> ## 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 an Azure AI Foundry agent's session history to Postgres across runs.

## Code

```python db.py theme={null}
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.azure import AzureAIFoundry
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=AzureAIFoundry(id="Phi-4"),
    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?")
```

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export AZURE_API_KEY=xxx
    export AZURE_ENDPOINT=xxx
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U azure-ai-inference aiohttp 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>