🦜🔗 LangChain Connector

LangChain Web Scraping & Ingestion

Load live web pages and entire sitemaps directly into LangChain `Document` objects. Eliminate 90% of token noise before chunking and vector storage.

Get Free API Key → RAG Architecture Guide
Python LangChain Snippet 
from langchain_core.documents import Document
from flycrawl import FlyCrawl

client = FlyCrawl(api_key="YOUR_API_KEY")
res = client.scrape_url("https://example.com")

doc = Document(
    page_content=res["markdown"],
    metadata={"source": res["url"]}
)
# Ready for LangChain text splitters & vector stores