Struct KreuzbergConfig 

pub struct KreuzbergConfig {
    pub ocr_enabled: bool,
    pub force_ocr: bool,
    pub ocr_backend: String,
    pub ocr_language: String,
    pub pdf_dpi: u32,
    pub extract_tables: bool,
    pub extract_metadata: bool,
    pub output_format: String,
    pub chunking: Option<KreuzbergChunkingConfig>,
    pub max_input_bytes: u64,
    pub extraction_timeout_secs: u64,
}

Kreuzberg local file processing configuration. Kreuzberg is a high-performance document intelligence framework with a Rust core.

Fields

ocr_enabled: bool

Enable OCR for scanned documents and images

force_ocr: bool

Force OCR even if text layer exists in PDFs

ocr_backend: String

OCR backend: “tesseract” (default), “easyocr”, “paddleocr”

ocr_language: String

OCR language(s), e.g., “eng”, “eng+deu” for multiple

pdf_dpi: u32

PDF rendering DPI for OCR (higher = better quality but more memory)

extract_tables: bool

Extract tables from documents

extract_metadata: bool

Extract metadata from documents

output_format: String

Output format: “markdown” or “text”

chunking: Option<KreuzbergChunkingConfig>

Optional chunking config for RAG pipelines (kreuzberg v4 feature)

max_input_bytes: u64

Maximum accepted input size in bytes before handing content to kreuzberg’s native parsers. Compensating control for RUSTSEC-2026-0187 (lopdf stack overflow) / RUSTSEC-2026-0194 (quick-xml quadratic attribute-check DoS): both are reachable through kreuzberg’s document-parsing path with no consumer-side opt-out, so bounding the input size limits the CPU/stack cost a single crafted document can incur.

extraction_timeout_secs: u64

Wall-clock timeout (seconds) for a single kreuzberg extraction call. Compensating control alongside max_input_bytes — bounds worst-case request latency if a crafted document still triggers pathological parsing cost within the size cap.

Trait Implementations

impl Clone for KreuzbergConfig

fn clone(&self) -> KreuzbergConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for KreuzbergConfig

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

Formats the value using the given formatter.

impl Default for KreuzbergConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for KreuzbergConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for KreuzbergConfig

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.