All hype in my opinion, and apparently the #2 committer of the project may agree.<p>He agrees that @neo4j is slower than a “normal vector db”.<p>“if you are not dealing with many documents, it works quite well”<p>“Neo4j might not be optimized for vector search, but that doesn't mean it can't do it.”<p><a href="https://x.com/tb_tomaz/status/1646626362243919873?s=20" rel="nofollow noreferrer">https://x.com/tb_tomaz/status/1646626362243919873?s=20</a>
I know Neo4j is trying stay relevant in the AI space and this could be just hype however, I am curious what others think about using Neo4j over other purpose built vector stores / databases (chroma, pinecone, etc).