morpheus_llm.service.vdb.faiss_vdb_service.FaissVectorDBResourceService#

class FaissVectorDBResourceService(parent, *, name)[source]#

Bases: VectorDBResourceService

Represents a service for managing resources in a FAISS Vector Database.

Parameters:

parentFaissVectorDBService: The parent service for this resource.
namestr: The name of the resource.

Methods

`count`(**kwargs)	Returns number of rows/entities.
`delete`(expr, **kwargs)	Delete vectors by giving a list of IDs.
`delete_by_keys`(keys, **kwargs)	Delete vectors by keys from the collection.
`describe`(**kwargs)	Provides a description of the collection.
`drop`(**kwargs)	Drops the resource from the vector database service.
`insert`(data, **kwargs)	Insert data into the vector database.
`insert_dataframe`(df, **kwargs)	Insert a dataframe entires into the vector database.
`query`(query, **kwargs)	Query data in a collection in the vector database.
`retrieve_by_keys`(keys, **kwargs)	Retrieve the inserted vectors using their primary keys.
`similarity_search`(embeddings[, k])	Perform a similarity search within the FAISS docstore.
`update`(data, **kwargs)	Update data in the collection.

count(**kwargs)[source]#

Returns number of rows/entities.

Parameters:

**kwargs: Additional keyword arguments for the count operation.

Returns:

int: Returns number of entities in the collection.

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

Delete vectors by giving a list of IDs.

Parameters:

exprstr: Delete expression.
**kwargs: Extra keyword arguments specific to the vector database implementation.

Returns:

dict[str, typing.Any]: Returns result of the given keys that are deleted from the collection.

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

Delete vectors by keys from the collection.

Parameters:

keysint | str | list: Primary keys to delete vectors.
**kwargs: Extra keyword arguments specific to the vector database implementation.

Returns:

typing.Any: Returns result of the given keys that are deleted from the collection.

describe(**kwargs)[source]#

Provides a description of the collection.

Parameters:

**kwargs: Extra keyword arguments specific to the vector database implementation.

Returns:

dict: Returns response content as a dictionary.

drop(**kwargs)[source]#

Drops the resource from the vector database service.

This function allows you to drop a collection.

Parameters:

**kwargs: Additional keyword arguments for specifying the type and partition name (if applicable).

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

Insert data into the vector database.

Parameters:

datalist[list] | list[dict]: Data to be inserted into the collection.
**kwargs: Extra keyword arguments specific to the vector database implementation.

Returns:

dict: Returns response content as a dictionary.

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

Insert a dataframe entires into the vector database.

Parameters:

dfDataFrameType: Dataframe to be inserted into the collection.
**kwargs: Extra keyword arguments specific to the vector database implementation.

Returns:

dict: Returns response content as a dictionary.

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

Query data in a collection in the vector database.

Parameters:

querystr, optional: The search query, which can be a filter expression, by default None.
**kwargs: Additional keyword arguments for the search operation.

Returns:

typing.Any: The search result, which can vary depending on the query and options.

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

Retrieve the inserted vectors using their primary keys.

Parameters:

keysint | str | list: Primary keys to get vectors for. Depending on pk_field type it can be int or str or a list of either.
**kwargs: Additional keyword arguments for the retrieval operation.

Returns:

list[typing.Any]: Returns result rows of the given keys from the collection.

async similarity_search(

embeddings,

k=4,

**kwargs,

)[source]#

Perform a similarity search within the FAISS docstore.

Parameters:

embeddingslist[list[float]]: Embeddings for which to perform the similarity search.
kint, optional: The number of nearest neighbors to return, by default 4.
**kwargs: Extra keyword arguments specific to the vector database implementation.

Returns:

list[dict]: Returns a list of dictionaries representing the results of the similarity search.

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

Update data in the collection.

Parameters:

datalist[typing.Any]: Data to be updated in the collection.
**kwargs: Extra keyword arguments specific to upsert operation.

Returns:

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