Parsing

Parse File

ParsingCreateResponse parsing().create(, )

POST/api/v2/parse

Get Parse Job

ParsingGetResponse parsing().get(, )

GET/api/v2/parse/{job_id}

List Parse Jobs

ParsingListPage parsing().list(, )

GET/api/v2/parse

ModelsExpand Collapse

class BBox:

Bounding box with coordinates and optional metadata.

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

class CodeItem:

String md

Markdown representation preserving formatting

String value

Code content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<String> language

Programming language identifier

Optional<Type> type

Code block item type

enum FailPageMode:

Enum for representing the different available page error handling modes.

BLANK_PAGE("blank_page")

ERROR_MESSAGE("error_message")

RAW_TEXT("raw_text")

class FooterItem:

List<Item> items

List of items within the footer

One of the following:

class CodeItem:

String md

Markdown representation preserving formatting

String value

Code content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<String> language

Programming language identifier

Optional<Type> type

Code block item type

class HeadingItem:

long level

Heading level (1-6)

String md

Markdown representation preserving formatting

String value

Heading text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Heading item type

class ImageItem:

String caption

Image caption

String md

Markdown representation preserving formatting

String url

URL to the image

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Image item type

class LinkItem:

String md

Markdown representation preserving formatting

String text

Display text of the link

String url

URL of the link

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Link item type

class ListItem:

List<Item> items

List of nested text or list items

One of the following:

class TextItem:

String md

Markdown representation preserving formatting

String value

Text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Text item type

ListItem

String md

Markdown representation preserving formatting

boolean ordered

Whether the list is ordered or unordered

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

List item type

class TableItem:

String csv

CSV representation of the table

String html

HTML representation of the table

String md

Markdown representation preserving formatting

List<List<Row>> rows

Table data as array of arrays (string, number, or null)

One of the following:

String

double

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<List<Long>> mergedFromPages

List of page numbers with tables that were merged into this table (e.g., [1, 2, 3, 4])

Optional<Long> mergedIntoPage

Populated when merged into another table. Page number where the full merged table begins (used on empty tables).

Optional<List<ParseConcern>> parseConcerns

Quality concerns detected during table extraction, indicating the table may have issues

String details

Human-readable details about the concern

String type

Type of parse concern (e.g. header_value_type_mismatch, inconsistent_row_cell_count)

Optional<Type> type

Table item type

class TextItem:

String md

Markdown representation preserving formatting

String value

Text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Text item type

String md

Markdown representation preserving formatting

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Page footer container

class Form:

One form detected on a page, in two representations of the same content.

List<Json> json

Structured representation: an ordered tree of sections, fields, and tables

One of the following:

class FormField:

One labeled form entry: a text input, checkbox, select group, or signature line.

Field field

Kind of entry: text (any free-text input), checkbox, single_select, multi_select, or signature

One of the following:

CHECKBOX("checkbox")

MULTI_SELECT("multi_select")

SIGNATURE("signature")

SINGLE_SELECT("single_select")

TEXT("text")

Optional<String> id

Field number/letter printed on the form (e.g. ‘1a’), if any

Optional<Boolean> isEmpty

True for a printed-but-blank text field (mutually exclusive with value)

Optional<String> label

Printed field caption, if any

Optional<Type> type

Form field node

Optional<Value> value

Entered content: verbatim text for text fields, or a boolean for checkbox (checked) and signature (signed). Absent on blank text fields and on select groups

One of the following:

String

boolean

Optional<List<ValueItem>> valueItems

Options of a single_select/multi_select group (only on select fields)

One of the following:

FormField

class FormSection:

A grouping of form content, in the form’s reading order.

Optional<String> id

Identifier printed on the form (e.g. ‘Part III’), if any

Optional<String> label

Printed section heading, if any

Optional<Type> type

Form section node

class FormSection:

A grouping of form content, in the form’s reading order.

Optional<String> id

Identifier printed on the form (e.g. ‘Part III’), if any

Optional<String> label

Printed section heading, if any

Optional<Type> type

Form section node

FormListItem list

Flattened list representation of the same content

List<Item> items

Nested lines and sub-lists, in the form’s reading order

One of the following:

class FormListTextItem:

One line of a form’s list representation.

