Ruby::OpenAI
A simple Ruby wrapper for the OpenAI GPT-3 API.
Installation
Bundler
Add this line to your application's Gemfile:
gem 'ruby-openai'
And then execute:
$ bundle install
Gem install
Or install with:
$ gem install ruby-openai
and require with:
require "ruby/openai"
Usage
Get your API key from https://beta.openai.com/docs/developer-quickstart/your-api-keys
With dotenv
If you're using dotenv, you can add your secret key to your .env file:
OPENAI_ACCESS_TOKEN=access_token_goes_here
And create a client:
client = OpenAI::Client.new
Without dotenv
Alternatively you can pass your key directly to a new client:
client = OpenAI::Client.new(access_token: "access_token_goes_here")
Engines
There are different engines that can be used to generate text. For a full list and to retrieve information about a single engine:
client.engines.list
client.engines.retrieve(id: 'text-ada-001')
Examples
- GPT-3
- text-ada-001
- text-babbage-001
- text-curie-001
- text-davinci-001
- Codex (private beta)
- davinci-codex
- cushman-codex
- Content Filter
- content-filter-alpha
Completions
Hit the OpenAI API for a completion:
response = client.completions(engine: "text-davinci-001", parameters: { prompt: "Once upon a time", max_tokens: 5 })
puts response.parsed_response['choices'].map{ |c| c["text"] }
=> [", there lived a great"]
Files
Put your data in a .jsonl
file like this:
{"text": "puppy A is happy", "metadata": "emotional state of puppy A"}
{"text": "puppy B is sad", "metadata": "emotional state of puppy B"}
and pass the path to client.files.upload
to upload it to OpenAI, and then interact with it:
client.files.upload(parameters: { file: 'path/to/puppy.jsonl', purpose: 'search' })
client.files.list
client.files.retrieve(id: 123)
client.files.delete(id: 123)
Search
Pass documents and a query string to get semantic search scores against each document:
response = client.search(engine: "text-ada-001", parameters: { documents: %w[washington hospital school], query: "president" })
puts response["data"].map { |d| d["score"] }
=> [202.0, 48.052, 19.247]
You can alternatively search using the ID of a file you've uploaded:
client.search(engine: "text-ada-001", parameters: { file: "abc123", query: "happy" })
Answers
Pass documents, a question string, and an example question/response to get an answer to a question:
response = client.answers(parameters: {
documents: ["Puppy A is happy.", "Puppy B is sad."],
question: "which puppy is happy?",
model: "text-curie-001",
examples_context: "In 2017, U.S. life expectancy was 78.6 years.",
examples: [["What is human life expectancy in the United States?","78 years."]],
})
Or use the ID of a file you've uploaded:
response = client.answers(parameters: {
file: "123abc",
question: "which puppy is happy?",
model: "text-curie-001",
examples_context: "In 2017, U.S. life expectancy was 78.6 years.",
examples: [["What is human life expectancy in the United States?","78 years."]],
})
Classifications
Pass examples and a query to predict the most likely labels:
response = client.classifications(parameters: {
examples: [
["A happy moment", "Positive"],
["I am sad.", "Negative"],
["I am feeling awesome", "Positive"]
],
query: "It is a raining day :(",
model: "text-ada-001"
})
Or use the ID of a file you've uploaded:
response = client.classifications(parameters: {
file: "123abc,
query: "It is a raining day :(",
model: "text-ada-001"
})
Fine-tunes
Put your fine-tuning data in a .jsonl
file like this:
{"prompt":"Overjoyed with my new phone! ->", "completion":" positive"}
{"prompt":"@lakers disappoint for a third straight night ->", "completion":" negative"}
and pass the path to client.files.upload
to upload it to OpenAI and get its ID:
response = client.files.upload(parameters: { file: 'path/to/sentiment.jsonl', purpose: 'fine-tune' })
file_id = JSON.parse(response.body)["id"]
You can then use this file ID to create a fine-tune model:
response = client.finetunes.create(
parameters: {
training_file: file_id,
model: "text-ada-001"
})
fine_tune_id = JSON.parse(response.body)["id"]
That will give you the fine-tune ID. If you made a mistake you can cancel the fine-tune model before it is processed:
client.finetunes.cancel(id: fine_tune_id)
You may need to wait a short time for processing to complete. Once processed, you can use list or retrieve to get the name of the fine-tuned model:
client.finetunes.list
response = client.finetunes.retrieve(id: fine_tune_id)
fine_tuned_model = JSON.parse(response.body)["fine_tuned_model"]
This fine-tuned model name can then be used in classifications:
response = client.completions(
parameters: {
model: fine_tuned_model,
prompt: "I love Mondays!"
}
)
JSON.parse(response.body)["choices"].map { |c| c["text"] }
Do not pass the engine parameter when using a fine-tuned model.
Embeddings
You can use the embeddings endpoint to get a vector of numbers representing an input. You can then compare these vectors for different inputs to efficiently check how similar the inputs are.
client.embeddings(
engine: "babbage-similarity",
parameters: {
input: "The food was delicious and the waiter..."
}
)
Development
After checking out the repo, run bin/setup
to install dependencies. Then, run rake spec
to run the tests. You can also run bin/console
for an interactive prompt that will allow you to experiment.
To install this gem onto your local machine, run bundle exec rake install
. To release a new version, update the version number in version.rb
, update CHANGELOG.md
, and then run bundle exec rake release
, which will create a git tag for the version, push git commits and tags, and push the .gem
file to rubygems.org.
Contributing
Bug reports and pull requests are welcome on GitHub at https://github.com/alexrudall/ruby-openai. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the code of conduct.
License
The gem is available as open source under the terms of the MIT License.
Code of Conduct
Everyone interacting in the Ruby::OpenAI project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the code of conduct.