Chat Completion

Leverage advanced AI models from OpenAI to perform complex tasks such as categorization, analysis, summarization, or decision support.

For more information on OpenAI's API, see OpenAI Documentation (opens in a new tab).

SDK Import:

from admyral.actions import openai_chat_completion

Arguments:

Argument Name	Description	Required
Model `model`	The model to use for the chat completion (e.g., `gpt-4`).	Yes
Prompt `prompt`	The input prompt to use for generating the chat completion.	Yes
Top P `top_ü`	Value between 0 and 1 for nucleus sampling. Only tokens with the top P probability mass are considered. Recommended to tweak this or temperature, but not both.	-
Temperature `temperature`	Sampling temperature, between 0 and 2. Higher values (e.g., 0.8) increase randomness, while lower values (e.g., 0.2) make output more deterministic. Recommended to adjust this or Top P, but not both.	-
Stop Tokens `stop_tokens`	A list of tokens to stop the completion upon encountering.	-

A string.

Secret Placeholder	Description
`OPENAI_SECRET`	OpenAI secret. See OpenAI setup

response = openai_chat_completion(
	model="gpt-4o",
	prompt="Why is the ocean salty?",
	secrets={
		"OPENAI_SECRET": "my_stored_openai_secret"
	}
)