Skip to main content
All CollectionsIntegrations and EnrichmentsOpenAI/GPT
ChatGPT: Generate text (legacy) with OpenAI/GPT
ChatGPT: Generate text (legacy) with OpenAI/GPT

Ask ChatGPT (assistant) a question using Clay inputs (user) and context clues (system) to generate a response.

Updated over 3 months ago

Introduction

This integration enables users to leverage OpenAI's GPT model within Clay workflows. The "ChatGPT: Generate text (legacy)" action allows you to send queries to ChatGPT, utilizing Clay inputs as user prompts and additional context as system messages. This functionality harnesses GPT's natural language processing capabilities to generate relevant responses based on the provided information, enhancing Clay's data enrichment and analysis capabilities.

Input

Name

Is Optional

Description

Type

# of Messages

The number of messages you want to send to ChatGPT for context. [Learn More.](https://platform.openai.com/docs/guides/chat) Max of 20

number

true

dynamicFields

Model

true

The ChatGPT model to run this request with. Defaults to "gpt-4". [Learn more about models here.](https://platform.openai.com/docs/models/gpt-3-5)

text

Creativity Level

true

Choose the creativity level for GPT. Higher temperatures mean higher creativity, or more variance in the responses. The scale is from 0-2, default being 1. You can [read more about it here.](https://platform.openai.com/docs/api-reference/chat/create#chat-create-temperature)

text

Stop Sequence

true

Optionally, enter a piece of text where OpenAI will stop generating tokens. By default, any whitespace will be used. [Learn More](https://help.openai.com/en/articles/5072263-how-do-i-use-stop-sequences)

text

Output

Name

Type

Messages

array

Did this answer your question?