semantic_search
Find log entries matching natural-language problem descriptions via vector similarity, not exact text, to locate relevant logs when exact messages are unknown.
Instructions
Find log entries whose meaning is similar to a natural-language description, using vector similarity (not substring matching). Use this when the user describes a problem in their own words rather than citing exact log text — e.g. 'requests failing because the database was down'. Covers all logs once they have been embedded (a background job embeds new logs shortly after ingest).
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>",
"project_id": "<project_id>"
},
"name": "semantic_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (default 20, max 50). | |
| query | Yes | Natural-language description of what to find. | |
| project_id | Yes | The project to query. Call list_projects first to see which ids you can use. |