Description: Generate personalized real-time recommendations using a dataset of movie reviews
Nodes 28863 Relationships 166261
MATCH (m:Movie {title:$movie})<-[:RATED]-(u:User)-[:RATED]->(rec:Movie)
RETURN distinct rec.title AS recommendation LIMIT 20This is for Neo4j version: 4.0
The database is also available on https://demo.neo4jlabs.com:7473
Username "recommendations", password: "recommendations", database: "recommendations"
Rendered guide available via: :play https://guides.neo4j.com/sandbox/recommendations/index.html
Unrendered guide: documentation/recommendations.neo4j-browser-guide
Load graph data via the following:
The file was dumped from Neo4j 5.13.
It is based on recommendations-50.dump, enriched with embeddings provided from https://data.neo4j.com/rec-embed/README.html on Movie nodes, under the property embedding.
Embeddings are 1536-vectors generated with OpenAI’s model text-embedding-ada-002.
The dump does not contain a vector index.
-
Drop the file into the
Filessection of a project in Neo4j Desktop. Then choose the option toCreate new DBMS from dumpoption from the file options. -
Use the neo4j-admin tool to load data from the command line with the command below.
bin/neo4j-admin load --from data/recommendations-40.dump [--database "database"]-
Upload the dump file to Neo4j Aura via https://console.neo4j.io/#import-instructions
See /graphql directory for Node.js GraphQL API server example using @neo4j/graphql