OmniAI::OpenAI
An OpenAI implementation of the OmniAI interface supporting ChatGPT, Whisper, Text-to-Voice, Voice-to-Text, and more. This library is community maintained.
Installation
gem install omniai-openai
Usage
Client
A client is setup as follows if ENV['OPENAI_API_KEY']
exists:
client = OmniAI::OpenAI::Client.new
A client may also be passed the following options:
api_key
(required - default isENV['OPENAI_API_KEY']
)organization
(optional)project
(optional)host
(optional) useful for usage with Ollama or LocalAI
Configuration
Global configuration is supported for the following options:
OmniAI::OpenAI.configure do |config|
config.api_key = 'sk-...' # default: ENV['OPENAI_API_KEY']
config.organization = '...' # default: ENV['OPENAI_ORGANIZATION']
config.project = '...' # default: ENV['OPENAI_PROJECT']
config.host = '...' # default: 'https://api.openai.com' - override for usage with LocalAI / Ollama
end
Usage with LocalAI
LocalAI offers built in compatability with the OpenAI specification. To initialize a client that points to a Ollama change the host accordingly:
client = OmniAI::OpenAI::Client.new(host: 'http://localhost:8080', api_key: nil)
For details on installation or running LocalAI see the getting started tutorial.
Usage with Ollama
Ollama offers built in compatability with the OpenAI specification. To initialize a client that points to a Ollama change the host accordingly:
client = OmniAI::OpenAI::Client.new(host: 'http://localhost:11434', api_key: nil)
For details on installation or running Ollama checkout the project README.
Chat
A chat completion is generated by passing in prompts using any a variety of formats:
completion = client.chat('Tell me a joke!')
completion.choice..content # 'Why did the chicken cross the road? To get to the other side.'
completion = client.chat({
role: OmniAI::Chat::Role::USER,
content: 'Is it wise to jump off a bridge?'
})
completion.choice..content # 'No.'
completion = client.chat([
{
role: OmniAI::Chat::Role::SYSTEM,
content: 'You are a helpful assistant.'
},
'What is the capital of Canada?',
])
completion.choice..content # 'The capital of Canada is Ottawa.'
Model
model
takes an optional string (default is gtp-4o
):
completion = client.chat('How fast is a cheetah?', model: OmniAI::OpenAI::Chat::Model::GPT_3_5_TURBO)
completion.choice..content # 'A cheetah can reach speeds over 100 km/h.'
Temperature
temperature
takes an optional float between 0.0
and 2.0
(defaults is 0.7
):
completion = client.chat('Pick a number between 1 and 5', temperature: 2.0)
completion.choice..content # '3'
OpenAI 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.choice.delta.content) # 'Better', 'three', 'hours', ...
end
client.chat('Be poetic.', stream:)
Format
format
takes an optional symbol (:json
) and that setes the response_format
to json_object
:
completion = client.chat([
{ role: OmniAI::Chat::Role::SYSTEM, content: OmniAI::Chat::JSON_PROMPT },
{ role: OmniAI::Chat::Role::USER, content: 'What is the name of the drummer for the Beatles?' }
], format: :json)
JSON.parse(completion.choice..content) # { "name": "Ringo" }
OpenAI API Reference response_format
When using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message.
Transcribe
A transcription is generated by passing in a path to a file:
transcription = client.transcribe(file.path)
transcription.text # '...'
Prompt
prompt
is optional and can provide additional context for transcribing:
transcription = client.transcribe(file.path, prompt: '')
transcription.text # '...'
Format
format
is optional and supports json
, text
, srt
or vtt
:
transcription = client.transcribe(file.path, format: OmniAI::Transcribe::Format::TEXT)
transcription.text # '...'
