Struct FileExtractionConfig 

pub struct FileExtractionConfig {

    pub enable_quality_processing: Option<bool>,
    pub ocr: Option<OcrConfig>,
    pub force_ocr: Option<bool>,
    pub force_ocr_pages: Option<Vec<usize>>,
    pub chunking: Option<ChunkingConfig>,
    pub images: Option<ImageExtractionConfig>,
    pub token_reduction: Option<TokenReductionConfig>,
    pub language_detection: Option<LanguageDetectionConfig>,
    pub pages: Option<PageConfig>,
    pub postprocessor: Option<PostProcessorConfig>,
    pub result_format: Option<OutputFormat>,
    pub output_format: Option<OutputFormat>,
    pub include_document_structure: Option<bool>,
    pub timeout_secs: Option<u64>,
}

Per-file extraction configuration overrides for batch processing.

All fields are Option<T> — None means “use the batch-level default.” This type is used with crate::batch_extract_file and crate::batch_extract_bytes to allow heterogeneous extraction settings within a single batch.

Excluded Fields

The following super::ExtractionConfig fields are batch-level only and cannot be overridden per file:

• max_concurrent_extractions — controls batch parallelism
• use_cache — global caching policy
• acceleration — shared ONNX execution provider
• security_limits — global archive security policy

Example

use kreuzberg::FileExtractionConfig;

// Override just OCR forcing for a specific file
let config = FileExtractionConfig {
    force_ocr: Some(true),
    ..Default::default()
};

Fields

enable_quality_processing: Option<bool>

Override quality post-processing for this file.

ocr: Option<OcrConfig>

Override OCR configuration for this file (None in the Option = use batch default).

force_ocr: Option<bool>

Override force OCR for this file.

force_ocr_pages: Option<Vec<usize>>

Override force OCR pages for this file (1-indexed page numbers).

chunking: Option<ChunkingConfig>

Override chunking configuration for this file.

images: Option<ImageExtractionConfig>

Override image extraction configuration for this file.

token_reduction: Option<TokenReductionConfig>

Override token reduction for this file.

language_detection: Option<LanguageDetectionConfig>

Override language detection for this file.

pages: Option<PageConfig>

Override page extraction for this file.

postprocessor: Option<PostProcessorConfig>

Override post-processor for this file.

result_format: Option<OutputFormat>

Override result format for this file.

output_format: Option<OutputFormat>

Override output content format for this file.

include_document_structure: Option<bool>

Override document structure output for this file.

timeout_secs: Option<u64>

Override per-file extraction timeout in seconds.

When set, the extraction for this file will be canceled after the specified duration. A timed-out file produces an error result without affecting other files in the batch.

Trait Implementations

impl Clone for FileExtractionConfig

fn clone(&self) -> FileExtractionConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for FileExtractionConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for FileExtractionConfig

fn default() -> FileExtractionConfig

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FileExtractionConfig

where FileExtractionConfig: Default,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for FileExtractionConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.