VectorisedGraph#

class VectorisedGraph#

Bases: object

Methods:

`documents_by_similarity`(query, limit[, window])	Search the top scoring documents according to query with no more than limit documents
`edges_by_similarity`(query, limit[, window])	Search the top scoring edges according to query with no more than limit edges
`empty_selection`()	Return an empty selection of documents
`entities_by_similarity`(query, limit[, window])	Search the top scoring entities according to query with no more than limit entities
`get_graph_documents`()	Return all the graph level documents
`nodes_by_similarity`(query, limit[, window])	Search the top scoring nodes according to query with no more than limit nodes
`save_embeddings`(file)	Save the embeddings present in this graph to file so they can be further used in a call to vectorise

documents_by_similarity(query, limit, window=None)#

Search the top scoring documents according to query with no more than limit documents

Parameters:

query (str | list) – the text or the embedding to score against
limit (int) – the maximum number of documents to search
window (Tuple[int | str, int | str], optional) – the window where documents need to belong to in order to be considered

Returns:

The vector selection resulting from the search

Return type:

VectorSelection

edges_by_similarity(query, limit, window=None)#

Search the top scoring edges according to query with no more than limit edges

Parameters:

query (str | list) – the text or the embedding to score against
limit (int) – the maximum number of new edges to search
window (Tuple[int | str, int | str], optional) – the window where documents need to belong to in order to be considered

Returns:

The vector selection resulting from the search

Return type:

VectorSelection

entities_by_similarity(query, limit, window=None)#

Search the top scoring entities according to query with no more than limit entities

Parameters:

query (str | list) – the text or the embedding to score against
limit (int) – the maximum number of new entities to search
window (Tuple[int | str, int | str], optional) – the window where documents need to belong to in order to be considered

Returns:

The vector selection resulting from the search

Return type:

VectorSelection

get_graph_documents()#

Return all the graph level documents

nodes_by_similarity(query, limit, window=None)#

Search the top scoring nodes according to query with no more than limit nodes

Parameters:

query (str | list) – the text or the embedding to score against
limit (int) – the maximum number of new nodes to search
window (Tuple[int | str, int | str], optional) – the window where documents need to belong to in order to be considered

Returns:

The vector selection resulting from the search

Return type:

VectorSelection

save_embeddings(file)#: Save the embeddings present in this graph to file so they can be further used in a call to vectorise