GQLite 1.7 - Released

This new release of GQLite brings support for vector index, and a tensor value.

This allows support for querying for embedding in machine-learning based application. The syntax is similar to neo4j. New index are created with:

CREATE VECTOR INDEX moviePlots IF NOT EXISTS
  FOR (m:Movie)
  ON m.embedding
  OPTIONS { indexConfig: {
    `vector.dimensions`: 1536,
    `vector.similarity_function`: 'cosine'
  }}

The index is used in conjonction with the SEARCH clause such as:

MATCH (m:Movie {title: 'Godfather, The'})
MATCH (movie: Movie)
  SEARCH movie IN (
    VECTOR INDEX moviePlots
    FOR m.embedding
    LIMIT 5
  ) SCORE AS score
RETURN movie.title AS title, movie.plot AS plot, score

You can check our installation instructions. And the up-to-date changelog for the query engine.