compute_clusters
Computes live connected-component vector clusters for Species or Organism entities across biomes without altering the database, with adjustable similarity levels and optional full catalog coverage.
Instructions
Compute live connected-components vector clusters for Species or Organisms across biomes without modifying the database.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "compute_clusters"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Bypass Rails memory cache and recalculate adjacency graph | |
| level | No | Similarity granularity level from 1 (tight functional analogs, <= 0.16 cosine dist) to 15 (full catalog coverage absorption, <= 0.30) | |
| target_type | No | Target entity class to cluster: Species or Organism | Species |
| full_coverage | No | Forces 100% catalog assignment / zero singletons via nearest-cluster absorption |