ai_search
Run natural-language discovery across concepts, entities, and cached values to find relevant data; use it as the default search entry point before narrower semantic searches.
Instructions
Default search entry point — call this for fuzzy/natural-language discovery. Superset of semantic_search/semantic_search_entities/semantic_search_unified (concepts + entities + cached values); do not call those in parallel with this.
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": "ai_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of concepts to return | |
| query | Yes | Natural language query (e.g., "Asian inflation indicators") | |
| scope | No | Optional named retrieval scope constraining the concepts list; the response names the scope that governed it (see scope_list) | |
| value_date | No | Date for values (e.g., "2024-01-01") - only if include_values=True | |
| entity_type | No | Filter by entity type (country, stock, industry, etc.) | |
| include_values | No | If True, fetch actual values from semantic_observations |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||