cephalon 0.0.10

A library to extract information from documents, and feed it into vector database to create robust knowledge-base assistant.
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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61

pub mod models;
pub mod documents;
pub mod database;


#[cfg(not(feature="no-ml"))]
pub mod knowledge_base;


/*
IMPORTANT: PLEASE NOTE
Using the no-ml feature will ignore code written in the knowledge_base.rs, models directory, and some code in main.rs 
To ensure proper testing please use "cargo test --all-features" command

 */


use documents::document::{
    split_text_into_chunks,
    get_text_from_pdf,
    get_text_from_docx,
    get_text_from_txt
};

#[cfg(not(feature="no-ml"))]
use models::model::{
    encode_text
};

pub fn add(left: usize, right: usize) -> usize {
    left + right
}


#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn it_works() {
        let result = add(2, 2);
        assert_eq!(result, 4);
    }

    #[test]
    fn split_text_into_chunks_test(){
        let result = split_text_into_chunks("Split this test please!!".to_string(), 5).unwrap();
        assert_eq!(result,vec!["Split"," this", " test"," plea","se!!"]);
    }    

    #[cfg(not(feature="no-ml"))]
    #[test]
    fn encode_text_test(){
        let sentence = "This is a sentence that will be embedded!".to_string();
        let start_time = std::time::Instant::now();
        let _model_name = "all-MiniLM-L6-v2".to_string();
        let _result = encode_text(&vec![sentence]);
        println!("Time to generate embeddings: {:?}",start_time.elapsed());
    }

}