精简示例
精简示例
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
docs = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(docs)
engine = index.as_query_engine(similarity_top_k=3)
resp = engine.query("文档里如何配置超时？")
print(resp)
for node in resp.source_nodes:
print(node.score, node.metadata.get("file_name"))默认是内存索引，进程退出即丢失；生产要配置持久化（落盘或外接 Milvus / Qdrant / pgvector 等向量库）。