eval-ruby 0.1.0

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.
Files changed (31) hide show
  1. checksums.yaml +7 -0
  2. data/Gemfile +5 -0
  3. data/Gemfile.lock +51 -0
  4. data/LICENSE +21 -0
  5. data/README.md +121 -0
  6. data/Rakefile +11 -0
  7. data/eval-ruby.gemspec +34 -0
  8. data/lib/eval_ruby/comparison.rb +88 -0
  9. data/lib/eval_ruby/configuration.rb +17 -0
  10. data/lib/eval_ruby/dataset.rb +130 -0
  11. data/lib/eval_ruby/evaluator.rb +94 -0
  12. data/lib/eval_ruby/judges/anthropic.rb +40 -0
  13. data/lib/eval_ruby/judges/base.rb +26 -0
  14. data/lib/eval_ruby/judges/openai.rb +39 -0
  15. data/lib/eval_ruby/metrics/base.rb +17 -0
  16. data/lib/eval_ruby/metrics/context_precision.rb +39 -0
  17. data/lib/eval_ruby/metrics/context_recall.rb +40 -0
  18. data/lib/eval_ruby/metrics/correctness.rb +68 -0
  19. data/lib/eval_ruby/metrics/faithfulness.rb +42 -0
  20. data/lib/eval_ruby/metrics/mrr.rb +14 -0
  21. data/lib/eval_ruby/metrics/ndcg.rb +22 -0
  22. data/lib/eval_ruby/metrics/precision_at_k.rb +16 -0
  23. data/lib/eval_ruby/metrics/recall_at_k.rb +16 -0
  24. data/lib/eval_ruby/metrics/relevance.rb +37 -0
  25. data/lib/eval_ruby/minitest.rb +51 -0
  26. data/lib/eval_ruby/report.rb +82 -0
  27. data/lib/eval_ruby/result.rb +37 -0
  28. data/lib/eval_ruby/rspec.rb +70 -0
  29. data/lib/eval_ruby/version.rb +5 -0
  30. data/lib/eval_ruby.rb +94 -0
  31. metadata +128 -0
metadata ADDED
@@ -0,0 +1,128 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: eval-ruby
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Johannes Dwi Cahyo
8
+ bindir: bin
9
+ cert_chain: []
10
+ date: 1980-01-02 00:00:00.000000000 Z
11
+ dependencies:
12
+ - !ruby/object:Gem::Dependency
13
+ name: csv
14
+ requirement: !ruby/object:Gem::Requirement
15
+ requirements:
16
+ - - ">="
17
+ - !ruby/object:Gem::Version
18
+ version: '0'
19
+ type: :runtime
20
+ prerelease: false
21
+ version_requirements: !ruby/object:Gem::Requirement
22
+ requirements:
23
+ - - ">="
24
+ - !ruby/object:Gem::Version
25
+ version: '0'
26
+ - !ruby/object:Gem::Dependency
27
+ name: minitest
28
+ requirement: !ruby/object:Gem::Requirement
29
+ requirements:
30
+ - - "~>"
31
+ - !ruby/object:Gem::Version
32
+ version: '5.0'
33
+ type: :development
34
+ prerelease: false
35
+ version_requirements: !ruby/object:Gem::Requirement
36
+ requirements:
37
+ - - "~>"
38
+ - !ruby/object:Gem::Version
39
+ version: '5.0'
40
+ - !ruby/object:Gem::Dependency
41
+ name: rake
42
+ requirement: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - "~>"
45
+ - !ruby/object:Gem::Version
46
+ version: '13.0'
47
+ type: :development
48
+ prerelease: false
49
+ version_requirements: !ruby/object:Gem::Requirement
50
+ requirements:
51
+ - - "~>"
52
+ - !ruby/object:Gem::Version
53
+ version: '13.0'
54
+ - !ruby/object:Gem::Dependency
55
+ name: webmock
56
+ requirement: !ruby/object:Gem::Requirement
57
+ requirements:
58
+ - - "~>"
59
+ - !ruby/object:Gem::Version
60
+ version: '3.0'
61
+ type: :development
62
+ prerelease: false
63
+ version_requirements: !ruby/object:Gem::Requirement
64
+ requirements:
65
+ - - "~>"
66
+ - !ruby/object:Gem::Version
67
+ version: '3.0'
68
+ description: Measures quality metrics like faithfulness, relevance, context precision,
69
+ and answer correctness for LLM and RAG applications. Think Ragas or DeepEval for
70
+ Ruby.
71
+ executables: []
72
+ extensions: []
73
+ extra_rdoc_files: []
74
+ files:
75
+ - Gemfile
76
+ - Gemfile.lock
77
+ - LICENSE
78
+ - README.md
79
+ - Rakefile
80
+ - eval-ruby.gemspec
81
+ - lib/eval_ruby.rb
82
+ - lib/eval_ruby/comparison.rb
83
+ - lib/eval_ruby/configuration.rb
84
+ - lib/eval_ruby/dataset.rb
85
+ - lib/eval_ruby/evaluator.rb
86
+ - lib/eval_ruby/judges/anthropic.rb
87
+ - lib/eval_ruby/judges/base.rb
88
+ - lib/eval_ruby/judges/openai.rb
89
+ - lib/eval_ruby/metrics/base.rb
90
+ - lib/eval_ruby/metrics/context_precision.rb
91
+ - lib/eval_ruby/metrics/context_recall.rb
92
+ - lib/eval_ruby/metrics/correctness.rb
93
+ - lib/eval_ruby/metrics/faithfulness.rb
94
+ - lib/eval_ruby/metrics/mrr.rb
95
+ - lib/eval_ruby/metrics/ndcg.rb
96
+ - lib/eval_ruby/metrics/precision_at_k.rb
97
+ - lib/eval_ruby/metrics/recall_at_k.rb
98
+ - lib/eval_ruby/metrics/relevance.rb
99
+ - lib/eval_ruby/minitest.rb
100
+ - lib/eval_ruby/report.rb
101
+ - lib/eval_ruby/result.rb
102
+ - lib/eval_ruby/rspec.rb
103
+ - lib/eval_ruby/version.rb
104
+ homepage: https://github.com/johannesdwicahyo/eval-ruby
105
+ licenses:
106
+ - MIT
107
+ metadata:
108
+ homepage_uri: https://github.com/johannesdwicahyo/eval-ruby
109
+ source_code_uri: https://github.com/johannesdwicahyo/eval-ruby
110
+ changelog_uri: https://github.com/johannesdwicahyo/eval-ruby/blob/main/CHANGELOG.md
111
+ rdoc_options: []
112
+ require_paths:
113
+ - lib
114
+ required_ruby_version: !ruby/object:Gem::Requirement
115
+ requirements:
116
+ - - ">="
117
+ - !ruby/object:Gem::Version
118
+ version: 3.1.0
119
+ required_rubygems_version: !ruby/object:Gem::Requirement
120
+ requirements:
121
+ - - ">="
122
+ - !ruby/object:Gem::Version
123
+ version: '0'
124
+ requirements: []
125
+ rubygems_version: 3.6.9
126
+ specification_version: 4
127
+ summary: Evaluation framework for LLM and RAG applications in Ruby
128
+ test_files: []