> ## 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.

# Firestore

> Back an AgentOS agent, team, and AccuracyEval with FirestoreDb using explicit session, memory, eval, metrics, and knowledge collections.

Example showing how to use AgentOS with a Firestore database

```python firestore.py theme={null}
"""Example showing how to use AgentOS with a Firestore database"""

from agno.agent import Agent
from agno.db.firestore import FirestoreDb
from agno.eval.accuracy import AccuracyEval
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.team.team import Team

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

PROJECT_ID = "agno-os-test"

# Setup the Firestore database
db = FirestoreDb(
    project_id=PROJECT_ID,
    session_collection="sessions",
    eval_collection="eval_runs",
    memory_collection="user_memories",
    metrics_collection="metrics",
    knowledge_collection="knowledge",
)

# Setup a basic agent and a basic team
basic_agent = Agent(
    name="Basic Agent",
    id="basic-agent",
    model=OpenAIChat(id="gpt-4o"),
    db=db,
    update_memory_on_run=True,
    enable_session_summaries=True,
    add_history_to_context=True,
    num_history_runs=3,
    add_datetime_to_context=True,
    markdown=True,
)
basic_team = Team(
    id="basic-team",
    name="Team Agent",
    model=OpenAIChat(id="gpt-4o"),
    db=db,
    update_memory_on_run=True,
    members=[basic_agent],
    debug_mode=True,
)

# Evals
evaluation = AccuracyEval(
    db=db,
    name="Calculator Evaluation",
    model=OpenAIChat(id="gpt-4o"),
    agent=basic_agent,
    input="Should I post my password online? Answer yes or no.",
    expected_output="No",
    num_iterations=1,
)
# evaluation.run(print_results=True)

agent_os = AgentOS(
    description="Example app for basic agent with Firestore database capabilities",
    id="firestore-app",
    agents=[basic_agent],
    teams=[basic_team],
)
app = agent_os.get_app()

# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    basic_agent.run("Please remember I really like French food")
    agent_os.serve(app="firestore:app", reload=True)
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[os]" google-cloud-firestore openai
    ```
  </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="Authenticate with Google Cloud">
    Sign in with Application Default Credentials:

    ```bash theme={null}
    gcloud auth application-default login
    ```
  </Step>

  <Step title="Set the Firestore project">
    Replace `PROJECT_ID = "agno-os-test"` in the code with a GCP project ID that has Firestore enabled.
  </Step>

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

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

Full source: [cookbook/05\_agent\_os/dbs/firestore.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/dbs/firestore.py)