@@ -560,10 +560,12 @@ def __init__(
560560 'NAME_DEDUPLICATION' : 'name-deduplication' ,
561561 'PING' : 'ping' ,
562562 'RELATIONSHIPS' : 'relationships' ,
563+ 'SEMANTIC_VECTORS' : 'semantics/vector' ,
563564 'SENTENCES' : 'sentences' ,
564565 'SENTIMENT' : 'sentiment' ,
566+ 'SIMILAR_TERMS' : 'semantics/similar' ,
565567 'SYNTAX_DEPENDENCIES' : 'syntax/dependencies' ,
566- 'TEXT_EMBEDDING' : 'text-embedding ' ,
568+ 'TEXT_EMBEDDING' : 'semantics/vector ' ,
567569 'TOKENS' : 'tokens' ,
568570 'TOPICS' : 'topics' ,
569571 'TRANSLITERATION' : 'transliteration'
@@ -932,6 +934,14 @@ def text_embedding(self, parameters):
932934 @return: A python dictionary containing the results of text embedding."""
933935 return EndpointCaller (self , self .endpoints ['TEXT_EMBEDDING' ]).call (parameters )
934936
937+ def semantic_vectors (self , parameters ):
938+ """
939+ Create an L{EndpointCaller} to identify text vectors found in the texts
940+ to which it is applied and call it.
941+ @type parameters: L{DocumentParameters} or L{str}
942+ @return: A python dictionary containing the results of semantic vectors."""
943+ return EndpointCaller (self , self .endpoints ['SEMANTIC_VECTORS' ]).call (parameters )
944+
935945 def syntax_dependencies (self , parameters ):
936946 """
937947 Create an L{EndpointCaller} to identify the syntactic dependencies in the texts
@@ -954,3 +964,12 @@ def topics(self, parameters):
954964 @type parameters: DocumentParameters
955965 @return; A python dictionary containing the results"""
956966 return EndpointCaller (self , self .endpoints ['TOPICS' ]).call (parameters )
967+
968+ def similar_terms (self , parameters ):
969+ """
970+ Create an L{EndpointCaller} to identify terms most similar to the input in
971+ the requested languages
972+ :param parameters: DocumentParameters
973+ :return: A python dictionary containing the similar terms and their similarity
974+ """
975+ return EndpointCaller (self , self .endpoints ['SIMILAR_TERMS' ]).call (parameters )
0 commit comments