​
Prerequisites

You need to install the openai library.

pip install openai

Set the OPENAI_API_KEY environment variable.

export OPENAI_API_KEY=****

​
Example

The following agent will use DALL-E to generate an image based on a text prompt.

cookbook/tools/dalle_tools.py
from phi.agent import Agent
from phi.tools.dalle import Dalle

# Create an Agent with the DALL-E tool
agent = Agent(tools=[Dalle()], name="DALL-E Image Generator")

# Example 1: Generate a basic image with default settings
agent.print_response("Generate an image of a futuristic city with flying cars and tall skyscrapers", markdown=True)

# Example 2: Generate an image with custom settings
custom_dalle = Dalle(model="dall-e-3", size="1792x1024", quality="hd", style="natural")

agent_custom = Agent(
    tools=[custom_dalle],
    name="Custom DALL-E Generator",
    show_tool_calls=True,
)

agent_custom.print_response("Create a panoramic nature scene showing a peaceful mountain lake at sunset", markdown=True)

​
Toolkit Params

ParameterTypeDefaultDescription
modelstr"dall-e-3"The DALL-E model to use
nint1Number of images to generate
sizestr"1024x1024"Image size (256x256, 512x512, 1024x1024, 1792x1024, or 1024x1792)
qualitystr"standard"Image quality (standard or hd)
stylestr"vivid"Image style (vivid or natural)
api_keystrNoneThe OpenAI API key for authentication

​
Toolkit Functions

FunctionDescription
generate_imageGenerates an image based on a text prompt

​
Information

Was this page helpful?

CSVDuckDb