baran 0.1.6 → 0.1.7
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/Gemfile.lock +2 -2
- data/README.md +4 -0
- data/lib/baran/text_splitter.rb +3 -0
- 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: c2f275e2741118e6b0505c9f3ae20d195ca082b9338f28dd9e5fee3899b6d3a5
|
|
4
|
+
data.tar.gz: e0eaa0d7e56895c59ab33028f88efd5157a7c091bfb508d35f8cbd19fddf78c1
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 76da807e98e3ee3c8c11146b9fd960ad7e254eb8e185eaabda1cf43b524b63a70916eee29e5b698e6a90fae9ae7c5c638729f5b20299a5842e2a2780b41ce890
|
|
7
|
+
data.tar.gz: ae3d9ff9180cebb6ee57ab85f2c04239497ed0fd7713042cdc30dc3f8ca603457a3554b4ac05e0d7272293a928c27997172bdaa5562443252b8a9b81faf827a4
|
data/Gemfile.lock
CHANGED
data/README.md
CHANGED
|
@@ -1,5 +1,9 @@
|
|
|
1
1
|
# Baran
|
|
2
2
|
|
|
3
|
+
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
|
|
3
7
|
Text Splitter for Large Language Model datasets.
|
|
4
8
|
|
|
5
9
|
To avoid token constraints and improve the accuracy of vector search in the Large Language Model, it is necessary to divide the document. This gem supports splitting the text in the specified manner.
|
data/lib/baran/text_splitter.rb
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
1
|
+
require 'logger'
|
|
2
|
+
|
|
1
3
|
module Baran
|
|
2
4
|
class TextSplitter
|
|
3
5
|
attr_accessor :chunk_size, :chunk_overlap
|
|
@@ -46,6 +48,7 @@ module Baran
|
|
|
46
48
|
|
|
47
49
|
current_splits << split
|
|
48
50
|
total += split.length
|
|
51
|
+
Logger.new(STDOUT).warn("Created a chunk of size #{total}, which is longer than the specified #{@chunk_size}") if total > @chunk_size
|
|
49
52
|
end
|
|
50
53
|
|
|
51
54
|
results << joined(current_splits, separator)
|
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: 0.1.7
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Moeki Kawakami
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2023-
|
|
11
|
+
date: 2023-07-10 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: Text Splitter for Large Language Model Datasets.
|
|
14
14
|
email:
|