The general API from Unstructured — 1 operation(s) for general.
openapi: 3.1.0
info:
title: Unstructured Partition channels general API
version: 1.5.58
servers:
- url: https://api.unstructuredapp.io
description: Serverless SaaS API
x-speakeasy-server-id: saas-api
- url: http://localhost:8000
description: Development server
x-speakeasy-server-id: development
security:
- ApiKeyAuth: []
- {}
tags:
- name: general
paths:
/general/v0/general:
post:
tags:
- general
summary: Summary
description: Description
operationId: partition
parameters:
- name: unstructured-api-key
in: header
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Unstructured-Api-Key
requestBody:
required: true
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/partition_parameters'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
items:
$ref: '#/components/schemas/Element'
description: A list of element dictionaries extracted from the file
title: Elements
type: array
x-speakeasy-name-override: elements
text/csv:
schema:
items:
$ref: '#/components/schemas/CSV-Element'
description: A string containing elements in csv format
title: CSV-Element
type: string
x-speakeasy-name-override: csv_elements
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
5XX:
description: Server Error
content:
application/json:
schema:
$ref: '#/components/schemas/ServerError'
x-speakeasy-name-override: partition
components:
schemas:
ServerError:
type: object
properties:
detail:
type: string
example:
detail: An error occurred
CSV-Element:
title: CSV-Element
type: string
example: "type,element_id,text,languages,page_number,filename,filetype,parent_id,links\n Title,b7f58c2fd9c15949a55a62eb84e39575,LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis,['eng'],1,layout-parser-paper.pdf,application/pdf,,"
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
partition_parameters:
properties:
files:
type: string
format: binary
description: The file to extract
examples:
- summary: File to be partitioned
externalValue: https://github.com/Unstructured-IO/unstructured/blob/98d3541909f64290b5efb65a226fc3ee8a7cc5ee/example-docs/layout-parser-paper.pdf
coordinates:
type: boolean
title: Coordinates
description: 'If `True`, return coordinates for each element extracted via OCR. Default: `False`'
default: false
content_type:
anyOf:
- type: string
- type: 'null'
title: Content type
description: 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.
encoding:
anyOf:
- type: string
- type: 'null'
title: Encoding
description: 'The encoding method used to decode the text input. Default: utf-8'
extract_image_block_types:
items:
type: string
type: array
title: Image block types to extract
description: The types of elements to extract, for use in extracting image blocks as base64 encoded data stored in metadata fields.
default: []
gz_uncompressed_content_type:
anyOf:
- type: string
- type: 'null'
title: Uncompressed Content Type
description: If file is gzipped, use this content type after unzipping.
hi_res_model_name:
anyOf:
- type: string
- type: 'null'
title: Hi Res Model Name
description: The name of the inference model used when strategy is hi_res
include_page_breaks:
type: boolean
title: Include Page Breaks
description: 'If true, the output will include page breaks if the filetype supports it. Default: false'
default: false
languages:
items:
type: string
type: array
title: OCR Languages
description: The languages present in the document, for use in partitioning and/or OCR. See the Tesseract documentation for a full list of languages.
default: []
ocr_languages:
items:
type: string
type: array
title: OCR Languages
description: Deprecated! The languages present in the document, for use in partitioning and/or OCR
default: []
output_format:
type: string
enum:
- application/json
- text/csv
title: Output Format
description: 'The format of the response. Supported formats are application/json and text/csv. Default: application/json.'
default: application/json
x-speakeasy-unknown-values: allow
pdf_infer_table_structure:
type: boolean
title: Pdf Infer Table Structure
description: 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.
default: true
skip_infer_table_types:
items:
type: string
type: array
title: Skip Infer Table Types
description: 'The document types that you want to skip table extraction with. Default: []'
default: []
starting_page_number:
anyOf:
- type: integer
- type: 'null'
title: PDF Starting Page Number
description: 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.
strategy:
type: string
enum:
- fast
- hi_res
- auto
- ocr_only
- od_only
- vlm
title: Strategy
description: 'The strategy to use for partitioning PDF/image. Options are fast, hi_res, auto. Default: hi_res'
default: hi_res
examples:
- auto
- hi_res
- vlm
x-speakeasy-unknown-values: allow
vlm_model_provider:
type: string
enum:
- openai
- anthropic
- bedrock
- anthropic_bedrock
- vertexai
- google
- azure_openai
title: VLM Model Provider
description: The VLM Model provider to use.
examples:
- openai
- anthropic
- bedrock
x-speakeasy-unknown-values: allow
vlm_model:
type: string
title: VLM Model
description: The VLM Model to use.
examples:
- gpt-4o
x-speakeasy-unknown-values: allow
table_ocr_agent:
anyOf:
- type: string
- type: 'null'
title: Table OCR Agent
description: The OCR agent to use for table ocr inference.
