Class: Ragnar::UmapTransformService

Inherits:
Object
  • Object
show all
Defined in:
lib/ragnar/umap_transform_service.rb

Overview

Service for applying UMAP transformations to embeddings Separates transformation logic from training (UmapProcessor)

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(model_path: "umap_model.bin", database:) ⇒ UmapTransformService

Returns a new instance of UmapTransformService.



10
11
12
13
14
15
# File 'lib/ragnar/umap_transform_service.rb', line 10

def initialize(model_path: "umap_model.bin", database:)
  @model_path = model_path
  @database = database
  @umap_model = nil
  @model_metadata = nil
end

Instance Attribute Details

#databaseObject (readonly)

Returns the value of attribute database.



8
9
10
# File 'lib/ragnar/umap_transform_service.rb', line 8

def database
  @database
end

#model_pathObject (readonly)

Returns the value of attribute model_path.



8
9
10
# File 'lib/ragnar/umap_transform_service.rb', line 8

def model_path
  @model_path
end

Class Method Details

.instanceObject



201
202
203
# File 'lib/ragnar/umap_transform_service.rb', line 201

def instance
  UmapTransformServiceSingleton.instance
end

Instance Method Details

#check_model_stalenessHash

Check if model needs retraining based on staleness

Returns:

  • (Hash)

    Staleness info with :needs_retraining, :coverage_percentage



131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
# File 'lib/ragnar/umap_transform_service.rb', line 131

def check_model_staleness
  return { needs_retraining: true, coverage_percentage: 0, reason: "No model exists" } unless model_exists?
  
   = 
  return { needs_retraining: true, coverage_percentage: 0, reason: "No metadata found" } unless 
  
  trained_count = [:document_count] || 0
  current_count = @database.document_count
  
  if current_count == 0
    return { needs_retraining: false, coverage_percentage: 100, reason: "No documents" }
  end
  
  coverage = (trained_count.to_f / current_count * 100).round(1)
  staleness = 100 - coverage
  
  {
    needs_retraining: staleness > 30,
    coverage_percentage: coverage,
    trained_documents: trained_count,
    current_documents: current_count,
    staleness_percentage: staleness,
    reason: staleness > 30 ? "Model covers only #{coverage}% of documents" : "Model is up to date"
  }
end

#model_exists?Boolean

Check if a UMAP model exists

Returns:

  • (Boolean)

    true if model file exists



104
105
106
# File 'lib/ragnar/umap_transform_service.rb', line 104

def model_exists?
  File.exist?(@model_path)
end

#model_metadataHash?

Get metadata about the trained model

Returns:

  • (Hash, nil)

    Model metadata or nil if not found



110
111
112
113
114
115
116
117
118
119
120
# File 'lib/ragnar/umap_transform_service.rb', line 110

def 
  return @model_metadata if @model_metadata
  
   = @model_path.sub(/\.bin$/, '_metadata.json')
  return nil unless File.exist?()
  
  @model_metadata = JSON.parse(File.read(), symbolize_names: true)
rescue => e
  puts "Error loading model metadata: #{e.message}"
  nil
end

#model_versionInteger

Get the version of the current model

Returns:

  • (Integer)

    Model version (timestamp of file modification)



124
125
126
127
# File 'lib/ragnar/umap_transform_service.rb', line 124

def model_version
  return 0 unless File.exist?(@model_path)
  File.mtime(@model_path).to_i
end

#transform_documents(document_ids) ⇒ Hash

Transform embeddings for specific documents

Parameters:

  • document_ids (Array<Integer>)

    IDs of documents to transform

Returns:

  • (Hash)

    Results with :processed, :skipped, :errors counts



20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
# File 'lib/ragnar/umap_transform_service.rb', line 20

def transform_documents(document_ids)
  return { processed: 0, skipped: 0, errors: 0 } if document_ids.empty?
  
  load_model!
  
  # Fetch documents
  documents = @database.get_documents_by_ids(document_ids)
  
  if documents.empty?
    return { processed: 0, skipped: 0, errors: 0 }
  end
  
  # Extract and validate embeddings
  valid_docs = []
  embeddings_to_transform = []
  skipped_count = 0
  
  documents.each do |doc|
    emb = doc[:embedding]
    
    if emb.nil? || !emb.is_a?(Array) || emb.empty?
      skipped_count += 1
      next
    end
    
    if emb.any? { |v| !v.is_a?(Numeric) || v.nan? || !v.finite? }
      skipped_count += 1
      next
    end
    
    valid_docs << doc
    embeddings_to_transform << emb
  end
  
  return { processed: 0, skipped: skipped_count, errors: 0 } if embeddings_to_transform.empty?
  
  # Transform using UMAP
  begin
    reduced_embeddings = @umap_model.transform(embeddings_to_transform)
    
    # Prepare updates
    updates = valid_docs.zip(reduced_embeddings).map do |doc, reduced_emb|
      {
        id: doc[:id],
        reduced_embedding: reduced_emb,
        umap_version: model_version
      }
    end
    
    # Update database
    @database.update_reduced_embeddings(updates)
    
    { processed: updates.size, skipped: skipped_count, errors: 0 }
  rescue => e
    puts "Error transforming documents: #{e.message}"
    { processed: 0, skipped: skipped_count, errors: valid_docs.size }
  end
end

#transform_query(embedding) ⇒ Array<Float>?

Transform a single query embedding

Parameters:

  • embedding (Array<Numeric>)

    Query embedding to transform

Returns:

  • (Array<Float>, nil)

    Reduced embedding or nil if error



82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
# File 'lib/ragnar/umap_transform_service.rb', line 82

def transform_query(embedding)
  return nil if embedding.nil? || !embedding.is_a?(Array) || embedding.empty?
  
  # Validate embedding
  if embedding.any? { |v| !v.is_a?(Numeric) || v.nan? || !v.finite? }
    puts "Warning: Invalid query embedding (contains NaN or Infinity)"
    return nil
  end
  
  load_model!
  
  begin
    # Transform returns array of arrays, get first (and only) result
    @umap_model.transform([embedding]).first
  rescue => e
    puts "Error transforming query: #{e.message}"
    nil
  end
end