Search-Augmented Cypher Query
search_cypher_queryRead-onlyIdempotent
Run custom Cypher queries that leverage Neo4j vector and fulltext search indexes for advanced retrieval, filtering, and graph traversal in GraphRAG applications.
Instructions
Execute a Cypher query that uses vector and/or fulltext search indexes.
This powerful tool allows you to:
Use vector search ($vector_embedding) and/or fulltext search ($fulltext_text) in Cypher
Post-filter large result sets (fetch 100-1000, filter with WHERE)
Combine search with graph traversal
Aggregate over search results
Example:
search_cypher_query(
cypher_query='''
CALL db.index.vector.queryNodes('chunk_embedding_vector', 500, $vector_embedding)
YIELD node, score
WHERE score > 0.75
MATCH (node)-[:BELONGS_TO]->(d:Document)
WHERE d.year >= 2020
RETURN node.chunkId, d.title, score
ORDER BY score DESC
LIMIT 20
''',
vector_query="student requirements"
)Placeholders:
$vector_embedding: Replaced with embedding vector$fulltext_text: Replaced with text string for fulltext
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| params | No | Additional parameters for the Cypher query. | |
| cypher_query | Yes | Cypher query using $vector_embedding and/or $fulltext_text placeholders. | |
| vector_query | No | Text query to embed for vector search. Use $vector_embedding placeholder in Cypher. | |
| fulltext_query | No | Text query for fulltext search. Use $fulltext_text placeholder in Cypher. |