Skip to main content
Parse returns structured content in a format optimized for RAG and LLM applications. This page explains every field in the response.

Response Structure

Top-Level Fields


Result Types: Full vs URL

Parse can return results in two ways:
When returned: Documents under ~6MB response size (most documents).How to use: Access result.chunks directly.
To always receive a URL (useful for consistent handling), set force_url_result: true in your request.
Result URLs expire after 12 hours. For pdf_url and block image_url, the 12 hours start when the job completes. Reducto signs a new result.url each time you fetch the job. Download or process the content promptly after receiving the response. This applies to:
  • result.url (when type: "url")
  • pdf_url (processed PDF)
  • image_url on blocks (when return_images is enabled)

Understanding Chunks

Chunks are the primary output unit, optimized for RAG and embedding workflows.

content vs embed

  • content: Raw extracted content, preserves original text
  • embed: Optimized for vector embeddings, may include:
    • Table summaries (natural language descriptions)
    • Figure summaries (AI-generated descriptions)
For RAG: Use embed for your vector database, content for display.

Understanding Blocks

Blocks are the atomic content elements within each chunk. Every paragraph, table, header, and figure is a separate block.

Block Types

Reducto returns Comment blocks only when formatting.include contains "comments" and the document has comments, such as PDF comment annotations or Word comments. Reducto has no checkbox block type. A checkbox appears inside its block’s content as [x] (checked) or [ ] (unchecked), for example [x] Agree to terms.

Block Fields


Bounding Box Coordinates

Every block includes a bbox object describing its position on the page.

Coordinate System

All coordinates are normalized to [0, 1] relative to page dimensions:
page and original_page differ when using page_range to process a subset of pages. For example, if you process pages 5-10, page 5 becomes page: 1 but original_page: 5.

Confidence Scores

Parse provides confidence scores to help you identify potentially problematic extractions.

String Confidence

  • high: Extraction is reliable
  • low: May need review; compare the extracted content with the source. If your workflow needs use-case-specific interpretation, add a scoped custom prompt.

Granular Confidence


Complete Example

Here’s a complete example showing the full structure:

Parse Overview

Quick start and basic usage.

Best Practices

Optimize for your document types.

Chunking Methods

Control how content is split.

Table Output Formats

HTML, Markdown, JSON, CSV options.