Deep Research Multimodal Input (Interactions)

Pass images and PDFs to Deep Research as Agno Image and File objects.

Deep Research accepts images and documents (PDFs) as input, then conducts web-based research grounded in that content. Pass them as Agno Image / File objects with a URL. GCS and Gemini URIs pass through; regular HTTP URLs are downloaded and base64-encoded automatically.

Code

deep_research_multimodal.py

from agno.agent import Agent
from agno.media import File, Image
from agno.models.google import GeminiInteractions

agent = Agent(
    model=GeminiInteractions(
        agent="deep-research-preview-04-2026",
        thinking_summaries="auto",
    ),
    markdown=True,
)

if __name__ == "__main__":
    agent.print_response(
        "Analyze the interspecies dynamics in this image and research the "
        "symbiotic relationships shown.",
        images=[
            Image(
                url="https://storage.googleapis.com/generativeai-downloads/images/generated_elephants_giraffes_zebras_sunset.jpg"
            )
        ],
    )

    agent.print_response(
        "What is this document about, and how does it relate to current "
        "research trends?",
        files=[File(url="https://arxiv.org/pdf/1706.03762")],
    )

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Set your API key

   export GOOGLE_API_KEY=xxx
   
3. Install dependencies

   uv pip install -U "google-genai>=2.0" agno
   
4. Run Agent

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

   python deep_research_multimodal.py