Session Summary

Enable session summaries with enable_session_summaries or a custom SessionSummaryManager, stored in Postgres.

Use the session summary to store the conversation summary.

session_summary.py

"""
Session Summary
=============================

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 OpenAIResponses
from agno.session.summary import SessionSummaryManager  # noqa: F401

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

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5-mini"),
    db=db,
    enable_session_summaries=True,
    session_id="session_123",
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("Hi my name is John and I live in New York")
    agent.print_response("I like to play basketball and hike in the mountains")

    print(agent.get_session_summary(session_id="session_123"))

    # Method 2: Set session_summary_manager

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

    # agent = Agent(
    #     model=OpenAIResponses(id="gpt-5-mini"),
    #     db=db,
    #     session_id="session_summary",
    #     session_summary_manager=session_summary_manager,
    # )

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

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 "psycopg[binary]" openai sqlalchemy
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run PgVector

   macOS / Linux

   docker run -d \
     -e POSTGRES_DB=ai \
     -e POSTGRES_USER=ai \
     -e POSTGRES_PASSWORD=ai \
     -e PGDATA=/var/lib/postgresql \
     -v pgvolume:/var/lib/postgresql \
     -p 5532:5432 \
     --name pgvector \
     agnohq/pgvector:18
   

   docker run -d `
     -e POSTGRES_DB=ai `
     -e POSTGRES_USER=ai `
     -e POSTGRES_PASSWORD=ai `
     -e PGDATA=/var/lib/postgresql `
     -v pgvolume:/var/lib/postgresql `
     -p 5532:5432 `
     --name pgvector `
     agnohq/pgvector:18
   
5. Run the example

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

   python session_summary.py
   

Full source: cookbook/02_agents/05_state_and_session/session_summary.py