​
MilvusStorage

class MilvusStorage(BaseVectorStorage):

An implementation of the BaseVectorStorage for interacting with Milvus, a cloud-native vector search engine.

The detailed information about Milvus is available at: Milvus <https://milvus.io/docs/overview.md/>_

Parameters:

  • vector_dim (int): The dimension of storing vectors.
  • url_and_api_key (Tuple[str, str]): Tuple containing the URL and API key for connecting to a remote Milvus instance. URL maps to Milvus uri concept, typically “endpoint:port”. API key maps to Milvus token concept, for self-hosted it’s “username:pwd”, for Zilliz Cloud (fully-managed Milvus) it’s API Key.
  • collection_name (Optional[str], optional): Name for the collection in the Milvus. If not provided, set it to the current time with iso format. (default: :obj:None) **kwargs (Any): Additional keyword arguments for initializing MilvusClient.

​
init

def __init__(
    self,
    vector_dim: int,
    url_and_api_key: Tuple[str, str],
    collection_name: Optional[str] = None,
    **kwargs: Any
):

​
_create_client

def _create_client(self, url_and_api_key: Tuple[str, str], **kwargs: Any):

Initializes the Milvus client with the provided connection details.

Parameters:

  • url_and_api_key (Tuple[str, str]): The URL and API key for the Milvus server. **kwargs: Additional keyword arguments passed to the Milvus client.

​
_check_and_create_collection

def _check_and_create_collection(self):

Checks if the specified collection exists in Milvus and creates it if it doesn’t, ensuring it matches the specified vector dimensionality.

​
_create_collection

def _create_collection(self, collection_name: str, **kwargs: Any):

Creates a new collection in the database.

Parameters:

  • collection_name (str): Name of the collection to be created. **kwargs (Any): Additional keyword arguments pass to create collection.

​
_delete_collection

def _delete_collection(self, collection_name: str):

Deletes an existing collection from the database.

Parameters:

  • collection (str): Name of the collection to be deleted.

​
_collection_exists

def _collection_exists(self, collection_name: str):

Checks whether a collection with the specified name exists in the database.

Parameters:

  • collection_name (str): The name of the collection to check.

Returns:

bool: True if the collection exists, False otherwise.

​
_generate_collection_name

def _generate_collection_name(self):

Returns:

str: A unique, valid collection name.

​
_get_collection_info

def _get_collection_info(self, collection_name: str):

Retrieves details of an existing collection.

Parameters:

  • collection_name (str): Name of the collection to be checked.

Returns:

Dict[str, Any]: A dictionary containing details about the collection.

​
_validate_and_convert_vectors

def _validate_and_convert_vectors(self, records: List[VectorRecord]):

Validates and converts VectorRecord instances to the format expected by Milvus.

Parameters:

  • records (List[VectorRecord]): List of vector records to validate and convert.

Returns:

List[dict]: A list of dictionaries formatted for Milvus insertion.

​
add

def add(self, records: List[VectorRecord], **kwargs):

Adds a list of vectors to the specified collection.

Parameters:

  • records (List[VectorRecord]): List of vectors to be added. **kwargs (Any): Additional keyword arguments pass to insert.

​
delete

def delete(self, ids: List[str], **kwargs: Any):

Deletes a list of vectors identified by their IDs from the storage. If unsure of ids you can first query the collection to grab the corresponding data.

Parameters:

  • ids (List[str]): List of unique identifiers for the vectors to be deleted. **kwargs (Any): Additional keyword arguments passed to delete.

​
status

def status(self):

Returns:

VectorDBStatus: An object containing information about the collection’s status.

​
query

def query(self, query: VectorDBQuery, **kwargs: Any):

Searches for similar vectors in the storage based on the provided query.

Parameters:

  • query (VectorDBQuery): The query object containing the search vector and the number of top similar vectors to retrieve. **kwargs (Any): Additional keyword arguments passed to search.

Returns:

List[VectorDBQueryResult]: A list of vectors retrieved from the storage based on similarity to the query vector.

​
clear

def clear(self):

Removes all vectors from the Milvus collection. This method deletes the existing collection and then recreates it with the same schema to effectively remove all stored vectors.

​
load

def load(self):

Load the collection hosted on cloud service.

​
client

def client(self):

Returns:

Any: The Milvus client instance.