Skip to main content
The Firecrawl Reader with asynchronous processing uses the Firecrawl API to scrape and crawl web content efficiently, converting it into documents for your knowledge base.

​
Code

examples/context/knowledge/readers/overview/firecrawl_reader_async.py
import os
import asyncio

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.firecrawl_reader import FirecrawlReader
from agno.vectordb.pgvector import PgVector

api_key = os.getenv("FIRECRAWL_API_KEY")
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

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

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

async def main():
    # Add Firecrawl content to knowledge base
    await knowledge.add_content_async(
        url="https://github.com/agno-agi/agno",
        reader=FirecrawlReader(
            api_key=api_key,
            mode="scrape",
            chunk=True,
            params={"formats": ["markdown"]},
        ),
    )

    # Query the knowledge base
    await agent.aprint_response(
        "What is the main purpose of this repository?",
        markdown=True,
    )

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

​
Usage

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
2

Install dependencies

uv pip install -U firecrawl-py sqlalchemy psycopg pgvector agno
3

Set API Key

export FIRECRAWL_API_KEY="your-firecrawl-api-key"
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/context/knowledge/readers/overview/firecrawl_reader_async.py

​
Params

ParameterTypeDefaultDescription
api_keyOptional[str]NoneFirecrawl API key for authentication
paramsOptional[Dict]NoneAdditional parameters to pass to the Firecrawl API
modeLiteral["scrape", "crawl"]"scrape"Mode of operation - "scrape" for single page, "crawl" for multiple pages
urlstrRequiredURL of the website to scrape or crawl