String md

Markdown representation of the line

String value

Line content (e.g. ‘[1a] Wages: 29,513’)

Optional<Type> type

Text line

FormListItem

String md

Markdown representation of this list

boolean ordered

Whether the list is ordered

Optional<Type> type

List node

class FormField:

One labeled form entry: a text input, checkbox, select group, or signature line.

Field field

Kind of entry: text (any free-text input), checkbox, single_select, multi_select, or signature

One of the following:

CHECKBOX("checkbox")

MULTI_SELECT("multi_select")

SIGNATURE("signature")

SINGLE_SELECT("single_select")

TEXT("text")

Optional<String> id

Field number/letter printed on the form (e.g. ‘1a’), if any

Optional<Boolean> isEmpty

True for a printed-but-blank text field (mutually exclusive with value)

Optional<String> label

Printed field caption, if any

Optional<Type> type

Form field node

Optional<Value> value

Entered content: verbatim text for text fields, or a boolean for checkbox (checked) and signature (signed). Absent on blank text fields and on select groups

One of the following:

String

boolean

Optional<List<ValueItem>> valueItems

Options of a single_select/multi_select group (only on select fields)

One of the following:

FormField

class FormSection:

A grouping of form content, in the form’s reading order.

Optional<String> id

Identifier printed on the form (e.g. ‘Part III’), if any

Optional<String> label

Printed section heading, if any

Optional<Type> type

Form section node

class FormListItem:

The list representation of form content: nested lists of rendered field lines.

List<Item> items

Nested lines and sub-lists, in the form’s reading order

One of the following:

class FormListTextItem:

One line of a form’s list representation.

String md

Markdown representation of the line

String value

Line content (e.g. ‘[1a] Wages: 29,513’)

Optional<Type> type

Text line

FormListItem

String md

Markdown representation of this list

boolean ordered

Whether the list is ordered

Optional<Type> type

List node

class FormListTextItem:

One line of a form’s list representation.

String md

Markdown representation of the line

String value

Line content (e.g. ‘[1a] Wages: 29,513’)

Optional<Type> type

Text line

class FormSection:

A grouping of form content, in the form’s reading order.

Optional<String> id

Identifier printed on the form (e.g. ‘Part III’), if any

Optional<String> label

Printed section heading, if any

Optional<Type> type

Form section node

class HeaderItem:

List<Item> items

List of items within the header

One of the following:

class CodeItem:

String md

Markdown representation preserving formatting

String value

Code content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<String> language

Programming language identifier

Optional<Type> type

Code block item type

class HeadingItem:

long level

Heading level (1-6)

String md

Markdown representation preserving formatting

String value

Heading text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Heading item type

class ImageItem:

String caption

Image caption

String md

Markdown representation preserving formatting

String url

URL to the image

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Image item type

class LinkItem:

String md

Markdown representation preserving formatting

String text

Display text of the link

String url

URL of the link

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Link item type

class ListItem:

List<Item> items

List of nested text or list items

One of the following:

class TextItem:

String md

Markdown representation preserving formatting

String value

Text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Text item type

ListItem

String md

Markdown representation preserving formatting

boolean ordered

Whether the list is ordered or unordered

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

List item type

class TableItem:

String csv

CSV representation of the table

String html

HTML representation of the table

String md

Markdown representation preserving formatting

List<List<Row>> rows

Table data as array of arrays (string, number, or null)

One of the following:

String

double

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<List<Long>> mergedFromPages

List of page numbers with tables that were merged into this table (e.g., [1, 2, 3, 4])

Optional<Long> mergedIntoPage

Populated when merged into another table. Page number where the full merged table begins (used on empty tables).

Optional<List<ParseConcern>> parseConcerns

Quality concerns detected during table extraction, indicating the table may have issues

String details

Human-readable details about the concern

String type

Type of parse concern (e.g. header_value_type_mismatch, inconsistent_row_cell_count)

Optional<Type> type

Table item type

class TextItem:

String md

Markdown representation preserving formatting

String value

Text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Text item type

String md

Markdown representation preserving formatting

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Page header container

class HeadingItem:

long level

Heading level (1-6)

String md

Markdown representation preserving formatting

String value

Heading text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Heading item type

class ImageItem:

String caption

Image caption

String md

Markdown representation preserving formatting

String url

URL to the image

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Image item type

class LinkItem:

String md

Markdown representation preserving formatting

String text

Display text of the link

String url

URL of the link

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Link item type

class ListItem:

List<Item> items

List of nested text or list items

One of the following:

class TextItem:

String md

Markdown representation preserving formatting

String value

Text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Text item type

ListItem

String md

Markdown representation preserving formatting

boolean ordered

Whether the list is ordered or unordered

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

List item type

enum LlamaParseSupportedFileExtensions:

Enum for supported file extensions.

