GraphAcademy

Gen-AI - Hands-on Workshop

Knowledge Graphs, Unstructured Data, and Vectors

LLMs, RAG, Python, and LangChain

Search using a Vector Index

Movie Plots

The Neo4j sandbox contains a sample of 1000 embeddings for movie plots. Running the following Cypher query will return the titles and plots for the movies that have embeddings:

cypher
MATCH (m:Movie)
WHERE m.plotEmbedding IS NOT NULL
RETURN m.title, m.plot

Review the movies and find a plot that you think looks interesting.

You can adapt the query to only return a named movie by adding a filter:

cypher
MATCH (m:Movie {title: "Toy Story"})
RETURN m.title, m.plot

Finding similar movies

You can view the embedding for a movie plot by running the following query:

cypher
MATCH (m:Movie {title: "Toy Story"})
RETURN m.title, m.plotEmbedding

You can find similar movies using the embedding for the movie plot and a vector index.

Query the vector index

You can query the vector index to find similar movies by running the following query:

cypher
MATCH (m:Movie {title: 'Toy Story'})

CALL db.index.vector.queryNodes('moviePlots', 6, m.plotEmbedding)
YIELD node, score

RETURN node.title, node.plot, score

The db.index.vector.queryNodes procedure takes three arguments:

  • The name of the vector index to query - moviePlots

  • The number of results to return - 6

  • The embedding to search for - m.plotEmbedding

Experiment with the query to find similar movies to the one you searched earlier.

Summary

You learned how to use a vector index to find similar unstructured data.