Class: Parse::Embeddings::Jina

Inherits:
Provider
  • Object
show all
Defined in:
lib/parse/embeddings/jina.rb

Overview

Jina AI embeddings provider. Wraps ‘POST /v1/embeddings`.

Supported text-capable models:

  • **v5 text family** — ‘jina-embeddings-v5-text-small`, `jina-embeddings-v5-text-nano`.

  • **v5 omni family (text mode)** — ‘jina-embeddings-v5-omni-small`, `jina-embeddings-v5-omni-nano`. These models are multimodal at the network boundary but accept plain-text inputs through this provider just like the text-only variants.

  • v4 — ‘jina-embeddings-v4` (Matryoshka, multimodal; text inputs only here).

  • v3 — ‘jina-embeddings-v3` (Matryoshka, 32–1024).

  • **code embeddings** — ‘jina-code-embeddings-0.5b`, `jina-code-embeddings-1.5b`.

Rerankers (‘jina-reranker-*`), VLM (`jina-vlm`), image-only (`jina-clip-v2`), and `ReaderLM-v2` are NOT exposed through this provider — they don’t fit the ‘embed_text` contract. They’ll surface through forthcoming ‘embed_image` / rerank / generation hooks.

Asymmetric input types

Jina uses a ‘task` request field with the following canonical values (mapped from SDK-canonical `input_type:` Symbols):

  • ‘:search_query` → `“retrieval.query”`

  • ‘:search_document` → `“retrieval.passage”`

  • ‘:classification` → `“classification”`

  • ‘:clustering` → `“separation”`

The ‘Provider#supports_input_type?` flag returns `true` here so cache-keying middleware can branch on it. Code-embedding models accept the `task` field and use it to bias the head.

Matryoshka dimensions

‘jina-embeddings-v3`, `jina-embeddings-v4`, and the v5 family support Matryoshka-style output-width truncation via the `dimensions` request field. Pass `dimensions:` to the constructor to set the desired width (must be ≤ the model’s native width).

Examples:

registration

Parse::Embeddings.register(:jina,
  Parse::Embeddings::Jina.new(
    api_key: ENV.fetch("JINA_API_KEY"),
    model:   "jina-embeddings-v3",
  ))

Defined Under Namespace

Classes: AuthenticationError, BadRequestError, RateLimitError, TransientError

Constant Summary collapse

DEFAULT_BASE_URL = 
"https://api.jina.ai/v1"
DEFAULT_MODEL = 
"jina-embeddings-v3"
DEFAULT_TIMEOUT = 
30
DEFAULT_OPEN_TIMEOUT = 
5
DEFAULT_MAX_RETRIES = 
3
DEFAULT_BATCH_SIZE = 
100
MAX_RESPONSE_BYTES = 
16 * 1024 * 1024
MODEL_DEFAULT_DIMENSIONS =

Native vector widths. The Matryoshka-capable rows allow the caller to truncate via the ‘dimensions:` kwarg.

{
  "jina-embeddings-v5-omni-small" => 1024,
  "jina-embeddings-v5-omni-nano"  => 512,
  "jina-embeddings-v5-text-small" => 1024,
  "jina-embeddings-v5-text-nano"  => 512,
  "jina-embeddings-v4"            => 2048,
  "jina-embeddings-v3"            => 1024,
  "jina-code-embeddings-1.5b"     => 1024,
  "jina-code-embeddings-0.5b"     => 1024,
}.freeze
MODEL_MAX_INPUT_TOKENS = 
{
  "jina-embeddings-v5-omni-small" => 32_000,
  "jina-embeddings-v5-omni-nano"  => 32_000,
  "jina-embeddings-v5-text-small" => 32_000,
  "jina-embeddings-v5-text-nano"  => 32_000,
  "jina-embeddings-v4"            => 32_000,
  "jina-embeddings-v3"            => 8_192,
  "jina-code-embeddings-1.5b"     => 32_000,
  "jina-code-embeddings-0.5b"     => 32_000,
}.freeze
MATRYOSHKA_MODELS =

Models that accept the Matryoshka ‘dimensions` field. Other rows must pass the native width or no override.

