semantic_index
Index documents into a collection for semantic search. Automatically chunks and embeds text locally, with optional document_id to replace existing entries.
Instructions
Index a document into a collection for semantic search. Text is automatically chunked and embedded using a local ML model (no API calls). Use document_id to replace an existing document.
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": {
"collection": "<collection>",
"document": "<document>"
},
"name": "semantic_index"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| document | Yes | The text content to index | |
| metadata | No | Optional metadata to associate with the document (e.g. source, title) | |
| collection | Yes | Name of the collection to index into | |
| document_id | No | Optional unique ID for the document. If provided and already exists, the document is replaced. |