trawl_build_graph
Builds or rebuilds a client's knowledge graph in the background, extracting entities and relations from pool chunks with configurable workers, providers, and an optional test sample.
Instructions
Build or rebuild the knowledge graph for a client. Runs in background.
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": {
"pool_name": "<pool_name>"
},
"name": "trawl_build_graph"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sample | No | Process only N chunks (for testing) | |
| rebuild | No | Clear and rebuild from scratch (default: false) | |
| workers | No | Number of extraction workers | |
| pool_name | Yes | Pool to build graph for | |
| providers | No | Optional comma-separated provider allowlist (e.g. 'kimi,haiku'). When set, the LLM used for graph extraction must come from this list or the job fails. Accepts: local, kimi, gemini, haiku, sonnet, opus. |