Perplexity Web Search

Use Perplexity sonar-pro’s native web search to answer a current news question.

web_search.py

"""
Perplexity Web Search
=====================

Cookbook example for `perplexity/web_search.py`.
"""

from agno.agent import Agent, RunOutput  # noqa
from agno.models.perplexity import Perplexity

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

agent = Agent(model=Perplexity(id="sonar-pro"), markdown=True)

# Print the response in the terminal
agent.print_response("Show me top 2 news stories from USA?")

# Get the response in a variable
# run: RunOutput = agent.run("What is happening in the world today?")
# print(run.content)

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

if __name__ == "__main__":
    pass

Run the Example

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. Install dependencies

   uv pip install -U agno openai
   
3. Export your Perplexity API key

   Mac/Linux

   export PERPLEXITY_API_KEY="your_perplexity_api_key_here"
   

   $Env:PERPLEXITY_API_KEY="your_perplexity_api_key_here"
   
4. Run the example

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

   python web_search.py
   

Full source: cookbook/90_models/perplexity/web_search.py