documentrix 0.6.0 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ced4bf69e3ae1b4251844dd7915f8d75e72d1c40410f34c14311f70dd55c91f4
-  data.tar.gz: 6fc0799e4559f50a22d211e630ea5f7deaac671f24805f5501c85a11c7a9b853
+  metadata.gz: bd386c4c61e93a3c711116c94d8373b6051d43d46c7387ab86e46e139eaa8c5e
+  data.tar.gz: d4c490c4faf11f0785172cf8e2d70e53e92652edb59261f0579f6a11c3bf92a2
 SHA512:
-  metadata.gz: 8023a4b4d7cad8948e6cbd2a65cefd8b3993ae3de38ae5520a2ebf178989a78efb4c1296b51c614c4066c547372f9ad8067b6c8e196caaa098876a3adf44f523
-  data.tar.gz: 0c4544a80ecde5c98c1d3da64ffeb97155324fdc063993caddf6d2d0780c490b0c8ec24dbc2ca392b3ceb6023d964f58bad099ca4c509a6e43c33c4f7406beb0
+  metadata.gz: 6ccf9b47eeca82500116a7cacb370ba5f2981cc39815b11e7f05c1be826094c0a932ab6226a3436294941af9e63e3be7e1021061f3c4a3a9903422a9b19a9c3d
+  data.tar.gz: 2bd7415288c8a45291c669d7d7012d676770d967d4954184b309f84350e2b13dd741fea4b79130aa1f857aac288b9d4f083dee00b3011d54a15ee0a53c09672e

data/CHANGES.md

@@ -1,5 +1,20 @@
 # Changes
 
+## 2026-09-12 v0.7.0
+
+*   `Documents#initialize`: Changed `model_options` default contract from
+    `Hash` to `#to_h` in YARD docs and normalized with `.to_h` on assignment to
+    ensure `@model_options` is always a `Hash`
+*   `Documents#fetch_embeddings`: Changed `options` keyword default from `nil`
+    to `{}` to avoid passing `nil` to `Ollama::Client#embed`
+*   `Splitters::Semantic#initialize`: Changed `model_options` default from
+    `nil` to `{}`, normalized with `.to_h` on assignment, and updated YARD type
+    from `[Hash, nil]` to `[#to_h]`
+*   Updated `rubygems_version` in `documentrix.gemspec` from **4.0.10** to
+    **4.0.17**
+*   Raised `gem_hadar` development dependency minimum version from **2.17.1**
+    to **2.18.0**
+
 ## 2026-06-17 v0.6.0
 
 ### Changed

data/documentrix.gemspec

@@ -1,9 +1,9 @@
 # -*- encoding: utf-8 -*-
-# stub: documentrix 0.6.0 ruby lib
+# stub: documentrix 0.7.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "documentrix".freeze
-  s.version = "0.6.0".freeze
+  s.version = "0.7.0".freeze
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0".freeze) if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib".freeze]
@@ -17,13 +17,13 @@ Gem::Specification.new do |s|
   s.licenses = ["MIT".freeze]
   s.rdoc_options = ["--title".freeze, "Documentrix - Ruby library for embedding vector database".freeze, "--main".freeze, "README.md".freeze]
   s.required_ruby_version = Gem::Requirement.new(">= 3.1".freeze)
-  s.rubygems_version = "4.0.10".freeze
+  s.rubygems_version = "4.0.17".freeze
   s.summary = "Ruby library for embedding vector database".freeze
   s.test_files = ["spec/documentrix/documents/cache/interface_spec.rb".freeze, "spec/documentrix/documents/cache/memory_cache_spec.rb".freeze, "spec/documentrix/documents/cache/redis_cache_spec.rb".freeze, "spec/documentrix/documents/cache/sqlite_cache_spec.rb".freeze, "spec/documentrix/documents/splitters/character_spec.rb".freeze, "spec/documentrix/documents/splitters/semantic_spec.rb".freeze, "spec/documents_spec.rb".freeze, "spec/spec_helper.rb".freeze, "spec/utils/colorize_texts_spec.rb".freeze, "spec/utils/digests_spec.rb".freeze, "spec/utils/tags_spec.rb".freeze]
 
