baran 0.1.9 → 0.1.11
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +5 -2
- data/Gemfile +1 -1
- data/Gemfile.lock +3 -3
- data/README.md +6 -6
- data/lib/baran/markdown_splitter.rb +3 -3
- data/lib/baran/version.rb +1 -1
- metadata +2 -2
    
        checksums.yaml
    CHANGED
    
    | @@ -1,7 +1,7 @@ | |
| 1 1 | 
             
            ---
         | 
| 2 2 | 
             
            SHA256:
         | 
| 3 | 
            -
              metadata.gz:  | 
| 4 | 
            -
              data.tar.gz:  | 
| 3 | 
            +
              metadata.gz: 95a0c57558fc237d12ab005d24e444381725f8ddbb1fbbfe1ee730f9e14384ba
         | 
| 4 | 
            +
              data.tar.gz: a7eacd8e62b27478df98aaaf534a6b37348696d2baa78e67c5781891c1b74c03
         | 
| 5 5 | 
             
            SHA512:
         | 
| 6 | 
            -
              metadata.gz:  | 
| 7 | 
            -
              data.tar.gz:  | 
| 6 | 
            +
              metadata.gz: f09dd858f1dee1189ee543b440e8196871129fe33b6558762aedc85a1c9a26aebb1e439ff7c9b9e52bb0d92f6b1ffff37207105a146928c9350b26ed949019cd
         | 
| 7 | 
            +
              data.tar.gz: 59ec6d83b1b7ce85e005dee095e8baf087ffffef750851a661957b431ef346521d75661cd266cf81e889eae64966b4876b3b8031ce43987fead5c2678437aace
         | 
    
        data/CHANGELOG.md
    CHANGED
    
    
    
        data/Gemfile
    CHANGED
    
    
    
        data/Gemfile.lock
    CHANGED
    
    | @@ -1,12 +1,12 @@ | |
| 1 1 | 
             
            PATH
         | 
| 2 2 | 
             
              remote: .
         | 
| 3 3 | 
             
              specs:
         | 
| 4 | 
            -
                baran (0.1. | 
| 4 | 
            +
                baran (0.1.11)
         | 
| 5 5 |  | 
| 6 6 | 
             
            GEM
         | 
| 7 7 | 
             
              remote: https://rubygems.org/
         | 
| 8 8 | 
             
              specs:
         | 
| 9 | 
            -
                minitest (5. | 
| 9 | 
            +
                minitest (5.21.2)
         | 
| 10 10 | 
             
                rake (13.0.6)
         | 
| 11 11 |  | 
| 12 12 | 
             
            PLATFORMS
         | 
| @@ -15,7 +15,7 @@ PLATFORMS | |
| 15 15 |  | 
| 16 16 | 
             
            DEPENDENCIES
         | 
| 17 17 | 
             
              baran!
         | 
| 18 | 
            -
              minitest (~> 5. | 
| 18 | 
            +
              minitest (~> 5.21)
         | 
| 19 19 | 
             
              rake (~> 13.0)
         | 
| 20 20 |  | 
| 21 21 | 
             
            BUNDLED WITH
         | 
    
        data/README.md
    CHANGED
    
    | @@ -35,8 +35,8 @@ splitter = Baran::CharacterTextSplitter.new( | |
| 35 35 | 
             
                chunk_overlap: 64,
         | 
| 36 36 | 
             
                separator: "\n\n"
         | 
| 37 37 | 
             
            )
         | 
| 38 | 
            -
            splitter.chunks(text)
         | 
| 39 | 
            -
            # => [{ cursor: 0, text: "..." }, ...]
         | 
| 38 | 
            +
            splitter.chunks(text, metadata: { ... })
         | 
| 39 | 
            +
            # => [{ cursor: 0, text: "...", metadata: { ... } }, ...]
         | 
| 40 40 | 
             
