Semantic Similarity between questions pair to find duplicate questions?

I had done semantic similarity to identify duplicate questions in data set using LSTM networks in python jupyter notebook. Now i want to do this task on neo4j to build knowledge graphs.
please suggest me to do this task.

Perhaps you can give an example of what you've done and what you'd like to accomplish with Neo4j.

For example, indicate whether you want to store what you've done in python or replicate it in neo4j? What queries would you ask of this knowledge graph? What properties do you use to determine whether or not a question is a duplicate?