Class Milvus

libs/community/langchain_community/vectorstores/milvus.py:31–1090

`Milvus` vector store. You need to install `pymilvus` and run Milvus. See the following documentation for how to run a Milvus instance: https://milvus.io/docs/install_standalone-docker.md If looking for a hosted Milvus, take a look at this documentation: https://zilliz.com/clo

    alternative_import="langchain_milvus.MilvusVectorStore",
)
class Milvus(VectorStore):
    """`Milvus` vector store.

    You need to install `pymilvus` and run Milvus.

    See the following documentation for how to run a Milvus instance:
    https://milvus.io/docs/install_standalone-docker.md

    If looking for a hosted Milvus, take a look at this documentation:
    https://zilliz.com/cloud and make use of the Zilliz vectorstore found in
    this project.

    IF USING L2/IP metric, IT IS HIGHLY SUGGESTED TO NORMALIZE YOUR DATA.

    Args:
        embedding_function (Embeddings): Function used to embed the text.
        collection_name (str): Which Milvus collection to use. Defaults to
            "LangChainCollection".
        collection_description (str): The description of the collection. Defaults to
            "".
        collection_properties (Optional[dict[str, any]]): The collection properties.
            Defaults to None.
            If set, will override collection existing properties.
            For example: {"collection.ttl.seconds": 60}.
        connection_args (Optional[dict[str, any]]): The connection args used for
            this class comes in the form of a dict.
        consistency_level (str): The consistency level to use for a collection.
            Defaults to "Session".
        index_params (Optional[dict]): Which index params to use. Defaults to
            HNSW/AUTOINDEX depending on service.
        search_params (Optional[dict]): Which search params to use. Defaults to
            default of index.
        drop_old (Optional[bool]): Whether to drop the current collection. Defaults
            to False.
        auto_id (bool): Whether to enable auto id for primary key. Defaults to False.
            If False, you needs to provide text ids (string less than 65535 bytes).
            If True, Milvus will generate unique integers as primary keys.
        primary_field (str): Name of the primary key field. Defaults to "pk".
        text_field (str): Name of the text field. Defaults to "text".
        vector_field (str): Name of the vector field. Defaults to "vector".
        metadata_field (str): Name of the metadata field. Defaults to None.
            When metadata_field is specified,
            the document's metadata will store as json.

    The connection args used for this class comes in the form of a dict,
    here are a few of the options:
        address (str): The actual address of Milvus
            instance. Example address: "localhost:19530"
        uri (str): The uri of Milvus instance. Example uri:
            "http://randomwebsite:19530",
            "tcp:foobarsite:19530",
            "https://ok.s3.south.com:19530".
        host (str): The host of Milvus instance. Default at "localhost",
            PyMilvus will fill in the default host if only port is provided.
        port (str/int): The port of Milvus instance. Default at 19530, PyMilvus
            will fill in the default port if only host is provided.
        user (str): Use which user to connect to Milvus instance. If user and
            password are provided, we will add related header in every RPC call.