xberg 1.1.1

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 107 formats and 371 programming languages via tree-sitter code intelligence 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

//! Document-summarisation configuration.
//!
//! When `ExtractionConfig::summarization` is `Some`, the summarisation post-processor
//! runs at the Middle stage and populates
//! [`ExtractedDocument::summary`](crate::types::ExtractedDocument::summary).

use crate::types::summary::SummaryStrategy;
use serde::{Deserialize, Serialize};

/// Configuration for the summarisation post-processor.
#[derive(Debug, Clone, Default, PartialEq, Serialize, Deserialize)]
#[serde(deny_unknown_fields)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
#[cfg_attr(feature = "alef-meta", alef(since = "1.0.0"))]
pub struct SummarizationConfig {
    /// Summarisation strategy.
    #[serde(default)]
    pub strategy: SummaryStrategy,
    /// Maximum summary length in tokens. `None` lets the backend pick a default.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub max_tokens: Option<u32>,
    /// LLM configuration for the abstractive backend. Ignored when
    /// `strategy = Extractive`. Required when `strategy = Abstractive`.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub llm: Option<super::llm::LlmConfig>,
}