Last updated May 10, 2025

The Cohere Embed Multilingual (cohere-embed-multilingual) model generates vector embeddings (lists of numbers) for provided text inputs. These embeddings can be used in various applications, such as search, classification, and clustering. This guide shows how to access the v1-embeddings API using Ruby.

Prerequisites

1. If it’s not already installed, install the Heroku CLI. Then install the Heroku AI plugin:

   heroku plugins:install @heroku/plugin-ai
   

2. Attach the embedding model to an app of yours:

   # If you don't have an app yet, you can create one with:
   heroku create $APP_NAME # specify the name you want for your app (or skip this step to use an existing app you have)
   
   # Create and attach the embedding model to your app, $APP_NAME.
   heroku ai:models:create -a $APP_NAME cohere-multilingual --as EMBEDDING
   

Ruby Example Code

# frozen_string_literal: true

require 'net/http'
require 'json'
require 'uri'

EMBEDDING_URL = ENV.fetch('EMBEDDING_URL') do
  raise <<~ERROR
    Environment variable 'EMBEDDING_URL' is missing.
    Set it using:
      export EMBEDDING_URL=$(heroku config:get -a $APP_NAME EMBEDDING_URL)
  ERROR
end

EMBEDDING_KEY = ENV.fetch('EMBEDDING_KEY') do
  raise <<~ERROR
    Environment variable 'EMBEDDING_KEY' is missing.
    Set it using:
      export EMBEDDING_KEY=$(heroku config:get -a $APP_NAME EMBEDDING_KEY)
  ERROR
end

EMBEDDING_MODEL_ID = ENV.fetch('EMBEDDING_MODEL_ID') do
  raise <<~ERROR
    Environment variable 'EMBEDDING_MODEL_ID' is missing.
    Set it using:
      export EMBEDDING_MODEL_ID=$(heroku config:get -a $APP_NAME EMBEDDING_MODEL_ID)
  ERROR
end

##
# Parses and prints the API response for the embedding request.
#
# @param response [Net::HTTPResponse] The response object from the API call.
def parse_embedding_output(response)
  if response.is_a?(Net::HTTPSuccess)
    result = JSON.parse(response.body)
    puts "Embeddings: #{result['data']}"
  else
    puts "Request failed: #{response.code}, #{response.body}"
  end
end

##
# Generates embeddings using the Stability AI Embeddings model.
#
# @param payload [Hash] Hash containing parameters for the embedding generation.
def generate_embeddings(payload)
  uri = URI.join(EMBEDDING_URL, '/v1/embeddings')
  request = Net::HTTP::Post.new(uri)
  request['Authorization'] = "Bearer #{EMBEDDING_KEY}"
  request['Content-Type']  = 'application/json'
  request.body             = payload.to_json

  response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == 'https') do |http|
    http.request(request)
  end

  parse_embedding_output(response)
end

# Example payload
payload = {
  model: EMBEDDING_MODEL_ID,
  input: [
    'Hello, I am a blob of text.',
    "How's the weather in Portland?"
  ],
  input_type: 'search_document',
  truncate: 'END',
  encoding_format: 'float'
}

# Generate embeddings with the given payload
generate_embeddings(payload)