ABW(".abw")

AWT(".awt")

AZW(".azw")

AZW3(".azw3")

AZW4(".azw4")

BMP(".bmp")

CB7(".cb7")

CBC(".cbc")

CBR(".cbr")

CBZ(".cbz")

CGM(".cgm")

CHM(".chm")

CSV(".csv")

CWK(".cwk")

DBF(".dbf")

DIF(".dif")

DJVU(".djvu")

DOC(".doc")

DOCM(".docm")

DOCX(".docx")

DOT(".dot")

DOTM(".dotm")

DOTX(".dotx")

EPUB(".epub")

ET(".et")

ETH(".eth")

FB2(".fb2")

FBZ(".fbz")

FODG(".fodg")

FODP(".fodp")

FODS(".fods")

FODT(".fodt")

FOPD(".fopd")

GIF(".gif")

HEIC(".heic")

HEIF(".heif")

HTM(".htm")

HTML(".html")

HTMLZ(".htmlz")

HWP(".hwp")

JPEG(".jpeg")

JPG(".jpg")

KEY(".key")

LIT(".lit")

LRF(".lrf")

LWP(".lwp")

M4A(".m4a")

MCW(".mcw")

MD(".md")

MOBI(".mobi")

MP3(".mp3")

MP4(".mp4")

MPEG(".mpeg")

MPGA(".mpga")

MW(".mw")

MWD(".mwd")

NUMBERS(".numbers")

ODF(".odf")

ODG(".odg")

ODP(".odp")

ODS(".ods")

ODT(".odt")

OTG(".otg")

OTP(".otp")

OTS(".ots")

OTT(".ott")

PAGES(".pages")

PBD(".pbd")

PDB(".pdb")

PDF(".pdf")

PML(".pml")

PNG(".png")

POT(".pot")

POTM(".potm")

POTX(".potx")

PPT(".ppt")

PPTM(".pptm")

PPTX(".pptx")

PRC(".prc")

PRN(".prn")

PSW(".psw")

QPW(".qpw")

RB(".rb")

RTF(".rtf")

SDA(".sda")

SDD(".sdd")

SDP(".sdp")

SDW(".sdw")

SGL(".sgl")

SLK(".slk")

SNB(".snb")

STC(".stc")

STD(".std")

STI(".sti")

STW(".stw")

SVG(".svg")

SXC(".sxc")

SXD(".sxd")

SXG(".sxg")

SXI(".sxi")

SXM(".sxm")

SXW(".sxw")

SYLK(".sylk")

TCR(".tcr")

TIF(".tif")

TIFF(".tiff")

TSV(".tsv")

TXTZ(".txtz")

UOF(".uof")

UOP(".uop")

UOS(".uos")

UOS1(".uos1")

UOS2(".uos2")

UOT(".uot")

VDX(".vdx")

VOR(".vor")

VSD(".vsd")

VSDM(".vsdm")

VSDX(".vsdx")

WAV(".wav")

WB1(".wb1")

WB2(".wb2")

WB3(".wb3")

WEBM(".webm")

WEBP(".webp")

WK1(".wk1")

WK2(".wk2")

WK3(".wk3")

WK4(".wk4")

WKS(".wks")

WN(".wn")

WPD(".wpd")

WPS(".wps")

WPT(".wpt")

WQ1(".wq1")

WQ2(".wq2")

WRI(".wri")

XHTM(".xhtm")

XLR(".xlr")

XLS(".xls")

XLSB(".xlsb")

XLSM(".xlsm")

XLSX(".xlsx")

XLW(".xlw")

XML(".xml")

YXMD(".yxmd")

ZABW(".zabw")

class ParsingJob:

A parse job (v1).

