Pipeline
Description
Authorizations
Headers
Body
The file to extract
If True, return coordinates for each element extracted via OCR. Default: False
A hint about the content type to use (such as text/markdown), when there are problems processing a specific file. This value is a MIME type in the format type/subtype.
The encoding method used to decode the text input. Default: utf-8
The types of elements to extract, for use in extracting image blocks as base64 encoded data stored in metadata fields.
If file is gzipped, use this content type after unzipping.
The name of the inference model used when strategy is hi_res
If true, the output will include page breaks if the filetype supports it. Default: false
The languages present in the document, for use in partitioning and/or OCR. See the Tesseract documentation for a full list of languages.
Deprecated! The languages present in the document, for use in partitioning and/or OCR
The format of the response. Supported formats are application/json and text/csv. Default: application/json.
application/json, text/csv Deprecated! Use skip_infer_table_types to opt out of table extraction for any file type. If False and strategy=hi_res, no Table Elements will be extracted from pdf files regardless of skip_infer_table_types contents.
The document types that you want to skip table extraction with. Default: []
When PDF is split into pages before sending it into the API, providing this information will allow the page number to be assigned correctly. Introduced in 1.0.27.
The strategy to use for partitioning PDF/image. Options are fast, hi_res, auto. Default: hi_res
fast, hi_res, auto, ocr_only When True, assign UUIDs to element IDs, which guarantees their uniqueness (useful when using them as primary keys in database). Otherwise a SHA-256 of element text is used. Default: False
If True, will retain the XML tags in the output. Otherwise it will simply extract the text from within the tags. Only applies to XML documents.
Use one of the supported strategies to chunk the returned elements after partitioning. When 'chunking_strategy' is not specified, no chunking is performed and any other chunking parameters provided are ignored. Supported strategies: 'basic', 'by_page', 'by_similarity', or 'by_title'
basic, by_page, by_similarity, by_title If chunking strategy is set, combine elements until a section reaches a length of n chars. Default: 500
When a chunking strategy is specified, each returned chunk will include the elements consolidated to form that chunk as .metadata.orig_elements. Default: true.
If chunking strategy is set, cut off new sections after reaching a length of n chars (hard max). Default: 500
If chunking strategy is set, determines if sections can span multiple sections. Default: true
If chunking strategy is set, cut off new sections after reaching a length of n chars (soft max). Default: 1500
Specifies the length of a string ('tail') to be drawn from each chunk and prefixed to the next chunk as a context-preserving mechanism. By default, this only applies to split-chunks where an oversized element is divided into multiple chunks by text-splitting. Default: 0
When True, apply overlap between 'normal' chunks formed from whole elements and not subject to text-splitting. Use this with caution as it entails a certain level of 'pollution' of otherwise clean semantic chunk boundaries. Default: False
A value between 0.0 and 1.0 describing the minimum similarity two elements must have to be included in the same chunk. Note that similar elements may be separated to meet chunk-size criteria; this value can only guarantees that two elements with similarity below the threshold will appear in separate chunks.
When True, slide notes from .ppt and .pptx files will be included in the response. Default: True
Response
A list of element dictionaries extracted from the file
Was this page helpful?