#6#6#L:L"4  VW WK sDA FFA#F2=F /%FFF'AF9F FFc[URU55$![a)n[[ U5;a[[ 5eUeSnAff=f)rN)rrrr$rTr%)rBr;rss r6 get_resultLlamaParse.get_resultsJ t//78 8 3q6)"#344  r)r)NNN)F)NNNN)NNFNrNrx)rOrPrQrRrSrrirT__annotations__rr)r*rr+rkintrYr`rlrnrorrrpboolrqrvr TXTrwrxryrzr{r|r}r~rrrrrrrrrr9rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr!rrrrrr"rrrrrrrrrrrrrrrrrrrrr'rrrrrrrrrrrrrrrrrUr r rrrrrrpropertyrrr r FileInputrr dictrr3r:rTr rr[rXrYrrrrrrrrrrrrrrrrrrrrrrrrrVr^rFr6rcrcls#9GS  <Hc&+A&OXc]!&<!J  NNC ',%%y'O^$d 27"V2M8E--. UM4WK T K $,MK "NM4 GM4"QGT +0d+$&+P&NHTN!&!Ix~38^3 (3-:?z:&:?y:&8=z8%x}:?z:'#/4"</hsm38"@3 (3-,1"9,8C=',"4'hsm$)w$K%"'t"Ix#(u#J!&t!Hhuo.3w.HTN',~'OXd^#(x#K$05s0htn$)_$L(4.-2{-8D>&+[&NHTN&+}&NHTN!&O!Ix~ .3H.HTN$)u$L(4.6;D6"HTN27}27<J7#Xd^!&n!J EJEE18D>&+V&OXc](-S(htnCHAC./4X/HUO$"FHhsm@E{@-x} %S Ix}=Br=)8D>.3r.HTN,1D,8C=',^'hsm-2\-8D>16P1x~-2O-(5/"'V"K#%*X%NHSM"'V"K#5:X5J{C/01$)>$L(4."IFHSM>CG>*HTN05{0htn:?m:h~6DIoD18C=DInD18C=*/C*6;M6"HTN .3|.HTN 49j4 (4. -2f-8D> 27z2 ).o)x~49i4!8C=9>z9& $)f$M8C=+0@+(3-',N'OXd^#(d#L(3-"'M"K#0590x}38C3 (3-!QE8C="'R"K#&+I&OXc]$)E$L(4.$)F$L(4.).P) ).P) ).P) ).P)  #(F#L(3-:?j:'#49|4!8C=-2q-HSM"'H"J$)Q$M8C=16y1x~*/ I*#38?3$ (# T#s(^ S#X $ YXDA   B ZhTB,#,#,C, 0;4e/THeE%%t+,T ** nU5F5F5L&MyT,I$&*+/04 z$z$TNz$ ' ( z$ !) z$ z$x  5 U $>C8M8M(+8M6:8M c3h8Mz&*+/%)%) TN ' (  c]  c]  eCc3h'( )<&*+/%) TN ' (  c]    sDcN" #,&*+/%)%) JJTNJ ' ( J c] J c] J eCc3h'( )J^&*+/%) %%TN% ' ( %  % c] % h%T&*+/ ,i)34,TN, ' ( , h ,b&*+/ i)34 TN  ' (  h &&*+/%)    TN  ' (  c]   i >&*+/ Ki)34KTNK ' ( K tK +- . K`&*+/ i)34TN ' (  tK +- . >&*%) TNc]  d B&*i)34TN d B&* i)34 TN  d "&*;i)34;TN; d ;2:2692FI2 d2h : 69  d  : 69  d d4jdd4jdMtDzM#M$s)M T:T69T cT (:(69( d(TDJstDz $x. T(^ 4XCcN+4X y$y/) *4XlCcN+ y$y/) *rFrc)IrDrrrCr contextlibrcopyrenumriorpathlibrrr typingr r r r rrr urllib.parserrfsspecrllama_index.core.async_utilsrr llama_index.core.bridge.pydanticrrrrllama_index.core.constantsrllama_index.core.readers.baser"llama_index.core.readers.file.baserllama_index.core.schemarllama_cloud_services.utilsr llama_cloud_services.parse.typesr llama_cloud_services.parse.utilsrr r!r"r#r$r%r&r'r(rTrr rrHrFr&r7rr9rYrcr^rFr6rs *11JJJ! %> 8<=,96    #un, - B.(  $,SM ?G}  WW< S$ J#JrF