doc_extractor 0.1.0

Extract text chunks from common document formats.
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

mod html;
mod office;
mod pdf;
mod source;
mod text;

use std::io::{Read, Seek};

use super::*;

// modified from https://github.com/Abraxas-365/langchain-rust/tree/v4.6.0/src/document_loaders
pub trait Loader: Send + Sync {
  fn load(self) -> LoaderResult<Vec<Document>>;
  fn load_and_split<TS: TextSplitter + 'static>(self, splitter: TS) -> LoaderResult<Vec<Document>>
  where
    Self: Sized,
  {
    let docs = self.load()?;
    Ok(splitter.split_documents(&docs)?)
  }
}

pub use html::HtmlLoader;
pub use office::OfficeLoader;
pub use pdf::PdfExtractLoader;
pub use source::{LanguageParserOptions, SourceCodeLoader, get_language_by_filename};
pub use text::TextLoader;
pub use url::Url;