> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Research Agent Exa

> Research a topic with Exa search on Groq and save the markdown report to a file.

<Warning>
  For free and developer tiers, Groq will shut down `llama-3.3-70b-versatile` on August 16, 2026. Replace it with `openai/gpt-oss-120b` before that date. See [Groq deprecations](https://console.groq.com/docs/deprecations).
</Warning>

```python research_agent_exa.py theme={null}
"""Run `uv pip install groq exa-py` to install dependencies."""

from datetime import datetime
from pathlib import Path
from textwrap import dedent

from agno.agent import Agent
from agno.models.groq import Groq
from agno.tools.exa import ExaTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

cwd = Path(__file__).parent.resolve()
tmp = cwd.joinpath("tmp")
if not tmp.exists():
    tmp.mkdir(exist_ok=True, parents=True)

today = datetime.now().strftime("%Y-%m-%d")

agent = Agent(
    model=Groq(id="llama-3.3-70b-versatile"),
    tools=[ExaTools(start_published_date=today, type="keyword")],
    description="You are an advanced AI researcher writing a report on a topic.",
    instructions=[
        "For the provided topic, run 3 different searches.",
        "Read the results carefully and prepare a NYT worthy report.",
        "Focus on facts and make sure to provide references.",
    ],
    expected_output=dedent("""\
    An engaging, informative, and well-structured report in markdown format:

    ## Engaging Report Title

    ### Overview
    {give a brief introduction of the report and why the user should read this report}
    {make this section engaging and create a hook for the reader}

    ### Section 1
    {break the report into sections}
    {provide details/facts/processes in this section}

    ... more sections as necessary...

    ### Takeaways
    {provide key takeaways from the article}

    ### References
    - [Reference 1](link)
    - [Reference 2](link)
    - [Reference 3](link)

    ### About the Author
    {write a made up for yourself, give yourself a cyberpunk name and a title}

    - published on {date} in dd/mm/yyyy
    """),
    markdown=True,
    add_datetime_to_context=True,
    save_response_to_file=str(tmp.joinpath("{message}.md")),
)
agent.print_response("Llama 3.3 running on Groq", stream=True)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno exa-py groq
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export EXA_API_KEY="your_exa_api_key_here"
      export GROQ_API_KEY="your_groq_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:EXA_API_KEY="your_exa_api_key_here"
      $Env:GROQ_API_KEY="your_groq_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Replace Llama 3.3">
    Replace `llama-3.3-70b-versatile` with `openai/gpt-oss-120b` in the saved file.
  </Step>

  <Step title="Run the example">
    Save the code above as `research_agent_exa.py`, then run:

    ```bash theme={null}
    python research_agent_exa.py
    ```
  </Step>
</Steps>

Full source: [cookbook/90\_models/groq/research\_agent\_exa.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/groq/research_agent_exa.py)