import type * as Extend from "../index"; /** * Configuration options for the parsing process. Defaults depend on the selected parser engine and version. */ export interface ParseConfig { /** * The target format for the parsed content. * * Supported values: * * * `markdown`: True markdown with logical reading order (headings, lists, tables, checkboxes). Best default for LLMs/RAG and enables section-based chunking. * * `spatial`: Layout/position-preserving text that uses markdown elements for block types but is not strictly markdown due to whitespace/tabs used to maintain placement. Only page-based chunking is supported. * * Guidance: * * * Prefer `markdown` for most documents, multi-column reading order, and retrieval use cases * * Prefer `spatial` for messy/scanned/handwritten or skewed documents, when you need near 1:1 layout fidelity, or for BOL-like logistics docs * * See “Markdown vs Spatial” in the [Parse guide](https://docs.extend.ai/2026-02-09/product/parsing/configuration-options#target-format) for details. */ target?: Extend.ParseConfigTarget; /** Strategy for dividing the document into chunks. */ chunkingStrategy?: Extend.ParseConfigChunkingStrategy; /** * The parsing engine to use. Supported values: * * `parse_performance`: Full-featured parsing engine with highest accuracy (default) * * `parse_light`: Lightweight parsing engine optimized for speed. This does not have robust layout support and does not support markdown layout target. */ engine?: Extend.ParseConfigEngine; /** Pin a specific parser engine version for reproducibility. When set to `latest`, the most recent stable version of the selected engine is used. */ engineVersion?: string; /** Options for controlling how different block types are processed. */ blockOptions?: Extend.ParseConfigBlockOptions; advancedOptions?: Extend.ParseConfigAdvancedOptions; }