Neo4j, GraphQL, Vector Indexes, and GenAI: Exploring New Possibilities
summary
Neo4j GraphQL Library now exposes a read‑only @vector directive that plugs into GenAI providers (demo uses OpenAI) to encode/query 1,536‑dim embeddings; it requires Neo4j 5.50+, precomputed node embedding properties, and a manually created vector index (no cross‑label searches). Demo ingests the Recommendations dataset, runs a search movies by plot phrase, returns four ranked results with similarity scores and traverses actor relationships to fetch related movie titles — the example works end‑to‑end.
AI-written summary · about
related talks
28mData-Empowered AI Assistants
39mEnhancing RAG with Neo4j Knowledge Graph
30mAgentic RAG with Knowledge Graphs Explained
28mUse OpenSearch as Your Vector Search Database To Optimize GenAI Accuracy!
30mHow to Decipher User Uncertainty with GenAI and Vector Search
57mEnter the Brave New World of GenAI with Vector Search
45mUsing Postgres + OpenAI to power your AI Recommendation...
31mGraphQL Embeddings: AI-Powered Dynamic Operations From Schema To IDE