메뉴
Use HNSW vector indexes for Approximate Nearest Neighbor (ANN) search with embeddings
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | Create and query vector indexes |
| description | Use HNSW vector indexes for Approximate Nearest Neighbor (ANN) search with embeddings |
Use HNSW vector indexes for Approximate Nearest Neighbor (ANN) search.
Create vector indexes with specific dimension and similarity configurations, then query them using db.idx.vector.queryNodes.
redis-cli GRAPH.QUERY social "CREATE VECTOR INDEX FOR (p:Product) ON (p.embedding)
OPTIONS {dimension: 768, similarityFunction: 'cosine', M: 32, efConstruction: 200}"
redis-cli GRAPH.QUERY social "CALL db.idx.vector.queryNodes('Product', 'embedding', 5, vecf32([0.1, 0.2, 0.3]))
YIELD node, score RETURN node.name, score"
M and efConstruction parameters tune index performance and accuracyvecf32() to pass vector values in queriesPractical FalkorDB guidance — Cypher queries, UDF management, Docker operations, and data ingestion. Use when writing or reviewing FalkorDB queries, setting up FalkorDB containers, working with user-defined functions, or migrating data from other sources.
Extract data from Neo4j to CSV and load it into FalkorDB
Convert AWS Neptune Export CSVs and load them into FalkorDB
Migrate and continuously sync data from SQL systems into FalkorDB
Build FalkorDB databases from CSV inputs using the falkordb-bulk-loader utility
Account for FalkorDB Cypher limitations like non-indexed not-equal filters when designing queries