> ## 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.

# Team Session Metrics

> Demonstrates session-level metrics for teams with PostgreSQL persistence.

Demonstrates session-level metrics for teams with PostgreSQL persistence. Metrics accumulate across multiple team runs within the same session.

```python team_session_metrics.py theme={null}
"""
Team Session Metrics
=============================

Demonstrates session-level metrics for teams with PostgreSQL persistence.
Metrics accumulate across multiple team runs within the same session.

Run: ./cookbook/scripts/run_pgvector.sh
"""

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

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

# ---------------------------------------------------------------------------
# Create Members
# ---------------------------------------------------------------------------
assistant = Agent(
    name="Assistant",
    model=OpenAIChat(id="gpt-4o-mini"),
    role="Helpful assistant that answers questions.",
)

# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------
team = Team(
    name="Research Team",
    model=OpenAIChat(id="gpt-4o-mini"),
    members=[assistant],
    db=db,
    session_id="team_session_metrics_demo",
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Team
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # First run
    run_output_1 = team.run("What is the capital of Japan?")
    print("=" * 50)
    print("RUN 1 METRICS")
    print("=" * 50)
    pprint(run_output_1.metrics)

    # Second run on the same session
    run_output_2 = team.run("What about South Korea?")
    print("=" * 50)
    print("RUN 2 METRICS")
    print("=" * 50)
    pprint(run_output_2.metrics)

    # Session metrics aggregate both runs
    print("=" * 50)
    print("SESSION METRICS (accumulated)")
    print("=" * 50)
    session_metrics = team.get_session_metrics()
    pprint(session_metrics)
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno "psycopg[binary]" openai sqlalchemy
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Snippet file="run-pgvector-step.mdx" />

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

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

Full source: [cookbook/03\_teams/22\_metrics/03\_team\_session\_metrics.py](https://github.com/agno-agi/agno/blob/main/cookbook/03_teams/22_metrics/03_team_session_metrics.py)