semantic_search
Search stored memories using natural language queries. Retrieves results by meaning via embeddings, and reinforces returned memories by marking them as seen.
Instructions
Meaning-based search via the backend's /memory/query (embeddings + salience + recency + links). Good for questions phrased in your own words. Only meaningful when health_check shows a real embedding provider (openai, gemini, ollama); with 'synthetic' results are random. The backend marks every returned memory as seen and raises its salience slightly, so it also acts as reinforcement.
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 |
|---|---|---|---|
| k | No | ||
| query | Yes | ||
| sector | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |