Class: Ollama::Commands::Embeddings

Inherits:
Object
  • Object
show all
Includes:
DTO
Defined in:
lib/ollama/commands/embeddings.rb

Overview

A command class that represents the embeddings API endpoint for Ollama.

This class is used to interact with the Ollama API's embeddings endpoint, which generates embeddings for text input using a specified model. It inherits from the base command structure and provides the necessary functionality to execute embedding requests for generating vector representations of text.

Examples:

Generating embeddings for a prompt

embeddings = ollama.embeddings(model: 'mxbai-embed-large', prompt: 'The sky is blue because of rayleigh scattering')

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Methods included from DTO

#==, #as_array, #as_array_of_hashes, #as_hash, #as_json, #empty?, #to_json

Constructor Details

#initialize(model:, prompt:, options: nil, keep_alive: nil) ⇒ Embeddings

The initialize method sets up a new instance with streaming disabled.

This method is responsible for initializing a new object instance and configuring it with parameters required for embedding operations. It sets up the model, prompt text, and optional parameters while explicitly disabling streaming since embedding operations are typically non-streaming.

Parameters:

  • model (String)

    the name of the model to use for generating embeddings

  • prompt (String)

    the text prompt to generate embeddings for

  • options (Ollama::Options, nil) (defaults to: nil)

    optional configuration parameters for the model

  • keep_alive (String, nil) (defaults to: nil)

    duration to keep the model loaded in memory



35
36
37
38
# File 'lib/ollama/commands/embeddings.rb', line 35

def initialize(model:, prompt:, options: nil, keep_alive: nil)
  @model, @prompt, @options, @keep_alive, @stream =
    model, prompt, options, keep_alive, false
end

Instance Attribute Details

#client=(value) ⇒ Object (writeonly)

The client attribute writer allows setting the client instance associated with the object.

This method assigns the client that will be used to perform requests and handle responses for this command. It is typically called internally when a command is executed through a client instance.



75
76
77
# File 'lib/ollama/commands/embeddings.rb', line 75

def client=(value)
  @client = value
end

#keep_aliveString? (readonly)

The keep_alive attribute reader returns the keep-alive duration associated with the object.

Returns:

  • (String, nil)

    duration to keep the model loaded in memory



58
59
60
# File 'lib/ollama/commands/embeddings.rb', line 58

def keep_alive
  @keep_alive
end

#modelString (readonly)

The model attribute reader returns the model name associated with the object.

Returns:

  • (String)

    the name of the model used by the command instance



43
44
45
# File 'lib/ollama/commands/embeddings.rb', line 43

def model
  @model
end

#optionsOllama::Options? (readonly)

The options attribute reader returns the model configuration options associated with the object.

Returns:

  • (Ollama::Options, nil)

    optional configuration parameters for the model



53
54
55
# File 'lib/ollama/commands/embeddings.rb', line 53

def options
  @options
end

#promptString (readonly)

The prompt attribute reader returns the text prompt associated with the object.

Returns:

  • (String)

    the text prompt to generate embeddings for



48
49
50
# File 'lib/ollama/commands/embeddings.rb', line 48

def prompt
  @prompt
end

#streamFalseClass (readonly)

The stream attribute reader returns the streaming behavior setting associated with the object.

Returns:

  • (FalseClass)

    the streaming behavior flag, indicating whether streaming is enabled for the command execution (always false for embeddings commands)



65
66
67
# File 'lib/ollama/commands/embeddings.rb', line 65

def stream
  @stream
end

Class Method Details

.pathString

The path method returns the API endpoint path for embeddings requests.

This class method provides the specific URL path used to interact with the Ollama API's embeddings endpoint. It is utilized internally by the command structure to determine the correct API route for generating embeddings.

Returns:

  • (String)

    the API endpoint path '/api/embeddings' for embeddings requests



20
21
22
# File 'lib/ollama/commands/embeddings.rb', line 20

def self.path
  '/api/embeddings'
end

Instance Method Details

#perform(handler) ⇒ self

The perform method executes a command request using the specified handler.

This method initiates a POST request to the Ollama API's embeddings endpoint, utilizing the client instance to send the request and process responses through the provided handler. It handles non-streaming scenarios since embeddings commands do not support streaming.

responses

Parameters:

  • handler (Ollama::Handler)

    the handler object responsible for processing API

Returns:

  • (self)

    returns the current instance after initiating the request



88
89
90
# File 'lib/ollama/commands/embeddings.rb', line 88

def perform(handler)
  @client.request(method: :post, path: self.class.path, body: to_json, stream:, handler:)
end