Deep Research (Interactions)

Run the Deep Research managed agent through the Gemini Interactions API. The agent plans the task, searches the web, and returns a researched report with citations. The model forces background=True and store=True, and the non-streaming path polls until the result is ready.

Code

1import asyncio
2
3from kern.agent import Agent
4from kern.models.google import GeminiInteractions
5
6agent = Agent(
7    model=GeminiInteractions(
8        agent="deep-research-preview-04-2026",
9        thinking_summaries="auto",
10        visualization="auto",
11    ),
12    markdown=True,
13)
14
15if __name__ == "__main__":
16    agent.print_response(
17        "Research the current state of solid-state battery commercialization "
18        "and summarize the leading approaches."
19    )
20
21    asyncio.run(
22        agent.aprint_response(
23            "Compare the major open-source vector databases on indexing and query latency.",
24            stream=True,
25        )
26    )

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Set your API key

1export GOOGLE_API_KEY=xxx

Install dependencies

1uv pip install -U "google-genai>=2.0" kern-ai

Run Agent

1python cookbook/90_models/google/gemini_interactions/deep_research.py