%w[
  jina-embeddings-v5-omni-small
  jina-embeddings-v5-omni-nano
  jina-embeddings-v5-text-small
  jina-embeddings-v5-text-nano
  jina-embeddings-v4
  jina-embeddings-v3
].freeze
INPUT_TYPE_WIRE_VALUES =

Map SDK-canonical input_type symbols to Jina ‘task` strings.

{
  search_query:    "retrieval.query",
  search_document: "retrieval.passage",
  classification:  "classification",
  clustering:      "separation",
}.freeze

Constants inherited from Provider

Provider::AS_NOTIFICATION_NAME

Instance Method Summary collapse

Methods inherited from Provider

#embed_image, #embed_text_batched, #inspect, #instrument_embed, #modalities, #validate_response!

Constructor Details

#initialize(api_key:, model: DEFAULT_MODEL, dimensions: nil, base_url: DEFAULT_BASE_URL, timeout: DEFAULT_TIMEOUT, open_timeout: DEFAULT_OPEN_TIMEOUT, max_retries: DEFAULT_MAX_RETRIES, embed_batch_size: DEFAULT_BATCH_SIZE, allow_faraday_proxy: false, allow_insecure_base_url: false, connection: nil) ⇒ Jina

Returns a new instance of Jina.

Parameters:

  • api_key (String) —

    required. Sent as ‘Authorization: Bearer …`.

  • model (String) (defaults to: DEFAULT_MODEL) —

    one of MODEL_DEFAULT_DIMENSIONS‘s keys.

  • dimensions (Integer, nil) (defaults to: nil) —

    Matryoshka truncation. Only MATRYOSHKA_MODELS accept this; for others must be nil or equal to the native width.

  • base_url (String) (defaults to: DEFAULT_BASE_URL) —

    override. Must be HTTPS unless ‘allow_insecure_base_url: true`.

  • timeout (Integer) (defaults to: DEFAULT_TIMEOUT) —

    read timeout, seconds.

  • open_timeout (Integer) (defaults to: DEFAULT_OPEN_TIMEOUT) —

    connect timeout, seconds.

  • max_retries (Integer) (defaults to: DEFAULT_MAX_RETRIES) —

    retry attempts on 429/5xx/timeouts.

  • embed_batch_size (Integer) (defaults to: DEFAULT_BATCH_SIZE) —

    inputs per request.

  • allow_faraday_proxy (Boolean) (defaults to: false) —

    opt in to proxy / env-proxy autodiscovery. Defaults ‘false`.

  • allow_insecure_base_url (Boolean) (defaults to: false) —

    permit ‘http://` base.

  • connection (Faraday::Connection, nil) (defaults to: nil) —

    injection seam.



132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
 
# File 'lib/parse/embeddings/jina.rb', line 132

def initialize(
  api_key:,
  model: DEFAULT_MODEL,
  dimensions: nil,
  base_url: DEFAULT_BASE_URL,
  timeout: DEFAULT_TIMEOUT,
  open_timeout: DEFAULT_OPEN_TIMEOUT,
  max_retries: DEFAULT_MAX_RETRIES,
  embed_batch_size: DEFAULT_BATCH_SIZE,
  allow_faraday_proxy: false,
  allow_insecure_base_url: false,
  connection: nil
)
  validate_api_key!(api_key)
  validate_model!(model)
  validate_dimensions!(model, dimensions)
  sanitized_base_url = validate_base_url!(base_url, allow_insecure_base_url)
  validate_positive_integer!(:timeout, timeout)
  validate_positive_integer!(:open_timeout, open_timeout)
  validate_non_negative_integer!(:max_retries, max_retries)
  validate_positive_integer!(:embed_batch_size, embed_batch_size)

