OpenAI Ask

A provider-specific guide to the OpenAI Ask action for accessing GPT models.

The OpenAI Ask Action provides direct access to OpenAI's powerful language models, including the GPT-3.5 and GPT-4 families. Use this action when you want to leverage the specific capabilities and performance of OpenAI's technology for your text generation, summarization, or analysis tasks.

This guide covers specifics for the OpenAI action. For a general overview of how to work with Large Language Models, including prompting techniques, temperature, and other settings, please see our main **[LLM Action Guide](./llm.md)**.

Connection Setup

You will need an OpenAI account and your API key.

1. Sign up for an account on the OpenAI Platform.

2. Find your API key in your account settings under API Keys.

3. In AgenticFlow, navigate to Settings > Connections and add a new OpenAI Connection, providing your API key.

Configuration

Input Parameters

Parameter	Type	Description
Connection	Connection	Select the OpenAI connection you created.
Model	Select	Choose the specific OpenAI model you want to use (e.g., gpt-4-turbo, gpt-3.5-turbo).
System Prompt	Text	Instructions for the AI's persona or role (e.g., "You are a helpful assistant.").
User Prompt	Text	The main instruction or question for the AI model.
Temperature	Number	Controls randomness. See the main LLM guide for details.
Max Tokens	Number	The maximum length of the generated response.
JSON Mode	Boolean	If true, instructs the model to only output valid JSON. See the main LLM guide.

Output Parameters

Parameter	Type	Description
Output	Text	The text generated by the OpenAI model.

Example: Using a Specific GPT Model

This action is used in the same way as the general LLM Action, but it allows you to guarantee that you are using a specific model from OpenAI's lineup.

• To create a marketing email:

  • Model: gpt-4-turbo (for highest quality)

  • System Prompt: You are a world-class copywriter specializing in email marketing.

  • User Prompt: Write a short, punchy email announcing our new product: the "Quantum Coffee Mug".

• To extract structured data quickly:

  • Model: gpt-3.5-turbo (for speed and lower cost)

  • User Prompt: Extract the name and email from this text: {{some_input_text}}

  • JSON Mode: true