kreuzberg 4.6.1

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 88+ formats with async/sync APIs.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

pub mod rtdetr;
pub mod slanet;
pub mod table_classifier;
pub mod tatr;
pub mod yolo;

use image::RgbImage;

use crate::layout::error::LayoutError;
use crate::layout::types::LayoutDetection;

/// Common interface for all layout detection model backends.
pub trait LayoutModel: Send {
    /// Run layout detection on an image using the default confidence threshold.
    fn detect(&mut self, img: &RgbImage) -> Result<Vec<LayoutDetection>, LayoutError>;

    /// Run layout detection with a custom confidence threshold.
    fn detect_with_threshold(&mut self, img: &RgbImage, threshold: f32) -> Result<Vec<LayoutDetection>, LayoutError>;

    /// Run layout detection on a batch of images in a single model call.
    ///
    /// Returns one `Vec<LayoutDetection>` per input image (same order).
    /// `threshold` overrides the model's default confidence cutoff when `Some`.
    ///
    /// The default implementation is a sequential fallback: models that support
    /// true batched inference (e.g. [`rtdetr::RtDetrModel`]) override this.
    fn detect_batch(
        &mut self,
        images: &[&RgbImage],
        threshold: Option<f32>,
    ) -> Result<Vec<Vec<LayoutDetection>>, LayoutError> {
        images
            .iter()
            .map(|img| match threshold {
                Some(t) => self.detect_with_threshold(img, t),
                None => self.detect(img),
            })
            .collect()
    }

    /// Human-readable model name.
    fn name(&self) -> &str;
}