使用模式

快速开始

从索引构建查询引擎：

query_engine = index.as_query_engine()

向您的数据提问

response = query_engine.query("Who is Paul Graham?")

配置查询引擎

高级API

你可以用一行代码直接从索引中构建并配置一个查询引擎：

query_engine = index.as_query_engine(
    response_mode="tree_summarize",
    verbose=True,
)

Note: While the high-level API optimizes for ease-of-use, it does NOT expose full range of configurability.

查看响应模式获取完整的响应模式列表及其功能说明。

底层组合API

如果您需要更细粒度的控制，可以使用底层组合API。具体来说，您需要显式构造一个QueryEngine对象，而不是调用index.as_query_engine(...)。

注意：您可能需要查阅API参考或示例笔记本。

from llama_index.core import VectorStoreIndex, get_response_synthesizer
from llama_index.core.retrievers import VectorIndexRetriever
from llama_index.core.query_engine import RetrieverQueryEngine

# build index
index = VectorStoreIndex.from_documents(documents)

# configure retriever
retriever = VectorIndexRetriever(
    index=index,
    similarity_top_k=2,
)

# configure response synthesizer
response_synthesizer = get_response_synthesizer(
    response_mode="tree_summarize",
)

# assemble query engine
query_engine = RetrieverQueryEngine(
    retriever=retriever,
    response_synthesizer=response_synthesizer,
)

# query
response = query_engine.query("What did the author do growing up?")
print(response)

流式处理

要启用流式传输，您只需传入一个 streaming=True 标志

query_engine = index.as_query_engine(
    streaming=True,
)
streaming_response = query_engine.query(
    "What did the author do growing up?",
)
streaming_response.print_response_stream()

阅读完整的流式处理指南
See an 端到端示例

定义自定义查询引擎

您也可以定义一个自定义查询引擎。只需继承 CustomQueryEngine 类，定义您希望拥有的任何属性（类似于定义 Pydantic 类），并实现一个 custom_query 函数，该函数返回一个 Response 对象或字符串。

from llama_index.core.query_engine import CustomQueryEngine
from llama_index.core.retrievers import BaseRetriever
from llama_index.core import get_response_synthesizer
from llama_index.core.response_synthesizers import BaseSynthesizer


class RAGQueryEngine(CustomQueryEngine):
    """RAG Query Engine."""

    retriever: BaseRetriever
    response_synthesizer: BaseSynthesizer

    def custom_query(self, query_str: str):
        nodes = self.retriever.retrieve(query_str)
        response_obj = self.response_synthesizer.synthesize(query_str, nodes)
        return response_obj

查看自定义查询引擎指南获取更多详情。