Gpt3.stream – Aigur Client

Name

gpt3PredictionStream

Description

Calls GPT3 and returns the result as a Stream

API Key

Uses the openai API key:

index.ts

const aigur = createClient({
  apiKeys: {
    openai: process.env.OPENAI_API_KEY
  }
})

Example

index.ts

import { gpt3PredictionStream } from '@aigur/client';
//...
flow.node(gpt3PredictionStream, () => ({
  prompt: 'Hello, how are you?'
})) // --> ReadableStream

Input

Property	Type	Required	Description	Default Value
prompt	string	Yes	The prompt to pass GPT3
model	enum('text-davinci-003', 'text-curie-001', 'text-babbage-001', 'text-ada-001', 'code-davinci-002', 'code-cushman-002')	No	ID of the model to use	text-davinci-003
max_tokens	number	No	The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).	200
temperature	number	No	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. We generally recommend altering this or `top_p` but not both.	0.7
top_p	number	No	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. It is generally recommend altering this or `temperature` but not both.	1
frequency_penalty	number	No	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.	0
presence_penalty	number	No	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.	0

Output

The output of this Node is not an object, rather a ReadableStream.