🦙 LlamaIndex Integration
LlamaIndex Web Knowledge Ingestion
Build high-recall query engines over the live web. FlyCrawl extracts clean Fit-Markdown from dynamic sites, keeping your LlamaIndex vector store pristine.
Python LlamaIndex Snippet
from llama_index.core import Document, VectorStoreIndex
from flycrawl import FlyCrawl
client = FlyCrawl(api_key="YOUR_KEY")
res = client.scrape_url("https://docs.example.com")
doc = Document(text=res["markdown"], metadata={"url": res["url"]})
index = VectorStoreIndex.from_documents([doc])
query_engine = index.as_query_engine()