            ```
         | 
| 41 41 |  | 
| 42 42 | 
             
            ### Recursive Character Text Splitter
         | 
| @@ -47,8 +47,8 @@ Splitting by the specified characters recursively. | |
| 47 47 | 
             
            splitter = Baran::RecursiveCharacterTextSplitter.new(
         | 
| 48 48 | 
             
                separators: ["\n\n", "\n", " ", ""]
         | 
| 49 49 | 
             
            )
         | 
| 50 | 
            -
            splitter.chunks(text)
         | 
| 51 | 
            -
            # => [{ cursor: 0, text: "..." }, ...]
         | 
| 50 | 
            +
            splitter.chunks(text, metadata: { ... })
         | 
| 51 | 
            +
            # => [{ cursor: 0, text: "...", metadata: { ... } }, ...]
         | 
| 52 52 | 
             
            ```
         | 
| 53 53 |  | 
| 54 54 | 
             
            ### Markdown Text Splitter
         | 
| @@ -57,8 +57,8 @@ Splitting by the Markdown descriptions. | |
| 57 57 |  | 
| 58 58 | 
             
            ```ruby
         | 
| 59 59 | 
             
            splitter = Baran::MarkdownSplitter.new
         | 
| 60 | 
            -
            splitter.chunks(markdown)
         | 
| 61 | 
            -
            # => [{ cursor: 0, text: "..." }, ...]
         | 
| 60 | 
            +
            splitter.chunks(markdown, metadata: { ... })
         | 
| 61 | 
            +
            # => [{ cursor: 0, text: "...", metadata: { ... } }, ...]
         | 
| 62 62 | 
             
            ```
         | 
| 63 63 |  | 
| 64 64 | 
             
            Split with the following priority.
         | 
| @@ -3,7 +3,7 @@ require_relative './recursive_character_text_splitter' | |
| 3 3 | 
             
            module Baran
         | 
| 4 4 | 
             
              class MarkdownSplitter < RecursiveCharacterTextSplitter
         | 
| 5 5 | 
             
                def initialize(chunk_size: 1024, chunk_overlap: 64)
         | 
| 6 | 
            -
                   | 
| 6 | 
            +
                  separators = [
         | 
| 7 7 | 
             
                    "\n# ", # h1
         | 
| 8 8 | 
             
                    "\n## ", # h2
         | 
| 9 9 | 
             
                    "\n### ", # h3
         | 
| @@ -19,7 +19,7 @@ module Baran | |
| 19 19 | 
             
                    " ", # space
         | 
| 20 20 | 
             
                    "" # empty
         | 
| 21 21 | 
             
                  ]
         | 
| 22 | 
            -
                  super(chunk_size: chunk_size, chunk_overlap: chunk_overlap)
         | 
| 22 | 
            +
                  super(chunk_size: chunk_size, chunk_overlap: chunk_overlap, separators: separators)
         | 
| 23 23 | 
             
                end
         | 
| 24 24 | 
             
              end
         | 
| 25 | 
            -
            end
         | 
| 25 | 
            +
            end
         | 
    
        data/lib/baran/version.rb
    CHANGED
    
    
    
        metadata
    CHANGED
    
    | @@ -1,14 +1,14 @@ | |
| 1 1 | 
             
            --- !ruby/object:Gem::Specification
         | 
| 2 2 | 
             
            name: baran
         | 
| 3 3 | 
             
            version: !ruby/object:Gem::Version
         | 
| 4 | 
            -
              version: 0.1. | 
| 4 | 
            +
              version: 0.1.11
         | 
| 5 5 | 
             
            platform: ruby
         | 
| 6 6 | 
             
            authors:
         | 
| 7 7 | 
             
            - Moeki Kawakami
         | 
| 8 8 | 
             
            autorequire:
         | 
| 9 9 | 
             
            bindir: exe
         | 
| 10 10 | 
             
            cert_chain: []
         | 
| 11 | 
            -
            date:  | 
| 11 | 
            +
            date: 2024-03-09 00:00:00.000000000 Z
         | 
| 12 12 | 
             
            dependencies: []
         | 
| 13 13 | 
             
            description: Text Splitter for Large Language Model Datasets.
         | 
| 14 14 | 
             
            email:
         |