Class: DSPy::Image

Inherits:
Object
  • Object
show all
Defined in:
lib/dspy/image.rb

Constant Summary collapse

SUPPORTED_FORMATS = 
%w[image/jpeg image/png image/gif image/webp].freeze
MAX_SIZE_BYTES =

5MB limit

5 * 1024 * 1024
PROVIDER_CAPABILITIES =

Provider capability registry

{
  'openai' => {
    sources: %w[url base64 data],
    parameters: %w[detail]
  },
  'anthropic' => {
    sources: %w[base64 data], 
    parameters: []
  },
  'gemini' => {
    sources: %w[base64 data], # Gemini supports inline base64 data, not URLs
    parameters: []
  }
}.freeze

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(url: nil, base64: nil, data: nil, content_type: nil, detail: nil) ⇒ Image

Returns a new instance of Image.



29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
 
# File 'lib/dspy/image.rb', line 29

def initialize(url: nil, base64: nil, data: nil, content_type: nil, detail: nil)
  @detail = detail # OpenAI detail level: 'low', 'high', or 'auto'
  
  # Validate input
  validate_input!(url, base64, data)
  
  if url
    @url = url
    @content_type = content_type || infer_content_type_from_url(url)
  elsif base64
    raise ArgumentError, "content_type is required when using base64" unless content_type
    @base64 = base64
    @content_type = content_type
    validate_size!(Base64.decode64(base64).bytesize)
  elsif data
    raise ArgumentError, "content_type is required when using data" unless content_type
    @data = data
    @content_type = content_type
    validate_size!(data.size)
  end
  
  validate_content_type!
end

Instance Attribute Details

#base64 ⇒ Object (readonly)

Returns the value of attribute base64.



8
9
10
 
# File 'lib/dspy/image.rb', line 8

def base64
  @base64
end

#content_type ⇒ Object (readonly)

Returns the value of attribute content_type.



8
9
10
 
# File 'lib/dspy/image.rb', line 8

def content_type
  @content_type
end

#data ⇒ Object (readonly)

Returns the value of attribute data.



8
9
10
 
# File 'lib/dspy/image.rb', line 8

def data
  @data
end

#detail ⇒ Object (readonly)

Returns the value of attribute detail.



8
9
10
 
# File 'lib/dspy/image.rb', line 8

def detail
  @detail
end

#url ⇒ Object (readonly)

Returns the value of attribute url.



8
9
10
 
# File 'lib/dspy/image.rb', line 8

def url
  @url
end

Instance Method Details

#to_anthropic_format ⇒ Object 



80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/dspy/image.rb', line 80

def to_anthropic_format
  if url
    # Anthropic requires base64, so we'd need to fetch the URL
    # For now, we'll raise an error or skip
    raise NotImplementedError, "URL fetching for Anthropic not yet implemented"
  elsif base64
    {
      type: 'image',
      source: {
        type: 'base64',
        media_type: content_type,
        data: base64
      }
    }
  elsif data
    {
      type: 'image',
      source: {
        type: 'base64',
        media_type: content_type,
        data: to_base64
      }
    }
  end
end

#to_base64 ⇒ Object 



127
128
129
130
131
 
# File 'lib/dspy/image.rb', line 127

def to_base64
  return base64 if base64
  return Base64.strict_encode64(data.pack('C*')) if data
  nil
end

#to_gemini_format ⇒ Object 



106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
 
# File 'lib/dspy/image.rb', line 106

def to_gemini_format
  if url
    # Gemini requires base64 for inline data, URLs not supported for inline_data
    raise NotImplementedError, "URL fetching for Gemini not yet implemented. Use base64 or data instead."
  elsif base64
    {
      inline_data: {
        mime_type: content_type,
        data: base64
      }
    }
  elsif data
    {
      inline_data: {
        mime_type: content_type,
        data: to_base64
      }
    }
  end
end

#to_openai_format ⇒ Object 



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
78
 
# File 'lib/dspy/image.rb', line 53

def to_openai_format
  if url
    format = {
      type: 'image_url',
      image_url: {
        url: url
      }
    }
    format[:image_url][:detail] = detail if detail
    format
  elsif base64
    {
      type: 'image_url',
      image_url: {
        url: "data:#{content_type};base64,#{base64}"
      }
    }
  elsif data
    {
      type: 'image_url',
      image_url: {
        url: "data:#{content_type};base64,#{to_base64}"
      }
    }
  end
end

#validate! ⇒ Object 



133
134
135
136
137
138
139
140
141
 
# File 'lib/dspy/image.rb', line 133

def validate!
  validate_content_type!
  
  if base64
    validate_size!(Base64.decode64(base64).bytesize)
  elsif data
    validate_size!(data.size)
  end
end

#validate_for_provider!(provider) ⇒ Object 



143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
 
# File 'lib/dspy/image.rb', line 143

def validate_for_provider!(provider)
  capabilities = PROVIDER_CAPABILITIES[provider]
  
  unless capabilities
    raise DSPy::LM::IncompatibleImageFeatureError, 
          "Unknown provider '#{provider}'. Supported providers: #{PROVIDER_CAPABILITIES.keys.join(', ')}"
  end
  
  # Check source compatibility
  current_source = if url
                     'url'
                   elsif base64
                     'base64'
                   elsif data
                     'data'
                   end
  
  unless capabilities[:sources].include?(current_source)
    case provider
    when 'anthropic'
      if current_source == 'url'
        raise DSPy::LM::IncompatibleImageFeatureError,
              "Anthropic doesn't support image URLs. Please provide base64 or raw data instead."
      end
    when 'gemini'
      if current_source == 'url'
        raise DSPy::LM::IncompatibleImageFeatureError,
              "Gemini doesn't support image URLs for inline data. Please provide base64 or raw data instead."
      end
    end
  end
  
  # Check parameter compatibility
  if detail && !capabilities[:parameters].include?('detail')
    case provider
    when 'anthropic'
      raise DSPy::LM::IncompatibleImageFeatureError,
            "Anthropic doesn't support the 'detail' parameter. This feature is OpenAI-specific."
    when 'gemini'
      raise DSPy::LM::IncompatibleImageFeatureError,
            "Gemini doesn't support the 'detail' parameter. This feature is OpenAI-specific."
    end
  end
end