SingleStore

SingleStoreReader

基类: BaseReader

SingleStore 读取器。

参数

名称	类型	描述	默认值
scheme	str	数据库 Scheme。	必需
host	str	数据库 Host。	必需
port	str	数据库 Port。	必需
user	str	数据库用户。	必需
password	str	数据库密码。	必需
dbname	str	数据库名称。	必需
table_name	str	表名称。	必需
content_field	str	内容字段。	'text'
vector_field	str	向量字段。	'embedding'

源代码位于 llama-index-integrations/readers/llama-index-readers-singlestore/llama_index/readers/singlestore/base.py

class SingleStoreReader(BaseReader):
    """
    SingleStore reader.

    Args:
        scheme (str): Database Scheme.
        host (str): Database Host.
        port (str): Database Port.
        user (str): Database User.
        password (str): Database Password.
        dbname (str): Database Name.
        table_name (str): Table Name.
        content_field (str): Content Field.
        vector_field (str): Vector Field.

    """

    def __init__(
        self,
        scheme: str,
        host: str,
        port: str,
        user: str,
        password: str,
        dbname: str,
        table_name: str,
        content_field: str = "text",
        vector_field: str = "embedding",
    ):
        """Initialize with parameters."""
        self.scheme = scheme
        self.host = host
        self.port = port
        self.user = user
        self.password = password
        self.dbname = dbname
        self.table_name = table_name
        self.content_field = content_field
        self.vector_field = vector_field

        try:
            import pymysql

            pymysql.install_as_MySQLdb()
        except ImportError:
            pass

        self.DatabaseReader = DatabaseReader
        self.reader = self.DatabaseReader(
            scheme=self.scheme,
            host=self.host,
            port=self.port,
            user=self.user,
            password=self.password,
            dbname=self.dbname,
        )

    def load_data(self, search_embedding: str, top_k: int = 5) -> List[Document]:
        """
        Load data from SingleStore.

        Args:
            search_embedding (str): The embedding to search.
            top_k (int): Number of results to return.

        Returns:
            List[Document]: A list of documents.

        """
        query = f"""
        SELECT {self.content_field}, DOT_PRODUCT_F64({self.vector_field}, JSON_ARRAY_PACK_F64(\'{search_embedding}\')) AS score
        FROM {self.table_name}
        ORDER BY score
        DESC LIMIT {top_k}
        """

        return self.reader.load_data(query=query)

load_data

load_data(search_embedding: str, top_k: int = 5) -> List[Document]

从 SingleStore 加载数据。

参数

名称	类型	描述	默认值
search_embedding	str	要搜索的嵌入向量。	必需
top_k	int	要返回的结果数量。	5

返回值

类型	描述
List[Document]	List[Document]：文档列表。

源代码位于 llama-index-integrations/readers/llama-index-readers-singlestore/llama_index/readers/singlestore/base.py

def load_data(self, search_embedding: str, top_k: int = 5) -> List[Document]:
    """
    Load data from SingleStore.

    Args:
        search_embedding (str): The embedding to search.
        top_k (int): Number of results to return.

    Returns:
        List[Document]: A list of documents.

    """
    query = f"""
    SELECT {self.content_field}, DOT_PRODUCT_F64({self.vector_field}, JSON_ARRAY_PACK_F64(\'{search_embedding}\')) AS score
    FROM {self.table_name}
    ORDER BY score
    DESC LIMIT {top_k}
    """

    return self.reader.load_data(query=query)