Image Agent with Memory
Use an OpenAIResponses gpt-4o agent with WebSearchTools and add_history_to_context to answer a follow-up question about an image described in an earlier turn.
Code
from agno.agent import Agent
from agno.db.in_memory import InMemoryDb
from agno.media import Image
from agno.models.openai import OpenAIResponses
from agno.tools.websearch import WebSearchTools
agent = Agent(
model=OpenAIResponses(id="gpt-4o"),
tools=[WebSearchTools()],
markdown=True,
db=InMemoryDb(),
add_history_to_context=True,
num_history_runs=3,
)
agent.print_response(
"Tell me about this image and give me the latest news about it.",
images=[
Image(
url="https://upload.wikimedia.org/wikipedia/commons/0/0c/GoldenGateBridge-001.jpg"
)
],
)
agent.print_response("Tell me where I can get more images?")
InMemoryDb retains this conversation within the current process. Use persistent storage and a stable session ID when history must survive a restart.
Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateSet your API key
export OPENAI_API_KEY=xxxInstall dependencies
uv pip install -U openai ddgs agnoRun Agent
Save the code above as image_agent_with_memory.py, then run:
python image_agent_with_memory.py