> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-codex-docs-audit-20260719-0149.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Accuracy Evaluation with Database Logging

> Persist AccuracyEval runs to a PostgresDb eval_runs_cookbook table while scoring a calculator agent.

Demonstrates storing accuracy evaluation results in PostgreSQL.

```python db_logging.py theme={null}
"""
Accuracy Evaluation with Database Logging
=========================================

Demonstrates storing accuracy evaluation results in PostgreSQL.
"""

from typing import Optional

from agno.agent import Agent
from agno.db.postgres.postgres import PostgresDb
from agno.eval.accuracy import AccuracyEval, AccuracyResult
from agno.models.openai import OpenAIChat
from agno.tools.calculator import CalculatorTools

# ---------------------------------------------------------------------------
# Create Database
# ---------------------------------------------------------------------------
db_url = "postgresql+psycopg://ai:ai@localhost:5432/ai"
db = PostgresDb(db_url=db_url, eval_table="eval_runs_cookbook")

# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
evaluation = AccuracyEval(
    db=db,
    name="Calculator Evaluation",
    model=OpenAIChat(id="o4-mini"),
    agent=Agent(
        model=OpenAIChat(id="gpt-4o"),
        tools=[CalculatorTools()],
    ),
    input="What is 10*5 then to the power of 2? do it step by step",
    expected_output="2500",
    additional_guidelines="Agent output should include the steps and the final answer.",
    num_iterations=1,
)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    result: Optional[AccuracyResult] = evaluation.run(print_results=True)
    assert result is not None and result.avg_score >= 8
```

## 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>

  <Step title="Start Postgres">
    Start Postgres on the port used by this example:

    ```bash theme={null}
    docker run -d --name postgres -e POSTGRES_USER=ai -e POSTGRES_PASSWORD=ai -e POSTGRES_DB=ai -p 5432:5432 postgres:17
    ```
  </Step>

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

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

Full source: [cookbook/09\_evals/accuracy/db\_logging.py](https://github.com/agno-agi/agno/blob/v2.7.4/cookbook/09_evals/accuracy/db_logging.py)