Build RAG with LlamaIndex

Less boilerplate

LlamaIndex handles loading, chunking, embedding, and retrieval so you can focus on your data.

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

docs = SimpleDirectoryReader("./docs").load_data()
index = VectorStoreIndex.from_documents(docs)
engine = index.as_query_engine()
print(engine.query("What is our refund policy?"))

When to use a framework

Frameworks accelerate the common path and are great for prototypes. As needs grow, you may drop to lower-level control over chunking and retrieval — but starting here gets you to a working demo fast.