OmniAI::Google

A Google implementation of the OmniAI APIs.

Installation

gem install omniai-google

Usage

Client

A client is setup as follows if ENV['GOOGLE_API_KEY'] exists:

client = OmniAI::Google::Client.new

A client may also be passed the following options:

• api_key (required - default is ENV['GOOGLE_API_KEY'])

• credentials (optional)

• host (optional)

• version (optional - options are v1 or v1beta)

Configuration

Vertex AI and Google AI offer different options for interacting w/ Google’s AI APIs. Checkout the Vertex AI and Google AI differences to determine which option best fits your requirements.

Authentication

w/ api_key

The quickest way to authenticate (available if using Google AI) is by using an API key:

OmniAI::Google.configure do |config|
  config.api_key = 'sk-...' # default: ENV['GOOGLE_API_KEY']
end

w/ credentials

An alternative approach for authentication (required if using Vertex AI) is to use credentials directly:

require 'googleauth'

credentials = Google::Auth::ServiceAccountCredentials.make_creds(
  json_key_io: File.open('credentials.json'),
  scope: 'https://www.googleapis.com/auth/cloud-platform'
)

OmniAI::Google.configure do |config|
  config.credentials = credentials
end

Host

The host (defaults to https://generativelanguage.googleapis.com) may be changed (required if using Vertex AI) using:

OmniAI::Google.configure do |config|
  config.host = 'https://us-east4-aiplatform.googleapis.com' # see https://cloud.google.com/vertex-ai/docs/general/locations
end

Version

The version (defaults to v1beta) may be changed using:

OmniAI::Google.configure do |config|
  # ...
  config.version = OmniAI::Google::Config::Version::STABLE # see https://ai.google.dev/gemini-api/docs/api-versions
end

The default API version is configured to v1beta instead of v1 due to various missing features in v1.

Chat

A chat completion is generated by passing in a simple text prompt:

completion = client.chat('Tell me a joke!')
completion.text # 'Why did the chicken cross the road? To get to the other side.'

A chat completion may also be generated by using the prompt builder:

completion = client.chat do |prompt|
  prompt.system('Your are an expert in geography.')
  prompt.user('What is the capital of Canada?')
end
completion.text # 'The capital of Canada is Ottawa.'

Model

model takes an optional string (default is gemini-1.5-pro):

completion = client.chat('How fast is a cheetah?', model: OmniAI::Google::Chat::Model::GEMINI_FLASH)
completion.text # 'A cheetah can reach speeds over 100 km/h.'

API Reference model

Temperature

temperature takes an optional float between 0.0 and 2.0:

completion = client.chat('Pick a number between 1 and 5', temperature: 2.0)
completion.text # '3'

API Reference temperature

Stream

stream takes an optional a proc to stream responses in real-time chunks instead of waiting for a complete response:

stream = proc do |chunk|
  print(chunk.text) # 'Better', 'three', 'hours', ...
end
client.chat('Be poetic.', stream:)

Upload

An upload is especially useful when processing audio / image / video / text files. To use:

CAT_URL = 'https://images.unsplash.com/photo-1472491235688-bdc81a63246e?fm=jpg'
DOG_URL = 'https://images.unsplash.com/photo-1517849845537-4d257902454a?fm=jpg'

begin
  cat_upload = client.upload(CAT_URL)
  dog_upload = client.upload(DOG_URL)

  completion = client.chat(stream: $stdout) do |prompt|
    prompt.user do |message|
      message.text 'What are these photos of?'
      message.url(cat_upload.uri, cat_upload.mime_type)
      message.url(dog_upload.uri, dog_upload.mime_type)
    end
  end
ensure
  cat_upload.delete!
  dog_upload.delete!
end

API Reference stream

Embed

Text can be converted into a vector embedding for similarity comparison usage via:

response = client.embed('The quick brown fox jumps over a lazy dog.')
response.embedding # [0.0, ...]