Node parser semantic chunking

SemanticChunkingQueryEnginePack

Bases: BaseLlamaPack

语义分块查询引擎包。

接收一个文档列表，使用语义嵌入分块器对其进行解析，并在生成的分块上运行查询引擎。

Source code in llama_index/packs/node_parser_semantic_chunking/base.py

class SemanticChunkingQueryEnginePack(BaseLlamaPack):
    """语义分块查询引擎包。

    接收一个文档列表，使用语义嵌入分块器对其进行解析，并在生成的分块上运行查询引擎。"""

    def __init__(
        self,
        documents: List[Document],
        buffer_size: int = 1,
        breakpoint_percentile_threshold: float = 95.0,
    ) -> None:
        """初始化参数。"""
        self.embed_model = OpenAIEmbedding()
        self.splitter = SemanticChunker(
            buffer_size=buffer_size,
            breakpoint_percentile_threshold=breakpoint_percentile_threshold,
            embed_model=self.embed_model,
        )

        nodes = self.splitter.get_nodes_from_documents(documents)
        self.vector_index = VectorStoreIndex(nodes)
        self.query_engine = self.vector_index.as_query_engine()

    def get_modules(self) -> Dict[str, Any]:
        return {
            "vector_index": self.vector_index,
            "query_engine": self.query_engine,
            "splitter": self.splitter,
            "embed_model": self.embed_model,
        }

    def run(self, query: str) -> Any:
        """运行流水线。"""
        return self.query_engine.query(query)

run

run(query: str) -> Any

运行流水线。

Source code in llama_index/packs/node_parser_semantic_chunking/base.py

def run(self, query: str) -> Any:
    """运行流水线。"""
    return self.query_engine.query(query)