NAME
OpenAI::API - access GPT models via OpenAI API
SYNOPSIS
use OpenAI::API;
my $openai = OpenAI::API->new(); # uses OPENAI_API_KEY environment variable
my $completions = $openai->completions(
model => 'text-davinci-003',
prompt => 'What is the capital of France?',
);
my $edits = $openai->edits(
model => 'text-davinci-edit-001',
input => 'What day of the wek is it?',
instruction => 'Fix the spelling mistakes',
);
my $moderations = $openai->moderations(
model => 'text-moderation-latest',
input => 'I want to kill them.',
);DESCRIPTION
OpenAI::API is a Perl module that provides an interface to the OpenAI API, which allows you to generate text, translate languages, summarize text, and perform other tasks using the language models developed by OpenAI.
To use the OpenAI::API module, you will need an API key, which you can obtain by signing up for an account on the OpenAI website.
METHODS
new()
Creates a new OpenAI::API object.
api_key [optional]
Your API key. Default:
$ENV{OPENAI_API_KEY}.Attention: never commit API keys to your repository. Use the
OPENAI_API_KEYenvironment variable instead.endpoint [optional]
The endpoint URL for the OpenAI API. Default: 'https://api.openai.com/v1/'.
completions()
Given a prompt, the model will return one or more predicted completions.
model
ID of the model to use.
See Models overview for a reference of them.
prompt
The prompt for the text generation.
suffix [optional]
The suffix that comes after a completion of inserted text.
max_tokens [optional]
The maximum number of tokens to generate.
Most models have a context length of 2048 tokens (except for the newest models, which support 4096.
temperature [optional]
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
top_p [optional]
An alternative to sampling with temperature, called nucleus sampling.
We generally recommend altering this or
temperaturebut not both.n [optional]
How many completions to generate for each prompt.
Use carefully and ensure that you have reasonable settings for
max_tokensandstop.stop [optional]
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
frequency_penalty [optional]
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
presence_penalty [optional]
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
best_of [optional]
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token).
Use carefully and ensure that you have reasonable settings for
max_tokensandstop.
Documentation: Completions
edits()
Creates a new edit for the provided input, instruction, and parameters.
model
ID of the model to use. You can use the text-davinci-edit-001 or code-davinci-edit-001 model with this endpoint.
input [optional]
The input text to use as a starting point for the edit.
instruction
The instruction that tells the model how to edit the prompt.
n [optional]
How many edits to generate for the input and instruction.
temperature [optional]
What sampling temperature to use, between 0 and 2.
top_p [optional]
An alternative to sampling with temperature.
Documentation: Edits
embeddings()
Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
model
input
user [optional]
Documentation: Embeddings
moderations()
Given a input text, outputs if the model classifies it as violating OpenAI's content policy.
input
model [optional]
Documentation: Moderations
SEE ALSO
AUTHOR
Nelson Ferraz <nferraz@gmail.com>
COPYRIGHT AND LICENSE
Copyright (C) 2022, 2023 by Nelson Ferraz
This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.30.2 or, at your option, any later version of Perl 5 you may have available.