Documentation Index
Fetch the complete documentation index at: https://mintlify.com/reductoai/reducto-python-sdk/llms.txt
Use this file to discover all available pages before exploring further.
ParseResponse
Response from document parsing operations.The duration of the parse request in seconds.
Unique identifier for the parse job.
The response from the document processing service. Can be either a Full Result or URL Result. Due to HTTPS size limitations, large responses are returned as presigned URLs.
Usage information for the parse operation.
The storage URL of the converted PDF file.
The link to the studio pipeline for the document.
Result Types
Full Result
Array of extracted chunks from the document.
Always set to “full”.
Custom metadata fields.
OCR data including lines and words with bounding boxes and confidence scores.
URL Result
Unique identifier for the result.
Always set to “url”.
Presigned URL to download the full result.
Chunk Structure
Array of blocks within the chunk.
The content of the chunk extracted from the document.
Chunk content optimized for embedding and retrieval.
The enriched content of the chunk extracted from the document.
Whether the enrichment was successful.
Block Structure
The bounding box of the block extracted from the document.
The content of the block extracted from the document.
The type of block. One of:
Header, Footer, Title, Section Header, Page Number, List Item, Figure, Table, Key Value, Text, Comment, Signature.(Experimental) The URL/link to chart data JSON for figure blocks processed by chart agent.
The confidence for the block (“low” or “high”). Takes into account factors like OCR and table structure.
Extra metadata fields for the block. Fields like ‘is_chart’ will only appear when set to True.
Granular confidence scores for the block. Available when numeric confidence scores are enabled.
(Experimental) The URL of the image associated with the block.
ExtractResponse
Response from structured data extraction operations.The extracted response in your provided schema. This is a list of dictionaries. If disable_chunking is True (default), then it will be a list of length one.
Usage information for the extract operation.
The citations corresponding to the extracted response.
Unique identifier for the extract job.
The link to the studio pipeline for the document.
V3ExtractResponse
Response from V3 extraction operations.The extracted response in your provided schema. This is a list of dictionaries. If disable_chunking is True (default), then it will be a list of length one.
Usage information for the extract operation.
Unique identifier for the extract job.
The link to the studio pipeline for the document.
SplitResponse
Response from document splitting operations.The split result containing section mappings and splits.
Usage information for the split operation.
SplitResult Structure
Array of document splits.
Mapping of section names to page numbers.
Split Structure
Name of the split section.
Page numbers included in this split.
Confidence level of the split (“high” or “low”).
Sub-partitions within this split.
EditResponse
Response from document editing operations.Presigned URL to download the edited document.
Form schema for PDF forms. List of widgets with their types, descriptions, and bounding boxes.
Usage information for the edit operation, including number of pages and credits charged.
FormSchema Structure
Bounding box coordinates of the widget.
Description of the widget extracted from the document.
Type of the form widget. One of:
text, checkbox, radio, dropdown, barcode.If True (default), the system will attempt to fill this widget. If False, the widget will be created but intentionally left unfilled.
If provided, this value will be used directly instead of attempting to intelligently determine the field value.
PipelineResponse
Response from pipeline operations combining multiple processing steps.Unique identifier for the pipeline job.
Combined results from all pipeline steps.
Total usage information for the pipeline operation.
PipelineResult Structure
Extract operation results. Can be a list of results (for Extract -> Split pipelines) or a single result.
Parse operation results. Can be a single response or list of responses.
Split operation results.
Edit operation results.