Skip to content

VectorSelection #

Bases: object

add_edges(edges) #

Add all the documents associated with the specified edges to the current selection.

Documents added by this call are assumed to have a distance of 0.

Parameters:

Name Type Description Default
edges list

List of the edge ids or edges to add.

required

Returns:

Type Description
None

add_nodes(nodes) #

Add all the documents associated with the specified nodes to the current selection.

Documents added by this call are assumed to have a distance of 0.

Parameters:

Name Type Description Default
nodes list

List of the node ids or nodes to add.

required

Returns:

Type Description
None

append(selection) #

Add all the documents in a specified selection to the current selection.

Parameters:

Name Type Description Default
selection VectorSelection

Selection to be added.

required

Returns:

Type Description
VectorSelection

The combined selection.

edges() #

Returns the edges present in the current selection.

Returns:

Type Description
list[Edge]

List of edges in the current selection.

expand(hops, window=None) #

Add all the documents a specified number of hops away from the selection.

Two documents A and B are considered to be 1 hop away from each other if they are on the same entity or if they are on the same node/edge pair. Provided that two nodes A and C are n hops away of each other if there is a document B such that A is n - 1 hops away of B and B is 1 hop away of C.

Parameters:

Name Type Description Default
hops int

The number of hops to carry out the expansion.

required
window Tuple[int | str, int | str]

The window that documents need to belong to in order to be considered.

None

Returns:

Type Description
None

expand_edges_by_similarity(query, limit, window=None) #

Add to the selection the limit adjacent edges closest to query

This function has the same behaviour as expand_entities_by_similarity but it only considers edges.

Parameters:

Name Type Description Default
query str | list

The text or the embedding to calculate the distance from.

required
limit int

The maximum number of new edges to add.

required
window Tuple[int | str, int | str]

The window that documents need to belong to in order to be considered.

None

Returns:

Type Description
None

expand_entities_by_similarity(query, limit, window=None) #

Add to the selection the limit adjacent entities closest to query

The expansion algorithm is a loop with two steps on each iteration:

  1. All the entities 1 hop away of some of the entities included on the selection (and not already selected) are marked as candidates.
  2. Those candidates are added to the selection in ascending distance from query.

This loops goes on until the number of new entities reaches a total of limit entities or until no more documents are available

Parameters:

Name Type Description Default
query str | list

The text or the embedding to calculate the distance from.

required
limit int

The number of documents to add.

required
window Tuple[int | str, int | str]

The window that documents need to belong to in order to be considered.

None

Returns:

Type Description
None

expand_nodes_by_similarity(query, limit, window=None) #

Add to the selection the limit adjacent nodes closest to query

This function has the same behaviour as expand_entities_by_similarity but it only considers nodes.

Parameters:

Name Type Description Default
query str | list

The text or the embedding to calculate the distance from.

required
limit int

The maximum number of new nodes to add.

required
window Tuple[int | str, int | str]

The window that documents need to belong to in order to be considered.

None

Returns:

Type Description
None

get_documents() #

Returns the documents present in the current selection.

Returns:

Type Description
list[Document]

List of documents in the current selection.

get_documents_with_distances() #

Returns the documents present in the current selection alongside their distances.

Returns:

Type Description
list[Tuple[Document, float]]

List of documents and distances.

nodes() #

Returns the nodes present in the current selection.

Returns:

Type Description
list[Node]

List of nodes in the current selection.