rrf 0.1.0 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0e291263a6f09f559b804dbcab1332b9b110d0a5ecb6c707d2156ad4583d9873
-  data.tar.gz: 28524ae014e0c0ca2fa8a20f553008b3cf8b6c5e7df6101abeef514e325ab8f3
+  metadata.gz: 8fe716ce7d3ededc96a7f4c2889fedfb47f35dad8421b06fc2612a4c6f15a95b
+  data.tar.gz: c606c5d7cbb1adba77a2c00a4064edce6e5165074fc7386710ac21f9dc8ec338
 SHA512:
-  metadata.gz: 3ba1b4d3d5c593c864ab81824b1236d99e3d2f9ad805c92f15b895504dbad84142de698363664f7ce83a2457ea04c1fc4655ddb7d8dda535b5564f089c9981a9
-  data.tar.gz: d7bf0020c66eb425853e4135cb2c452000c388f190fdf094e41d556b6f4ead73e316d4c5f43893568d3a11b6a1cef47577dec921ba13e78d87b0718a9dcc8e60
+  metadata.gz: 61d01173570a12d1e13242d62f2d265cda4281e50fb0451ebfe7b8b5885cd832b8c1803bbed2053f160c7f0d39c4a870a169369afedd2e00ecf57e0af58f31e9
+  data.tar.gz: 8e53593ac2b6eadfe3c9b39dea093c02ee605fcb319d753fb90790663dfc431078eb3ab6e6c2a4277d426e94595378e195ef7f35325809569d83d7aa336e3152

data/README.md

@@ -44,7 +44,7 @@ end
 
 ### Performing Searches and Fusing Results
 
-You can perform searches using ActiveRecord and Searchkick, and then fuse the results using the fuse method:
+You can perform searches using ActiveRecord and Searchkick, and then fuse the results using the fuse method (the following relies on the [neighbor gem](https://github.com/ankane/neighbor) and the [red-candle gem](https://github.com/assaydepot/red-candle)):
 
 ```ruby
 # Configure the constant value if needed
@@ -53,11 +53,11 @@ RRF.configure do |config|
 end
 
 # Perform Searchkick search
-es_result = Chunk.search("hi", load: false, limit: 50)
+es_result = Chunk.search("alpaca", load: false, limit: 50)
 
 # Perform ActiveRecord nearest neighbor search
-query_embedding = [0.1, 0.2, 0.3, ...] # Example embedding
-ar_result = Chunk.where("body ilike ?", "%hi%").limit(50)
+query_embedding = Candle::Model.new.embedding("alpaca") # You'd want to cache the model in memory
+ar_result = Chunk.all.nearest_neighbors(:embedding768, query_embedding, distance: :cosine).limit(50)
 
 # Fuse the results and limit to 10
 result = Chunk.fuse(ar_result, es_result, limit: 10)
@@ -77,9 +77,40 @@ end
 
 ## Development
 
-After checking out the repo, run bin/setup to install dependencies. Then, run rake spec to run the tests. You can also run bin/console for an interactive prompt that will allow you to experiment.
+After checking out the repo, run 
 
-To install this gem onto your local machine, run bundle exec rake install. To release a new version, update the version number in version.rb, and then run bundle exec rake release, which will create a git tag for the version, push git commits and tags, and push the .gem file to rubygems.org.
+```sh
+bundle install
+```
+
+Then, run 
+
+```sh
+rake spec
+```
+to run the tests.
+
+To install this gem onto your local machine, run 
+
+```sh
+bundle exec rake install
+```
+
+To release a new version, update the version number in version.rb, and then run
+
+```sh
+bundle exec rake release
+```
+
+which will create a git tag for the version, push git commits and tags, and push the .gem file to rubygems.org.
+
+To use this locally during development, I like to include it whatever project I'm working by adding the following to the `Gemfile` of the other project
+
+```ruby
+gem "rrf", path: '/what/ever/path/you/choose/rrf'
+```
+
+Then bundle and it will use your development copy.
 
 ## Contributing
 

data/lib/rrf/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RRF
-  VERSION = "0.1.0"
+  VERSION = "0.1.2"
 end

data/lib/rrf.rb

@@ -48,7 +48,7 @@ module RRF
 
         # Sort by score and limit results
         top_record_ids = record_scores.sort_by { |_id, result| -result[:score] }.to_h.keys.first(limit)
-  
+
         # Load actual records from ActiveRecord
         self.where(id: top_record_ids).index_by(&:id).values_at(*top_record_ids).each do |record|
           record.define_singleton_method(:_rrf_score) { record_scores[record.id][:score] }

data/rrf.gemspec

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+require_relative "lib/rrf/version"
+
+Gem::Specification.new do |spec|
+  spec.name = "rrf"
+  spec.version = RRF::VERSION
+  spec.authors = ["Chris Petersen"]
+  spec.email = ["chris@scientist.com"]
+
+  spec.summary = %q{A Ruby gem for Reciprocal Rank Fusion across different search engines}
+  spec.description = %q{This gem provides an implementation of Reciprocal Rank Fusion (RRF) to merge results from different search engines. Initially supporting Active Record and Elasticsearch.}
+  spec.homepage = "https://github.com/assaydepot/rrf"
+  spec.license = "MIT"
+  spec.required_ruby_version = ">= 2.6.0"
+
+  # spec.metadata["allowed_push_host"] = "TODO: Set to your gem server 'https://example.com'"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+  # spec.metadata["changelog_uri"] = spec.homepage
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(__dir__) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (File.expand_path(f) == __FILE__) ||
+        f.start_with?(*%w[bin/ test/ spec/ features/ .git appveyor Gemfile])
+    end
+  end
+  spec.bindir = "exe"
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  # Uncomment to register a new dependency of your gem
+  # spec.add_dependency "example-gem", "~> 1.0"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "elasticsearch"
+  spec.add_development_dependency "faraday"
+
+  # For more information and examples about making a new gem, check out our
+  # guide at: https://bundler.io/guides/creating_gem.html
+end

metadata

@@ -1,15 +1,56 @@
 --- !ruby/object:Gem::Specification
 name: rrf
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.2
 platform: ruby
 authors:
 - Chris Petersen
-autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-07-16 00:00:00.000000000 Z
-dependencies: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: elasticsearch
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: faraday
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: This gem provides an implementation of Reciprocal Rank Fusion (RRF) to
   merge results from different search engines. Initially supporting Active Record
   and Elasticsearch.
@@ -28,6 +69,7 @@ files:
 - lib/configuration.rb
 - lib/rrf.rb
 - lib/rrf/version.rb
+- rrf.gemspec
 - sig/rrf.rbs
 homepage: https://github.com/assaydepot/rrf
 licenses:
@@ -35,7 +77,6 @@ licenses:
 metadata:
   homepage_uri: https://github.com/assaydepot/rrf
   source_code_uri: https://github.com/assaydepot/rrf
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -50,8 +91,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.3
-signing_key:
+rubygems_version: 3.6.9
 specification_version: 4
 summary: A Ruby gem for Reciprocal Rank Fusion across different search engines
 test_files: []