kaba 0.1.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7d0d15c1454667339192ecb68a40a0128221f0e2f176c9668fdddbaf6507a143
-  data.tar.gz: 63d4b6088c24453874a2acf9a1c183b6d7468a0297c43cf32feccd0e838f84c0
+  metadata.gz: 73fe981d3fc1a765b78b603f5f04ee8cd23514cc620f601e437363b158362d8b
+  data.tar.gz: bac9dcf38f519286ac2d9d1fd2b24ff3f1c2dabf3a0c85a93b761394f6d13db8
 SHA512:
-  metadata.gz: 0e937f2aea17053fd01b8a4b5f76f61d58d2817eed4e12942f4edaee0ef72b8cf2fc2c3febeb082d49131fad6aba495bfc7385d59bd13c127b8faaa0ad1a7719
-  data.tar.gz: 592a977e7ec2c0b80f76e9f4c9fa0875357466ab1e6cbb05e9dec0fdabe086d8f25fda39caad60d0334ed145a69483ef6ea091d25bc5c39299c9afc5380d6155
+  metadata.gz: 5f60669e92bc3851fe7c481d2271d64cca8cfc1c1e67ffeb2e6ce24c0749171366360b330cfa7e9453e1a30876fbfcdc2c41cd42ef5de97a1a3a31e1000d4f35
+  data.tar.gz: 2139393a5569187cb8d7b5a32d9a641b33f26b93ac0c8b799ac991aad2db965db8d755d23850895af16f95c15518a8b9f6ca58df6d16e1497763c58d0498a071

data/.dockerignore

@@ -0,0 +1,3 @@
+DPodfile
+/data
+.env

data/Dockerfile

@@ -0,0 +1,33 @@
+FROM ruby:3.3-alpine
+
+# Set the working directory to /kaba
+WORKDIR /kaba
+
+# Copy the Gemfile, Gemfile.lock into the container
+COPY Gemfile Gemfile.lock kaba.gemspec ./
+
+# Required in kaba.gemspec
+COPY lib/kaba/version.rb /kaba/lib/kaba/version.rb
+COPY Gemfile /kaba/Gemfile
+COPY Gemfile.lock /kaba/Gemfile.lock
+
+# Install application dependencies
+RUN apk add --no-cache build-base git && bundle install
+
+# Copy the rest of our application code into the container.
+# We do this after bundle install, to avoid having to run bundle
+# every time we do small fixes in the source code.
+COPY . .
+
+# Install the gem locally from the project folder
+RUN gem build kaba.gemspec && \
+    gem install ./kaba-*.gem --no-document
+
+RUN rm -rf /kaba
+
+# Set the working directory to /workdir
+WORKDIR /workdir
+
+# Set the entrypoint to run the installed binary in /workdir
+# Example:  docker run -it -v "$PWD:/workdir" kaba
+ENTRYPOINT ["kaba"]

data/README.md

@@ -1,9 +1,33 @@
 # Kaba
+咔吧是一款数据构建工具，使用 Ruby 完成，使用 typechat 作为核心，目的是构建一款能够比较好适配大模型 sft 数据集的工具，整个项目使用起来只需要安装 docker 即可。
 
-## 目录结构
+> 开源协议：你爱干嘛干嘛
+
+## 安装
+
+如果你有一个 Ruby 环境可用（且 ruby 版本大于 3.3），你可以使用以下命令全局安装 kaba：
+```
+gem install kaba
+```
+
+否则，你可以通过别名运行一个 docker 化版本（将下面的命令添加到你的~/.bashrc、~/.zshrc或类似文件中，以简化重复使用）。
+
+```
+alias kaba='docker run -it --rm -v "${PWD}:/workdir" ghcr.io/mjason/kaba:latest'
+```
+
+## 目录结构说明
+你的项目目录必须有 data 目录
 - data
   - row
+    - *.target.json
+    - *.input.txt
   - schema
+    - *.ts
+
+`*`代表文件名，随你喜欢，一般推荐用数字即可，schema 怎么定义直接看 typechat 文档就好了。
+
+## 关联项目
+- [lisa_typechat_server](https://github.com/mjason/lisa_typechat_server)
 
-## 命令
-`gem install kaba`
+如果要修改服务地址你有两个方式，一个通过 `.env` 来处理，还有就是自己设置环境变量，变量名 `LISA_TYPECHAT_ENDPOINT`

data/exe/kaba

@@ -10,10 +10,14 @@ require 'async/http/faraday'
 require 'json'
 require "kaba"
 
+require 'dotenv'
+Dotenv.load
+
 class Application
   class << self
     def connection
-      @connection ||= Faraday.new('https://lisa-typechat.listenai.com') do |faraday|
+      endpoint = ENV["LISA_TYPECHAT_ENDPOINT"] || "https://lisa-typechat.listenai.com"
+      @connection ||= Faraday.new(endpoint) do |faraday|
         faraday.adapter :async_http, clients: Async::HTTP::Faraday::PersistentClients
         faraday.request :json
       end

data/kaba.gemspec

@@ -36,6 +36,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "async-http-faraday", "~> 0.19.0"
   spec.add_dependency "colorize", "~> 1.1"
   spec.add_dependency "tty-progressbar", "~> 0.18.3"
+  spec.add_dependency "dotenv", "~> 3.1"
 
   # For more information and examples about making a new gem, check out our
   # guide at: https://bundler.io/guides/creating_gem.html

data/lib/kaba/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Kaba
-  VERSION = "0.1.0"
+  VERSION = "0.2.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: kaba
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.1
 platform: ruby
 authors:
 - MJ
@@ -80,6 +80,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.18.3
+- !ruby/object:Gem::Dependency
+  name: dotenv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
 description: 用来做数据集的工具
 email:
 - tywf91@gmail.com
@@ -88,6 +102,8 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- ".dockerignore"
+- Dockerfile
 - README.md
 - Rakefile
 - exe/kaba