   s.specification_version = 4
 
-  s.add_development_dependency(%q<gem_hadar>.freeze, [">= 2.17.1".freeze])
+  s.add_development_dependency(%q<gem_hadar>.freeze, [">= 2.18.0".freeze])
   s.add_development_dependency(%q<all_images>.freeze, ["~> 0.12".freeze])
   s.add_development_dependency(%q<rspec>.freeze, ["~> 3.2".freeze])
   s.add_development_dependency(%q<kramdown>.freeze, ["~> 2.0".freeze])

data/lib/documentrix/documents/splitters/semantic.rb

@@ -28,13 +28,13 @@ module Documentrix::Documents::Splitters
     #
     # @param ollama [Ollama::Client] the client used for generating embeddings
     # @param model [String] the embedding model name
-    # @param model_options [Hash, nil] optional parameters passed to the embedding model
+    # @param model_options [#to_h] optional parameters passed to the embedding model
     # @param separator [Regexp] the regex used to identify sentence boundaries
     # @param chunk_size [Integer] the maximum character length of a resulting chunk
     # @param force [Boolean] whether to force split chunks that exceed chunk_size (defaults to false)
-    def initialize(ollama:, model:, model_options: nil, separator: DEFAULT_SEPARATOR, chunk_size: 4096, force: false)
+    def initialize(ollama:, model:, model_options: {}, separator: DEFAULT_SEPARATOR, chunk_size: 4096, force: false)
       @ollama, @model, @model_options, @separator, @chunk_size, @force =
-        ollama, model, model_options, separator, chunk_size, force
+        ollama, model, model_options.to_h, separator, chunk_size, force
     end
 
     # Splits the given text into semantic chunks.

data/lib/documentrix/documents.rb

@@ -69,7 +69,7 @@ class Documentrix::Documents
   #
   # @param ollama [ Ollama::Client ] the client used for embedding
   # @param model [ String ] the name of the model to use for embeddings
-  # @param model_options [ Hash ] optional parameters for the model
+  # @param model_options [ #to_h ] optional parameters for the model
   # @param collection [ Symbol ] the default collection to use (defaults to :default)
   # @param embedding_length [ Integer ] the length of the embeddings (defaults to 1024)
   # @param cache [ Documentrix::Cache ] the cache to use for storing documents (defaults to MemoryCache)
@@ -80,7 +80,7 @@ class Documentrix::Documents
   def initialize(ollama:, model:, model_options: nil, collection: nil, embedding_length: 1_024, cache: MemoryCache, database_filename: nil, redis_url: nil, debug: false, database_busy_timeout: 5000)
     collection ||= default_collection
     @ollama, @model, @model_options, @collection, @debug =
-      ollama, model, model_options, collection.to_sym, debug
+      ollama, model, model_options.to_h, collection.to_sym, debug
     database_filename ||= ':memory:'
     @cache = connect_cache(cache, redis_url, embedding_length, database_filename, database_busy_timeout)
   end
@@ -486,7 +486,7 @@ class Documentrix::Documents
   # @param options [ Hash ] optional parameters for the embedding process
   #
   # @return [ Array<Array<Float>> ] an array containing the embeddings for each input string
-  def fetch_embeddings(model:, input:, options: nil)
+  def fetch_embeddings(model:, input:, options: {})
     @ollama.embed(model:, input:, options:).embeddings
   end
 

data/lib/documentrix/version.rb

@@ -1,6 +1,6 @@
 module Documentrix
   # Documentrix version
-  VERSION         = '0.6.0'
+  VERSION         = '0.7.0'
   VERSION_ARRAY   = VERSION.split('.').map(&:to_i) # :nodoc:
   VERSION_MAJOR   = VERSION_ARRAY[0] # :nodoc:
   VERSION_MINOR   = VERSION_ARRAY[1] # :nodoc:

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: documentrix
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.7.0
 platform: ruby
 authors:
 - Florian Frank
@@ -15,14 +15,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.17.1
+        version: 2.18.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.17.1
+        version: 2.18.0
 - !ruby/object:Gem::Dependency
   name: all_images
   requirement: !ruby/object:Gem::Requirement
@@ -319,7 +319,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.10
+rubygems_version: 4.0.17
 specification_version: 4
 summary: Ruby library for embedding vector database
 test_files: