Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/lumina-ai-inc/chunkr/llms.txt

Use this file to discover all available pages before exploring further.

​
Segment Types

Chunkr identifies the following segment types during layout analysis:
​
Title
SegmentType
Main title or heading of the document.
​
SectionHeader
SegmentType
Section headers and subheadings within the document.
​
Text
SegmentType
Regular paragraph text.
​
ListItem
SegmentType
Individual items in bulleted or numbered lists.
​
Table
SegmentType
Tabular data.
​
Picture
SegmentType
Images, diagrams, and figures.
​
Caption
SegmentType
Captions for images, tables, or other elements.
​
Formula
SegmentType
Mathematical formulas and equations.
​
Footnote
SegmentType
Footnotes and endnotes.
​
PageHeader
SegmentType
Headers that appear at the top of pages.
​
PageFooter
SegmentType
Footers that appear at the bottom of pages.
​
Page
SegmentType
An entire page treated as a single segment (when using Page segmentation strategy).

​
Segment Processing

The SegmentProcessing configuration allows you to control how each segment type is processed and which content representations are generated.

​
Configuration Structure

Each segment type can have its own processing configuration: 
{
  "segment_processing": {
    "Title": { /* AutoGenerationConfig */ },
    "SectionHeader": { /* AutoGenerationConfig */ },
    "Text": { /* AutoGenerationConfig */ },
    "ListItem": { /* AutoGenerationConfig */ },
    "Table": { /* TableGenerationConfig */ },
    "Picture": { /* PictureGenerationConfig */ },
    "Caption": { /* AutoGenerationConfig */ },
    "Formula": { /* LlmGenerationConfig */ },
    "Footnote": { /* AutoGenerationConfig */ },
    "PageHeader": { /* AutoGenerationConfig */ },
    "PageFooter": { /* AutoGenerationConfig */ },
    "Page": { /* LlmGenerationConfig */ }
  }
}

​
AutoGenerationConfig

Used for most segment types (Title, SectionHeader, Text, ListItem, Caption, Footnote, PageHeader, PageFooter).
​
format
SegmentFormat
default:"Markdown"
Specifies the output format.
​
strategy
GenerationStrategy
default:"Auto"
Determines how the content is generated.
​
crop_image
CroppingStrategy
default:"Auto"
Controls whether to crop the page image to the segment’s bounding box.
​
llm
string
Custom prompt for LLM-based processing of this segment. Only used when LLM processing is enabled for the segment.
​
embed_sources
EmbedSource[]
default:"[Content]"
Defines which content sources will be included in the chunk’s embed field and counted towards the chunk length. The array’s order determines the sequence in which content appears.
​
extended_context
boolean
default:false
Use the full page image as context for LLM generation.

​
Deprecated Fields

​
html
GenerationStrategy
deprecated
DEPRECATED: Use format: Html and strategy instead.
​
markdown
GenerationStrategy
deprecated
DEPRECATED: Use format: Markdown and strategy instead.

​
LlmGenerationConfig

Used for Formula and Page segment types. Has the same fields as AutoGenerationConfig but with strategy defaulting to LLM.
​
format
SegmentFormat
default:"Markdown"
Output format (Html or Markdown).
​
strategy
GenerationStrategy
default:"LLM"
Generation strategy (Auto or LLM).
​
crop_image
CroppingStrategy
default:"Auto"
Image cropping strategy.
​
llm
string
Custom LLM prompt.
​
embed_sources
EmbedSource[]
default:"[Content]"
Content sources for embedding.
​
extended_context
boolean
default:false
Use full page image as context.

​
TableGenerationConfig

Used specifically for Table segments. Has the same fields as AutoGenerationConfig but with different defaults.
​
format
SegmentFormat
default:"Html"
Output format (Html or Markdown). Tables default to HTML for better structure preservation.
​
strategy
GenerationStrategy
default:"LLM"
Generation strategy. Tables default to LLM for higher accuracy.
​
crop_image
CroppingStrategy
default:"Auto"
Image cropping strategy.
​
llm
string
Custom LLM prompt.
​
embed_sources
EmbedSource[]
default:"[Content]"
Content sources for embedding.
​
extended_context
boolean
default:false
Use full page image as context.

​
PictureGenerationConfig

Used specifically for Picture segments.
​
format
SegmentFormat
default:"Markdown"
Output format (Html or Markdown).
​
strategy
GenerationStrategy
default:"Auto"
Generation strategy.When set to Auto, generates image tags:
  • HTML format: <img src="{url}" />
  • Markdown format: ![Image]({url})
​
crop_image
PictureCroppingStrategy
default:"All"
Controls image cropping for pictures.
​
llm
string
Custom LLM prompt for describing or processing the image.
​
embed_sources
EmbedSource[]
default:"[Content]"
Content sources for embedding.
​
extended_context
boolean
default:false
Use full page image as context.

​
Example Configuration

{
  "segment_processing": {
    "Text": {
      "format": "Markdown",
      "strategy": "Auto",
      "crop_image": "Auto",
      "embed_sources": ["Content"]
    },
    "Table": {
      "format": "Html",
      "strategy": "LLM",
      "crop_image": "All",
      "embed_sources": ["Content", "LLM"]
    },
    "Picture": {
      "format": "Markdown",
      "strategy": "Auto",
      "crop_image": "All",
      "embed_sources": ["Content"]
    },
    "Formula": {
      "format": "Markdown",
      "strategy": "LLM",
      "crop_image": "Auto",
      "embed_sources": ["LLM"],
      "llm": "Convert this formula to LaTeX notation"
    }
  }
}

Build docs developers (and LLMs) love

Get started for freeTalk to us