OpenAI API Reference response_format
Language
language
is optional and may improve accuracy and latency:
transcription = client.transcribe(file.path, language: OmniAI::Transcribe::Language::SPANISH)
transcription.text
Temperature
temperature
is optional and must be between 0.0 (more deterministic) and 1.0 (less deterministic):
transcription = client.transcribe(file.path, temperature: 0.2)
transcription.text
OpenAI API Reference temperature
Speak
Speech can be generated by passing text with a block:
File.open('example.ogg', 'wb') do |file|
client.speak('How can a clam cram in a clean cream can?') do |chunk|
file << chunk
end
end
If a block is not provided then a tempfile is returned:
tempfile = client.speak('Can you can a can as a canner can can a can?')
tempfile.close
tempfile.unlink
Voice
voice
is optional and must be one of the supported voices:
client.speak('She sells seashells by the seashore.', voice: OmniAI::OpenAI::Speak::Voice::SHIMMER)
Model
model
is optional and must be either tts-1
or tts-1-hd
(default):
client.speak('I saw a kitten eating chicken in the kitchen.', format: OmniAI::OpenAI::Speak::Model::TTS_1)
Speed
speed
is optional and must be between 0.25 and 0.40:
client.speak('How much wood would a woodchuck chuck if a woodchuck could chuck wood?', speed: 4.0)
Format
format
is optional and supports MP3
(default), OPUS
, AAC
, FLAC
, WAV
or PCM
:
client.speak('A pessemistic pest exists amidst us.', format: OmniAI::OpenAI::Speak::Format::FLAC)
Files
Finding an File
client.files.find(id: 'file_...')
Listing all Files
client.files.all
Uploading a File
Using a File
file = client.files.build(io: File.open('demo.pdf', 'wb'))
file.save!
Using a Path
file = client.files.build(io: 'demo.pdf'))
file.save!
Downloading a File
file = client.files.find(id: 'file_...')
File.open('...', 'wb') do |file|
file.content do |chunk|
file << chunk
end
end
Destroying a File
client.files.destroy!('file_...')
Assistants
Finding an Assistant
client.assistants.find(id: 'asst_...')
Listing all Assistants
client.assistants.all
Creating an Assistant
assistant = client.assistants.build
assistant.name = 'Ringo'
assistant.model = OmniAI::OpenAI::Chat::Model::GPT_4
assistant.description = 'The drummer for the Beatles.'
assistant.save!
Updating an Assistant
assistant = client.assistants.find(id: 'asst_...')
assistant.name = 'George'
assistant.model = OmniAI::OpenAI::Chat::Model::GPT_4
assistant.description = 'A guitarist for the Beatles.'
assistant.save!
Destroying an Assistant
client.assistants.destroy!('asst_...')
Threads
Finding a Thread
client.threads.find(id: 'thread_...')
Creating a Thread
thread = client.threads.build
thread. = { user: 'Ringo' }
thread.save!
Updating a Thread
thread = client.threads.find(id: 'thread_...')
thread. = { user: 'Ringo' }
thread.save!
Destroying a Threads
client.threads.destroy!('thread_...')
Messages
Finding a Message
thread = client.threads.find(id: 'thread_...')
= thread..find(id: 'msg_...')
.save!
Listing all Messages
thread = client.threads.find(id: 'thread_...')
thread..all
Creating a Message
thread = client.threads.find(id: 'thread_...')
= thread..build(role: 'user', content: 'Hello?')
.save!
Updating a Message
thread = client.threads.find(id: 'thread_...')
= thread..build(role: 'user', content: 'Hello?')
.save!
Runs
Finding a Run
thread = client.threads.find(id: 'thread_...')
run = thread.runs.find(id: 'run_...')
run.save!
Listing all Runs
thread = client.threads.find(id: 'thread_...')
thread.runs.all
Creating a Run
run = client.runs.find(id: 'thread_...')
run = thread.runs.build
run. = { user: 'Ringo' }
run.save!
Updating a Run
thread = client.threads.find(id: 'thread_...')
run = thread..find(id: 'run_...')
run. = { user: 'Ringo' }
run.save!
Polling a Run
run.terminated? # false
run.poll!
run.terminated? # true
run.status # 'cancelled' / 'failed' / 'completed' / 'expired'
Cancelling a Run
thread = client.threads.find(id: 'thread_...')
run = thread.runs.cancel!(id: 'run_...')