morpheus_llm.service.vdb.vector_db_service.VectorDBService#

class VectorDBService[source]#

Bases: ABC

Class used for vectorstore specific implementation.

Methods

`close`()	Close connection to the vector database.
`count`(name, **kwargs)	Returns number of rows/entities in the given resource.
`create`(name[, overwrite])	Create resources in the vector database.
`create_from_dataframe`(name, df[, overwrite])	Create resources in the vector database.
`delete`(name, expr, **kwargs)	Delete data in the vector database.
`delete_by_keys`(name, keys, **kwargs)	Delete vectors by keys from the resource.
`describe`(name, **kwargs)	Describe resource in the vector database.
`drop`(name, **kwargs)	Drop resources from the vector database.
`has_store_object`(name)	Check if a resource exists in the vector database.
`insert`(name, data, **kwargs)	Insert data into the vector database.
`insert_dataframe`(name, df, **kwargs)	Converts dataframe to rows and insert into the vector database resource.
`list_store_objects`(**kwargs)	List existing resources in the vector database.
`query`(name, query, **kwargs)	Query a resource in the vector database.
`release_resource`(name)	Release a loaded resource from the memory.
`retrieve_by_keys`(name, keys, **kwargs)	Retrieve the inserted vectors using keys from the resource.
`similarity_search`(name, **kwargs)	Perform a similarity search within the vector database.
`transform`(data, **kwargs)	Transform data according to the specific vector database implementation.
`update`(name, data, **kwargs)	Update data in the vector database.

load_resource

abstractmethod close()[source]#

Close connection to the vector database.

abstractmethod count(name, **kwargs)[source]#

Returns number of rows/entities in the given resource.

Parameters:

namestr: Name of the resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

int: Returns number of rows/entities in the given resource.

abstractmethod create(name, overwrite=False, **kwargs)[source]#

Create resources in the vector database.

Parameters:

namestr: Name of the resource.
overwritebool, default False: Whether to overwrite the resource if it already exists.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

abstractmethod create_from_dataframe(

name,

df,

overwrite=False,

**kwargs,

)[source]#

Create resources in the vector database.

Parameters:

namestr: Name of the resource.
dfDataFrameType: The dataframe to create the resource from.
overwritebool, optional: Whether to overwrite the resource if it already exists. Default is False.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

abstractmethod delete(name, expr, **kwargs)[source]#

Delete data in the vector database.

Parameters:

namestr: Name of the resource.
exprtyping.Any: Delete expression.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

dict[str, typing.Any]: Returns result of the delete operation stats.

abstractmethod delete_by_keys(name, keys, **kwargs)[source]#

Delete vectors by keys from the resource.

Parameters:

namestr: Name of the resource.
keysint | str | list: Primary keys to delete vectors.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

typing.Any: Returns vectors of the given keys that are delete from the resource.

abstractmethod describe(name, **kwargs)[source]#

Describe resource in the vector database.

Parameters:

namestr: Name of the resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

dict: Returns resource information.

abstractmethod drop(name, **kwargs)[source]#

Drop resources from the vector database.

Parameters:

namestr: Name of the resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

abstractmethod has_store_object(name)[source]#

Check if a resource exists in the vector database.

Parameters:

namestr: Name of the resource.

Returns:

bool: Returns True if resource exists in the vector database, otherwise False.

abstractmethod insert(name, data, **kwargs)[source]#

Insert data into the vector database.

Parameters:

namestr: Name of the resource.
datalist[list] | list[dict]: Data to be inserted into the resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

dict: Returns response content as a dictionary.

abstractmethod insert_dataframe(name, df, **kwargs)[source]#

Converts dataframe to rows and insert into the vector database resource.

Parameters:

namestr: Name of the resource to be inserted.
dfDataFrameType: Dataframe to be inserted.
**kwargsdict[str, typing.Any]: Additional keyword arguments containing collection configuration.

Returns:

dict: Returns response content as a dictionary.

Raises:

RuntimeError: If the resource not exists exists.

abstractmethod list_store_objects(**kwargs)[source]#

List existing resources in the vector database.

Parameters:

**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

list[str]: Returns available resouce names in the vector database.

abstractmethod query(name, query, **kwargs)[source]#

Query a resource in the vector database.

Parameters:

namestr: Name of the resource.
querystr: Query to execute on the given resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

typing.Any: Returns search results.

abstractmethod release_resource(name)[source]#

Release a loaded resource from the memory.

Parameters:

namestr: Name of the resource to release.

abstractmethod retrieve_by_keys(name, keys, **kwargs)[source]#

Retrieve the inserted vectors using keys from the resource.

Parameters:

namestr: Name of the resource.
keystyping.Any: Primary keys to get vectors.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

list[typing.Any]: Returns rows of the given keys that exists in the resource.

abstractmethod async similarity_search(name, **kwargs)[source]#

Perform a similarity search within the vector database.

Parameters:

namestr: Name of the resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

list[list[dict]]: Returns a list of lists, where each inner list contains dictionaries representing the results of the similarity search.

transform(data, **kwargs)[source]#

Transform data according to the specific vector database implementation.

Parameters:

datatyping.Any: Data to be updated in the resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

typing.Any: Returns transformed data as per the implementation.

abstractmethod update(name, data, **kwargs)[source]#

Update data in the vector database.

Parameters:

namestr: Name of the resource.
datalist[typing.Any]: Data to be updated in the resource.
**kwargsdict[str, typing.Any]: Extra keyword arguments specific to the vector database implementation.

Returns:

dict[str, typing.Any]: Returns result of the updated operation stats.