semantic_search
Search entities in your knowledge graph by semantic similarity to a text query, using vector embeddings and optional hybrid keyword search.
Instructions
Search for entities semantically using vector embeddings and similarity in your knowledge graph
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"query": "<query>"
},
"name": "semantic_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The text query to search for semantically | |
| limit | No | Maximum number of results to return (default: 10; when a reranker is configured, default: 5, reranked best-first) | |
| min_similarity | No | Minimum similarity threshold 0.0-1.0 on Neo4j's normalised cosine scale, where 0.5 means unrelated and 1.0 identical (default: 0 — disabled; absolute floors are not meaningful for high-clustering embedding models) | |
| entity_types | No | Filter results by entity types | |
| hybrid_search | No | Whether to combine keyword and semantic search (default: true) | |
| semantic_weight | No | Weight of semantic results in hybrid search from 0.0 to 1.0 (default: 0.6) | |
| domain | No | Filter results by domain (user-defined string) | |
| include_null_domain | No | When true, only return entities with null domain (uncategorized). Mutually exclusive with domain parameter. |