> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent with Storage

> Persist a Nebius agent's chat history to Postgres with add_history_to_context for multi-turn context.

## Code

```python db.py theme={null}
import os

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.nebius import Nebius
from agno.tools.websearch import WebSearchTools

# Setup the database
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url)

agent = Agent(
    model=Nebius(id=os.environ["NEBIUS_MODEL_ID"]),
    db=db,
    tools=[WebSearchTools()],
    add_history_to_context=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")
```

Select a text-generation model with [function-calling support](https://docs.tokenfactory.nebius.com/ai-models-inference/function-calling) for this example.

## Usage

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

  <Step title="Export environment variables">
    Select an available text-generation model ID from the [Nebius model-list API](https://docs.tokenfactory.nebius.com/api-reference/examples/list-of-models).

    <CodeGroup>
      ```bash macOS / Linux theme={null}
      export NEBIUS_API_KEY="your_nebius_api_key"
      export NEBIUS_MODEL_ID="your_current_text_model_id"
      ```

      ```powershell Windows theme={null}
      $Env:NEBIUS_API_KEY="your_nebius_api_key"
      $Env:NEBIUS_MODEL_ID="your_current_text_model_id"
      ```
    </CodeGroup>
  </Step>

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

  <Step title="Run PgVector">
    ```bash theme={null}
    docker run -d \
      -e POSTGRES_DB=ai \
      -e POSTGRES_USER=ai \
      -e POSTGRES_PASSWORD=ai \
      -e PGDATA=/var/lib/postgresql/data/pgdata \
      -v pgvolume:/var/lib/postgresql/data \
      -p 5532:5432 \
      --name pgvector \
      agnohq/pgvector:18
    ```
  </Step>

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

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