Skip to main content
POST
Python

Authorizations

Authorization
string
header
required

Body

application/json

JSON request to create a parse task

file
string
required

The file to be parsed. Supported inputs:

  • ch://files/{file_id}: Reference to an existing file. Upload via the Files API
  • http(s)://...: Remote URL to fetch
  • data:*;base64,... or raw base64 string
chunk_processing
object

Controls the setting for the chunking and post-processing of each chunk.

error_handling
enum<string>
default:Fail

Controls how errors are handled during processing:

  • Fail: Stops processing and fails the task when any error occurs
  • Continue: Attempts to continue processing despite non-critical errors (eg. LLM refusals etc.)
Available options:
Fail,
Continue
ocr_strategy
enum<string>
default:All

Controls the Optical Character Recognition (OCR) strategy.

  • All: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
  • Auto: Selectively applies OCR only to pages with missing or low-quality text. When text layer is present the bounding boxes from the text layer are used.
Available options:
All,
Auto
pipeline
enum<string>
default:Chunkr
deprecated
Available options:
Azure,
Chunkr
segment_processing
null | object

Configuration for how each document segment is processed and formatted.

Each segment has sensible defaults, but you can override specific settings:

  • format: Output as Html or Markdown
  • strategy: Auto (rule-based), LLM (AI-generated), or Ignore (skip)
  • crop_image: Whether to crop images to segment bounds
  • extended_context: Use full page as context for LLM processing
  • description: Generate descriptions for segments

Defaults per segment type: Check the documentation for more details.

Only specify the fields you want to change - everything else uses the defaults.

segmentation_strategy
enum<string>
default:LayoutAnalysis

Controls the segmentation strategy:

  • LayoutAnalysis: Analyzes pages for layout elements (e.g., Table, Picture, Formula, etc.) using bounding boxes. Provides fine-grained segmentation and better chunking.
  • Page: Treats each page as a single segment. Faster processing, but without layout element detection and only simple chunking.
Available options:
LayoutAnalysis,
Page
expires_in
integer<int32> | null

The number of seconds until task is deleted. Expired tasks can not be updated, polled or accessed via web interface.

file_name
string | null

The name of the file to be parsed. If not set a name will be generated.

Response

Task created successfully.

completed
boolean
required

True when the task reaches a terminal state i.e. status is Succeeded or Failed or Cancelled

configuration
Parse · object
required
created_at
string<date-time>
required

The date and time when the task was created and queued.

file_info
object
required

Information about the input file.

message
string
required

A message describing the task's status or any errors that occurred.

status
enum<string>
required

The status of the task.

Available options:
Starting,
Processing,
Succeeded,
Failed,
Cancelled
task_id
string
required

The unique identifier for the task.

task_type
enum<string>
required
Available options:
Parse,
Extract
version_info
object
required

Version information for the task.

expires_at
string<date-time> | null

The date and time when the task will expire.

finished_at
string<date-time> | null

The date and time when the task was finished.

input_file_url
string | null
deprecated

The presigned URL of the input file. Deprecated use file_info.url instead.

output
null | Parse · object

The processed results of a document parsing task

started_at
string<date-time> | null

The date and time when the task was started.

task_url
string | null

The presigned URL of the task.