SiftQ + LangChain

Drop-in Retriever for any LangChain pipeline.

SiftQ ships an official LangChain integration: `SiftQRetriever` plugs into RetrievalQA, agent toolkits, and LCEL chains with the same interface as any other Retriever. Works in both LangChain Python and LangChain.js.

Install

pip install langchain-siftq

Example

from langchain_siftq import SiftQRetriever
from langchain.chains import RetrievalQA
from langchain_anthropic import ChatAnthropic

retriever = SiftQRetriever(scope="webpage", size=10)
qa = RetrievalQA.from_chain_type(
    llm=ChatAnthropic(model="claude-sonnet-4-6"),
    retriever=retriever,
)
print(qa.run("What are the latest open source LLM benchmarks?"))

Why use it

• ✓Same Retriever interface as Chroma, Pinecone, etc — swap with one line
• ✓Returns rich metadata (score, date, authors) for downstream filtering
• ✓Streams results when used in async chains
• ✓Auth via env var SIFTQ_API_KEY — no client setup