Parse a document

post

https://chunk.ing/

Convert and split a document into optimal chunks.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Convert files into optimal chunks of text ready to be embedded and/or indexed.

In case of success, the response will provide you with a string process ID that you can use to keep track of the different parsing jobs you started.

Learn more about how to use the Parsing parameters and what output to expect.

For code examples, check out how to integrate it in a custom pipeline, LlamaIndex, or LangChain

Query Params

webhook

string

The URL to be called after chunking, where the result will be posted. If you prefer to get the result through an HTTP request, omit this parameter.

language

string

The language in ISO 639-1 format. If not provided, the system will automatically identify it.

repeat_title

boolean

Defaults to false

If set to true, each chunk will include the title of the parent paragraph/section.

keep_header

boolean

Defaults to true

If set to false, the content of the headers will be removed. Headers may include page numbers, document titles, section titles, paragraph titles, and fixed layout elements.

smart_header

boolean

Defaults to true

If set to true, only relevant titles will be included in the chunks, while other information will be removed. Relevant titles are those that should be part of the body of the page as a title. If set to false, only the keep_header parameter will be considered. If keep_header is false, the smart_header parameter will be ignored.

keep_footer

boolean

Defaults to false

If set to true, the content of the footers will be included in the chunks. Footers may include page numbers, footnotes, and fixed layout elements.

image_text

boolean

Defaults to false

If set to true, the text contained in the images will be added to the chunks.

table_output_format

string

enum

Defaults to text

Specifies the output format for tables.

Allowed:

repeat_table_header

boolean

Defaults to false

If set to true, and if tables are split across multiple chunks, each chunk will include the table row header.

merge

boolean

Defaults to false

If set to true, short chunks will be merged with others to maximize the chunk length.

Body Params

file

required

The file to be uploaded as binary in the request form. Maximum file size 30 MB. Allowed file types: pdf, doc, docx, ppt, pptx, xls, xlsx, odt, ods, odp, eml, html, plain text

Response

200200