create

client

MilvusClient

Required

Parameter under kwargs (see Class Introduction). The parameter must be passed; otherwise, KeyError is reported.

params

Dict

Optional

Additional parameter of the index type. The default value is {}, which corresponds to params of the add_index method. For details, see Milvus Index-a-Collection. For dictionary verification, the dictionary, its strings, and all iterable sequences must not exceed 1024 in length, and the number of nested dictionary layers cannot exceed 2. Parameter configurations now include "sparse" and "dense" types to specify whether they apply to sparse or dense retrieval modes. A configuration example is as follows:

{

"dense": {"nlist": 128},

"sparse": {"inverted_index_algo": "DAAT_MAXSCORE"}

}

x_dim

Integer

Optional

Vector dimensionality. The MilvusClient.create_collection method is called. For details, see create_collection.

collection_name

String

Optional

Collection name. The default value is rag_sdk. The MilvusClient.set_collection_name is called. For details, see set_collection_name.

search_mode

SearchMode

Optional

Retrieval mode. Currently, three modes are supported: DENSE for dense retrieval (default), SPARSE for sparse retrieval, and HYBRID for hybrid retrieval.

For more details, see search_mode.

auto_id

Bool

Optional

Whether to automatically increment primary keys. The default value is False.

index_type

String

Optional

Vector retrieval type. Currently, FLAT (default), IVF_FLAT, IVF_PQ, and HNSW are supported. This parameter is valid for dense vectors in dense and hybrid retrieval modes. SPARSE_INVERTED_INDEX is used for sparse vector retrieval and cannot be changed.

metric_type

String

Optional

Vector distance calculation method, which can be IP, L2 (default), and COSINE. This parameter is valid for dense vectors in dense and hybrid retrieval modes. IP is used for sparse vector distance calculation and cannot be changed.

auto_flush

Bool

Optional

Whether to automatically update memory data during data changes. The default value is True.

MilvusDB

MilvusDB object.