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

# AgentQL

> Use AgentQL tools with Agno agents.

Enable Agno agents to scrape website content using AgentQL Tools,

## Prerequisites

* Set the environment variable `AGENTQL_API_KEY` with your AgentQL API key. You can obtain the API key from the AgentQL website: [https://agentql.com/](https://agentql.com/)
* Run `playwright install` to install a browser extension for playwright.

```python theme={null}
"""
AgentQL will open up a browser instance (don't close it) and do scraping on the site.
"""

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.agentql import AgentQLTools

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

# Example 1: Enable specific AgentQL functions
agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[
        AgentQLTools(
            enable_scrape_website=True,
            enable_custom_scrape_website=False,
            agentql_query="your_query_here",
        )
    ],
)

# Example 2: Enable all AgentQL functions
agent_all = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[AgentQLTools(all=True, agentql_query="your_query_here")],
)

# Example 3: Custom query with specific function enabled
custom_query = """
{
    title
    text_content[]
}
"""

custom_agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[
        AgentQLTools(
            enable_scrape_website=True,
            enable_custom_scrape_website=True,
            agentql_query=custom_query,
        )
    ],
)

# Test the agents

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "Scrape the main content from https://docs.agno.com/introduction", markdown=True
    )
    custom_agent.print_response(
        "Extract title and content from https://docs.agno.com/introduction",
        markdown=True,
    )
```

## Run the Example

```bash theme={null}
# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/91_tools

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python agentql_tools.py
```

For details, see [AgentQL cookbook](https://github.com/agno-agi/agno/blob/main/cookbook/91_tools/agentql.py).