LlamaIndex

pip install 'firecrawl-py>=4.3.3' llama-index llama-index-readers-web

import os

from llama_index.core import SummaryIndex
from llama_index.readers.web import FireCrawlWebReader

# Inicializa FireCrawlWebReader para rastrear un sitio web
firecrawl_reader = FireCrawlWebReader(
    api_key=os.environ["FIRECRAWL_API_KEY"],  # Obtén una clave en https://www.firecrawl.dev/app/api-keys
    mode="crawl",  # "scrape", "crawl", "map", "search" o "extract"
    params={"limit": 10},  # Parámetros opcionales de Firecrawl para el modo elegido
)

# Carga los documentos del sitio
documents = firecrawl_reader.load_data(url="https://www.paulgraham.com/")
index = SummaryIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)

import os

from llama_index.core import SummaryIndex
from llama_index.readers.web import FireCrawlWebReader

# Inicializa FireCrawlWebReader con tu clave de API y el modo deseado
firecrawl_reader = FireCrawlWebReader(
    api_key=os.environ["FIRECRAWL_API_KEY"],  # Obtén una clave en https://www.firecrawl.dev/app/api-keys
    mode="scrape",  # "scrape", "crawl", "map", "search" o "extract"
)

# Carga documentos desde una URL específica
documents = firecrawl_reader.load_data(url="https://www.paulgraham.com/worked.html")
index = SummaryIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)