Llamaindex

pip install firecrawl-py

from llama_index.readers.web import FireCrawlWebReader

# Initialize FireCrawlWebReader to crawl a website
firecrawl_reader = FireCrawlWebReader(
    api_key="<your_api_key>",  # Replace with your actual API key from https://www.firecrawl.dev/
    mode="scrape",  # Choose between "crawl" and "scrape" for single page scraping
    params={"additional": "parameters"}  # Optional additional parameters
)

# Load documents from a single page URL
documents = firecrawl_reader.load_data(url="http://paulgraham.com/")
index = SummaryIndex.from_documents(documents)

# Set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
display(Markdown(f"<b>{response}</b>"))

from llama_index.readers.web import FireCrawlWebReader

# Initialize the FireCrawlWebReader with your API key and desired mode
firecrawl_reader = FireCrawlWebReader(
    api_key="<your_api_key>",  # Replace with your actual API key from https://www.firecrawl.dev/
    mode="scrape",  # Choose between "crawl" and "scrape"
    params={"additional": "parameters"}  # Optional additional parameters
)

# Load documents from a specified URL
documents = firecrawl_reader.load_data(url="http://paulgraham.com/worked.html")
index = SummaryIndex.from_documents(documents)

# Set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
display(Markdown(f"<b>{response}</b>"))