Skip to content

Easily create semantic graphs from text using SentenceTransformers

License

Notifications You must be signed in to change notification settings

Hevia/SentenceGraph

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SentenceGraph

Install

pip install SentenceGraph

How to use

# from SentenceGraph.core import SentenceGraph, Format, TextNodeType
# from SentenceGraph.functional import create_text_nodes
# sentenceGraph = SentenceGraph()
# SentenceGraph requires all sentences to be passed as TextNode, which is just a namedtuple containing an id and text.
# There are several ways to prepare your sentence data for SentenceGraph.

# Use the builtin helper function which will just assign sequential ids for the data. Useful for experimentation.
# sentences = ['This framework generates embeddings for each input sentence',
#     'Sentences are passed as a list of string.', 
#     'The quick brown fox jumps over the lazy dog.']

# sentences = create_text_nodes(sentences)

# # 
# sentences = [TextNode(1, 'This framework generates embeddings for each input sentence'),
#     TextNode(2, 'Sentences are passed as a list of string.'), 
#     TextNode(3,'The quick brown fox jumps over the lazy dog.')]
# sim_graph = sentenceGraph.createGraph(sentences)
# sim_graph

You can also return a graph matrix in different formats.

# sim_graph = sentenceGraph.createGraph(sentences, format=Format.Numpy)
# sim_graph

About

Easily create semantic graphs from text using SentenceTransformers

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published