from llama_index.core import (
    VectorStoreIndex, SimpleDirectoryReader, StorageContext, load_index_from_storage,
)
from llama_index.core.node_parser import SentenceSplitter

docs  = SimpleDirectoryReader("./docs").load_data()
nodes = SentenceSplitter(chunk_size=512, chunk_overlap=64).get_nodes_from_documents(docs)

index = VectorStoreIndex(nodes)
index.storage_context.persist("./storage")     # embedding once is the expensive part

engine = index.as_query_engine(
    similarity_top_k=5,
    response_mode="compact",
)

response = engine.query("How do I rotate an API key?")
print(response)
for node in response.source_nodes:              # always show your sources
    print(node.metadata.get("file_name"), round(node.score, 3))