default: unstructured.partition.utils.ocr_models.tesseract_ocr.OCRAgentTesseract
unique_element_ids:
type: boolean
title: Unique Element IDs
description: '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`'
default: false
xml_keep_tags:
type: boolean
title: Xml Keep Tags
description: 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.
default: false
chunking_strategy:
anyOf:
- type: string
- type: 'null'
title: Chunking Strategy
description: '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'''
examples:
- by_title
- basic
x-speakeasy-unknown-values: allow
combine_under_n_chars:
anyOf:
- type: integer
- type: 'null'
title: Combine Under N Chars
description: 'If chunking strategy is set, combine elements until a section reaches a length of n chars. Default: 500'
include_orig_elements:
anyOf:
- type: boolean
- type: 'null'
title: Include original elements in chunks
description: 'When a chunking strategy is specified, each returned chunk will include the elements consolidated to form that chunk as `.metadata.orig_elements`. Default: true.'
tracking_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Tracking enabled
description: Tracking enabled
max_characters:
anyOf:
- type: integer
- type: 'null'
title: Max Characters
description: 'If chunking strategy is set, cut off new sections after reaching a length of n chars (hard max). Default: 500'
multipage_sections:
type: boolean
title: Multipage Sections
description: 'If chunking strategy is set, determines if sections can span multiple sections. Default: true'
default: true
new_after_n_chars:
anyOf:
- type: integer
- type: 'null'
title: New after n chars
description: 'If chunking strategy is set, cut off new sections after reaching a length of n chars (soft max). Default: 1500'
overlap:
type: integer
title: Overlap
description: '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'
default: 0
overlap_all:
type: boolean
title: Overlap all
description: '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'
default: false
skip_table_chunking:
type: boolean
title: Skip table chunking
description: 'When `True`, tables are not chunked and always kept unchanged. Default: False'
default: false
isolate_table:
anyOf:
- type: boolean
- type: 'null'
title: Isolate table
description: 'When `True`, tables are never chunked together with other elements. Default: True'
default: true
similarity_threshold:
anyOf:
- type: number
- type: 'null'
title: similarity-threshold
description: 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.
do_not_break_similarity_on_footer_header:
type: boolean
title: do-not-break-similarity-on-footer-header
description: When `True`, footer, header, and page number are always considered similar to the text before them for chunk by similarity method. This allows chunk by similarity to connect contents across page better.
default: false
contextual_chunking_service_name:
anyOf:
- type: string
- type: 'null'
title: Contextual Chunking Service Name
description: Pre-resolved prompt service name for contextual chunking (e.g. 'BedrockContextualChunking'). When set, uses this service with the provided auth instead of the default env-var-based model selection.
contextual_chunking_auth:
anyOf:
- type: string
- type: 'null'
title: Contextual Chunking Auth
description: JSON-encoded auth credentials for the contextual chunking provider. Structure depends on the provider.
include_slide_notes:
type: boolean
title: include_slide_notes
description: 'When `True`, slide notes from .ppt and .pptx files will be included in the response. Default: `True`'
default: true
pdfminer_line_overlap:
anyOf:
- type: number
- type: 'null'
title: PDFMiner Line Overlap
description: If two characters have more overlap than this they are considered to be on the same line. The overlap is specified relative to the minimum height of both characters.
pdfminer_char_margin:
anyOf:
- type: number
- type: 'null'
title: PDFMiner Char Margin
description: If two characters are closer together than this margin they are considered part of the same line. The margin is specified relative to the width of the character.
pdfminer_line_margin:
anyOf:
- type: number
- type: 'null'
title: PDFMiner Line Margin
description: If two lines are close together they are considered to be part of the same paragraph. The margin is specified relative to the height of a line.
pdfminer_word_margin:
anyOf:
- type: number
- type: 'null'
title: PDFMiner Word Margin
description: If two characters on the same line are further apart than this margin then they are considered to be two separate words, and an intermediate space will be added for readability. The margin is specified relative to the width of the character.
default: 0.185
type: object
required:
- files
title: Partition Parameters
HTTPValidationError:
type: object
properties:
detail:
oneOf:
- type: array
items:
$ref: '#/components/schemas/ValidationError'
- type: string
example:
detail:
- type: int_parsing
loc:
- body
- combine_under_n_chars
msg: Input should be a valid integer, unable to parse string as an integer
input: forty
Element:
title: Element
type: object
additionalProperties: true
example:
type: Title
element_id: 6aa0ff22f91bbe7e26e8e25ca8052acd
text: 'LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis'
metadata:
languages:
- eng
page_number: 1
filename: layout-parser-paper.pdf
filetype: application/pdf
securitySchemes:
ApiKeyAuth:
type: apiKey
name: unstructured-api-key
in: header
x-speakeasy-example: YOUR_API_KEY
x-speakeasy-retries:
strategy: backoff
backoff:
initialInterval: 3000
maxInterval: 720000
maxElapsedTime: 1800000
exponent: 1.88
statusCodes:
- 5xx
retryConnectionErrors: true