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

# Storage

> Store sessions in a named Postgres table so Llama 4 Maverick keeps history across runs.

```python storage.py theme={null}
"""Run `uv pip install ddgs sqlalchemy openai` to install dependencies."""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.meta import LlamaOpenAI
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

agent = Agent(
    model=LlamaOpenAI(id="Llama-4-Maverick-17B-128E-Instruct-FP8"),
    db=PostgresDb(db_url=db_url, session_table="llama_openai_sessions"),
    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?")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

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

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno "psycopg[binary]" ddgs llama-api-client openai sqlalchemy
```

**2. Export your Meta Llama API key**

```bash Mac/Linux theme={null}
export LLAMA_API_KEY="your_llama_api_key_here"
```

```bash Windows theme={null}
$Env:LLAMA_API_KEY="your_llama_api_key_here"
```

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

**3. Run the example**

Save the code above as `storage.py`, then run:

```bash theme={null}
python storage.py
```

Full source: [cookbook/90\_models/meta/llama\_openai/storage.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/meta/llama_openai/storage.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.