The Website Reader with asynchronous processing crawls and processes entire websites efficiently, following links to create comprehensive knowledge bases from web content.

​
Code

examples/concepts/knowledge/readers/website_reader_async.py
import asyncio

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.website_reader import WebsiteReader
from agno.vectordb.pgvector import PgVector

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

knowledge = Knowledge(
    vector_db=PgVector(
        table_name="website_documents",
        db_url=db_url,
    ),
)

agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
)

async def main():
    # Crawl and add website content to knowledge base
    await knowledge.add_content_async(
        url="https://docs.agno.com/introduction",
        reader=WebsiteReader(max_depth=2, max_links=20),
    )

    # Query the knowledge base
    await agent.aprint_response(
        "What are the main features of Agno?",
        markdown=True,
    )

if __name__ == "__main__":
    asyncio.run(main())

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Install libraries

pip install -U requests beautifulsoup4 sqlalchemy psycopg pgvector agno openai
3

Set environment variables

export OPENAI_API_KEY=xxx
4

Run PgVector

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 \
  agno/pgvector:16
5

Run Agent

python examples/concepts/knowledge/readers/website_reader_async.py

​
Params

ParameterTypeDefaultDescription
urlstrRequiredURL of the website to crawl and read
max_depthint3Maximum depth level for crawling links
max_linksint10Maximum number of links to crawl