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 o FireCrawlWebReader para rastrear um site
firecrawl_reader = FireCrawlWebReader(
    api_key=os.environ["FIRECRAWL_API_KEY"],  # Obtenha uma chave em https://www.firecrawl.dev/app/api-keys
    mode="crawl",  # "scrape", "crawl", "map", "search" ou "extract"
    params={"limit": 10},  # Parâmetros opcionais do Firecrawl para o modo escolhido
)

# Carrega os documentos do site
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

# Inicialize o FireCrawlWebReader com sua chave de API e o modo desejado
firecrawl_reader = FireCrawlWebReader(
    api_key=os.environ["FIRECRAWL_API_KEY"],  # Obtenha uma chave em https://www.firecrawl.dev/app/api-keys
    mode="scrape",  # "scrape", "crawl", "map", "search" ou "extract"
)

# Carregue documentos de uma 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)