String id

Unique parse job identifier

StatusEnum status

Current job status

One of the following:

CANCELLED("CANCELLED")

ERROR("ERROR")

PARTIAL_SUCCESS("PARTIAL_SUCCESS")

PENDING("PENDING")

SUCCESS("SUCCESS")

Optional<String> errorCode

Machine-readable error code when failed

Optional<String> errorMessage

Human-readable error details when failed

enum ParsingLanguages:

Enum for representing the languages supported by the parser.

ABQ("abq")

ADY("ady")

AF("af")

ANG("ang")

AR("ar")

AS("as")

AVA("ava")

AZ("az")

BE("be")

BG("bg")

BGC("bgc")

BH("bh")

BHO("bho")

BN("bn")

BS("bs")

CH_SIM("ch_sim")

CH_TRA("ch_tra")

CHE("che")

CS("cs")

CY("cy")

DA("da")

DAR("dar")

DE("de")

EN("en")

ES("es")

ET("et")

FA("fa")

FR("fr")

GA("ga")

GOM("gom")

HI("hi")

HR("hr")

HU("hu")

ID("id")

INH("inh")

IS("is")

IT("it")

JA("ja")

KBD("kbd")

KN("kn")

KO("ko")

KU("ku")

LA("la")

LBE("lbe")

LEZ("lez")

LT("lt")

LV("lv")

MAH("mah")

MAI("mai")

MI("mi")

MN("mn")

MNI("mni")

MR("mr")

MS("ms")

MT("mt")

NE("ne")

NEW("new")

NL("nl")

NO("no")

OC("oc")

PI("pi")

PL("pl")

PT("pt")

RO("ro")

RS_CYRILLIC("rs_cyrillic")

RS_LATIN("rs_latin")

RU("ru")

SA("sa")

SCK("sck")

SK("sk")

SL("sl")

SQ("sq")

SV("sv")

SW("sw")

TA("ta")

TAB("tab")

TE("te")

TH("th")

TJK("tjk")

TL("tl")

TR("tr")

UG("ug")

UK("uk")

UR("ur")

UZ("uz")

VI("vi")

enum ParsingMode:

Enum for representing the mode of parsing to be used.

PARSE_DOCUMENT_WITH_AGENT("parse_document_with_agent")

PARSE_DOCUMENT_WITH_LLM("parse_document_with_llm")

PARSE_DOCUMENT_WITH_LVM("parse_document_with_lvm")

PARSE_PAGE_WITH_AGENT("parse_page_with_agent")

PARSE_PAGE_WITH_LAYOUT_AGENT("parse_page_with_layout_agent")

PARSE_PAGE_WITH_LLM("parse_page_with_llm")

PARSE_PAGE_WITH_LVM("parse_page_with_lvm")

PARSE_PAGE_WITHOUT_LLM("parse_page_without_llm")

enum StatusEnum:

Enum for representing the status of a job

CANCELLED("CANCELLED")

ERROR("ERROR")

PARTIAL_SUCCESS("PARTIAL_SUCCESS")

PENDING("PENDING")

SUCCESS("SUCCESS")

class TableItem:

String csv

CSV representation of the table

String html

HTML representation of the table

String md

Markdown representation preserving formatting

List<List<Row>> rows

Table data as array of arrays (string, number, or null)

One of the following:

String

double

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<List<Long>> mergedFromPages

List of page numbers with tables that were merged into this table (e.g., [1, 2, 3, 4])

Optional<Long> mergedIntoPage

Populated when merged into another table. Page number where the full merged table begins (used on empty tables).

Optional<List<ParseConcern>> parseConcerns

Quality concerns detected during table extraction, indicating the table may have issues

String details

Human-readable details about the concern

String type

Type of parse concern (e.g. header_value_type_mismatch, inconsistent_row_cell_count)

Optional<Type> type

Table item type

class TextItem:

String md

Markdown representation preserving formatting

String value

Text content

Optional<List<BBox>> bbox

List of bounding boxes

double h

Height of the bounding box

double w

Width of the bounding box

double x

X coordinate of the bounding box

double y

Y coordinate of the bounding box

Optional<Double> confidence

Confidence score

Optional<Long> endIndex

End index in the text

Optional<String> label

Label for the bounding box

Optional<Double> r

Optional visual text rotation angle in degrees. Omitted when unrotated.

Optional<Long> startIndex

Start index in the text

Optional<Type> type

Text item type