llamaindex

llama-index-readers-reader

LlamaIndex data reader for Reader. Load web pages as LlamaIndex Documents for RAG pipelines and knowledge bases.

Installation

pip install llama-index-readers-reader

Usage

from llama_index_readers_reader import ReaderWebReader

reader = ReaderWebReader(api_key="rdr_...")

# Single URL
docs = reader.load_data(urls=["https://example.com"])
print(docs[0].text)      # Markdown content
print(docs[0].metadata)  # {"url": "...", "title": "..."}

# Multiple URLs (batch)
docs = reader.load_data(urls=[
    "https://example.com/page1",
    "https://example.com/page2",
])

Use with a VectorStoreIndex

from llama_index.core import VectorStoreIndex

reader = ReaderWebReader(api_key="rdr_...")
docs = reader.load_data(urls=["https://docs.example.com/getting-started"])

index = VectorStoreIndex.from_documents(docs)
query_engine = index.as_query_engine()
response = query_engine.query("How do I get started?")

Options

Parameter	Type	Default	Description
api_key	str	required	Reader API key
base_url	str	None	Custom API URL for self-hosted Reader
proxy_mode	str	None	"standard" or "premium"
only_main_content	bool	True	Extract main content only

License

MIT