Skip to main content

DefaultParserOcrProvider

Trait DefaultParserOcrProvider 

Source
pub trait DefaultParserOcrProvider: Send + Sync {
    // Required methods
    fn name(&self) -> &str;
    fn ocr_pdf(
        &self,
        path: &Path,
        config: &DefaultParserOcrConfig,
    ) -> Result<Option<String>>;
}
Expand description

Built-in rich document parser inspired by Kreuzberg’s multi-format extraction model.

This parser handles common binary and containerized document formats and returns plain text suitable for agentic_parse and agentic_search.

Required Methods§

Source

fn name(&self) -> &str

Source

fn ocr_pdf( &self, path: &Path, config: &DefaultParserOcrConfig, ) -> Result<Option<String>>

Implementors§