  @api_key = api_key
  @model = model
  @dimensions = dimensions || MODEL_DEFAULT_DIMENSIONS.fetch(model)
  @base_url = sanitized_base_url
  @timeout = timeout
  @open_timeout = open_timeout
  @max_retries = max_retries
  @embed_batch_size = embed_batch_size
  @allow_faraday_proxy = allow_faraday_proxy
  @connection = connection || build_connection
end

Instance Method Details

#dimensions ⇒ Object 



166
167
168
 
# File 'lib/parse/embeddings/jina.rb', line 166

def dimensions
  @dimensions
end

#embed_batch_size ⇒ Object 



174
175
176
 
# File 'lib/parse/embeddings/jina.rb', line 174

def embed_batch_size
  @embed_batch_size
end

#embed_text(strings, input_type: :search_document) ⇒ Array<Array<Float>>

Returns vectors aligned 1:1 with ‘strings`.

Parameters:

Returns:

  • (Array<Array<Float>>) —

    vectors aligned 1:1 with ‘strings`.



194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
 
# File 'lib/parse/embeddings/jina.rb', line 194

def embed_text(strings, input_type: :search_document)
  unless strings.is_a?(Array)
    raise ArgumentError,
          "Parse::Embeddings::Jina#embed_text expects Array<String> (got #{strings.class})."
  end
  return [] if strings.empty?
  strings.each_with_index do |s, i|
    unless s.is_a?(String)
      raise ArgumentError,
            "Parse::Embeddings::Jina#embed_text strings[#{i}] is not a String (#{s.class})."
    end
    if s.empty?
      raise ArgumentError,
            "Parse::Embeddings::Jina#embed_text strings[#{i}] is empty; Jina rejects empty inputs."
    end
  end
  unless INPUT_TYPE_WIRE_VALUES.key?(input_type)
    raise ArgumentError,
          "Parse::Embeddings::Jina#embed_text input_type #{input_type.inspect} not in " \
          "#{INPUT_TYPE_WIRE_VALUES.keys.inspect}."
  end
  task_value = INPUT_TYPE_WIRE_VALUES[input_type]

  body = {
    model: @model,
    input: strings,
    task: task_value,
    embedding_type: "float",
  }
  # Forward `dimensions` only for Matryoshka-capable models whose
  # active width differs from native. Sending it to a non-Matryoshka
  # model would yield a 400 from Jina.
  if MATRYOSHKA_MODELS.include?(@model) &&
     @dimensions != MODEL_DEFAULT_DIMENSIONS.fetch(@model)
    body[:dimensions] = @dimensions
  end

  instrument_embed(strings.length, input_type) do |emit_payload|
    payload = post_embeddings(body)
    if payload.is_a?(Hash) && payload["usage"].is_a?(Hash)
      tt = payload["usage"]["total_tokens"]
      emit_payload[:total_tokens] = tt if tt.is_a?(Integer) && tt >= 0
    end
    vectors = extract_vectors!(payload, strings.length)
    validate_response!(strings.length, vectors)
  end
end

#inspect_attrs ⇒ Object 



242
243
244
 
# File 'lib/parse/embeddings/jina.rb', line 242

def inspect_attrs
  super.merge(base: safe_base_host, retries: @max_retries)
end

#max_input_tokens ⇒ Object 



178
179
180
 
# File 'lib/parse/embeddings/jina.rb', line 178

def max_input_tokens
  MODEL_MAX_INPUT_TOKENS[@model]
end

#model_name ⇒ Object 



170
171
172
 
# File 'lib/parse/embeddings/jina.rb', line 170

def model_name
  @model
end

#normalize? ⇒ Boolean

Returns:

  • (Boolean) 


182
183
184
185
 
# File 'lib/parse/embeddings/jina.rb', line 182

def normalize?
  # Jina's v3/v4/v5 embeddings are documented unit-normalized.
  true
end

#supports_input_type? ⇒ Boolean

Returns:

  • (Boolean) 


187
188
189
 
# File 'lib/parse/embeddings/jina.rb', line 187

def supports_input_type?
  true
end