Session Caching for Performance

This example demonstrates how to enable session caching to store team sessions in memory for faster access and improved performance.

Code

cookbook/examples/teams/session/08_cache_session.py

"""Example of how to cache the team session in memory for faster access."""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIChat
from agno.team import Team

# Setup the database
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url, session_table="sessions")

agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    name="Research Assistant",
)

# Setup the team
team = Team(
    model=OpenAIChat(id="gpt-5-mini"),
    members=[agent],
    db=db,
    session_id="team_session_cache",
    add_history_to_context=True,
    # Activate session caching. The session will be cached in memory for faster access.
    cache_session=True,
)

team.print_response("Tell me a new interesting fact about space")

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Install required libraries

   pip install agno psycopg2-binary
   
3. Set environment variables

   export OPENAI_API_KEY=****
   
4. Start PostgreSQL database

   cookbook/run_pgvector.sh
   
5. Run the agent

   python cookbook/examples/teams/session/08_cache_session.py