Session Summary Management

This example shows how to use session summary to store and maintain conversation summaries for better context management over long conversations.

Code

03_session_summary.py

"""
This example shows how to use the session summary to store the conversation summary.
"""

from agno.agent.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIChat
from agno.session.summary import SessionSummaryManager  # noqa: F401
from agno.team import Team

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

db = PostgresDb(db_url=db_url, session_table="sessions")

# Method 1: Set enable_session_summaries to True

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

team = Team(
    model=OpenAIChat(id="gpt-5-mini"),
    members=[agent],
    db=db,
    enable_session_summaries=True,
)

team.print_response("Hi my name is John and I live in New York")
team.print_response("I like to play basketball and hike in the mountains")

# Method 2: Set session_summary_manager

# session_summary_manager = SessionSummaryManager(model=OpenAIChat(id="gpt-5-mini"))

# agent = Agent(
#     model=OpenAIChat(id="gpt-5-mini"),
# )

# team = Team(
#     model=OpenAIChat(id="gpt-5-mini"),
#     members=[agent],
#     db=db,
#     session_summary_manager=session_summary_manager,
# )

# team.print_response("Hi my name is John and I live in New York")
# team.print_response("I like to play basketball and hike in the mountains")

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 03_session_summary.py