node_semantic_search
Search for nodes in a diagram that are semantically similar to a given embedding vector. Returns top matches with similarity scores.
Instructions
Search for nodes semantically similar to a target embedding.
Args: diagram_id: ID of diagram target_embedding: The embedding vector (list of floats) to compare against top_k: Maximum number of results to return (default: 5) threshold: Minimum cosine similarity score to include (default: 0.5)
Returns: dict with similar nodes and similarity scores
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": {
"diagram_id": "<diagram_id>",
"target_embedding": "<target_embedding>"
},
"name": "node_semantic_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| top_k | No | ||
| threshold | No | ||
| diagram_id | Yes | ||
| target_embedding | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||