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/activate

Set your API key

export OPENAI_API_KEY=xxx

Install dependencies

uv pip install -U openai ddgs agno

Run Agent

Save the code above as image_agent_with_memory.py, then run:

python image_agent_with_memory.py