llmchain 0.1.3

A Rust framework for large language models, inspired by LangChain
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

// Copyright 2023 Shafish Labs.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

use anyhow::Result;

use crate::DocumentSplitter;
use crate::Documents;
use crate::TextSplitter;

pub struct MarkdownSplitter {
    pub splitter_chunk_size: usize,
}

impl MarkdownSplitter {
    pub fn create() -> Self {
        MarkdownSplitter {
            splitter_chunk_size: 400,
        }
    }

    pub fn with_chunk_size(mut self, chunk_size: usize) -> Self {
        self.splitter_chunk_size = chunk_size;
        self
    }
}

impl DocumentSplitter for MarkdownSplitter {
    fn separators(&self) -> Vec<String> {
        vec![
            "\n## ".to_string(),
            "\n### ".to_string(),
            "\n#### ".to_string(),
            "\n##### ".to_string(),
            "\n###### ".to_string(),
        ]
    }

    fn split_documents(&self, documents: &Documents) -> Result<Documents> {
        let text_splitter = TextSplitter::create()
            .with_chunk_size(self.splitter_chunk_size)
            .with_separators(self.separators());
        text_splitter.split_documents(documents)
    }
}