class Ollama::Commands::Embed

embed = ollama.embed(model: ‘all-minilm’, input: [‘Why is the sky blue?’, ‘Why is the grass green?’])
@example Generating embeddings for multiple texts
embed = ollama.embed(model: ‘all-minilm’, input: ‘Why is the sky blue?’)
@example Generating embeddings for a single text
embedding requests for generating vector representations of text.
the base command structure and provides the necessary functionality to execute
generates embeddings for text input using a specified model. It inherits from
This class is used to interact with the Ollama API’s embed endpoint, which
A command class that represents the embed API endpoint for Ollama.

def self.path

Returns:
  • (String) - the API endpoint path '/api/embed' for embed requests 
def self.path
  '/api/embed'
end

def initialize(model:, input:, options: nil, truncate: nil, keep_alive: nil, dimensions: nil)

Parameters:
  • dimensions (Integer, nil) -- truncates the output embedding to the specified dimension.
  • keep_alive (String, nil) -- duration to keep the model loaded in memory
  • truncate (Boolean, nil) -- whether to truncate the input if it exceeds context length
  • options (Ollama::Options, nil) -- optional configuration parameters for the model
  • input (String, Array) -- the text input(s) to generate embeddings for
  • model (String) -- the name of the model to use for generating embeddings 
def initialize(model:, input:, options: nil, truncate: nil, keep_alive: nil, dimensions: nil)
  @model, @input, @options, @truncate, @keep_alive, @dimensions =
    model, input, options, truncate, keep_alive, dimensions
  @stream = false
end

def perform(handler)

Returns:
  • (self) - returns the current instance after initiating the request

Parameters:
  • handler (Ollama::Handler) -- the handler object responsible for processing API 
def perform(handler)
  @client.request(method: :post, path: self.class.path, body: to_json, stream:, handler:)
end