from pathlib import Path
from agno.agent import Agent
from agno.media import Image
from agno.models.openai import OpenAIChat
agent = Agent(
model=OpenAIChat(id="gpt-4o"),
agent_id="image-to-text",
name="Image to Text Agent",
markdown=True,
debug_mode=True,
show_tool_calls=True,
instructions=[
"You are an AI agent that can generate text descriptions based on an image.",
"You have to return a text response describing the image.",
],
)
image_path = Path(__file__).parent.joinpath("sample.jpg")
agent.print_response(
"Write a 3 sentence fiction story about the image",
images=[Image(filepath=image_path)],
stream=True,
)
Create a virtual environment
Terminal
and create a python virtual environment.python3 -m venv .venv
source .venv/bin/activate
Set your API key
export OPENAI_API_KEY=xxx
Install libraries
pip install -U openai agno
Run Agent
python cookbook/agent_concepts/multimodal/image_to_text_agent.py
Was this page helpful?