Delegated embeddings
embedGenerate vector representations for one text or an array of texts through a local model provider; returns exactly one vector per input.
Instructions
DELEGATED EMBEDDINGS: Generate embeddings for a string or an array of texts. Without provider, runs on the live local provider that has the model. Always returns one vector per input.
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": {
"model": "<model>",
"input": "<input>"
},
"name": "embed"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Text or array of texts to embed | |
| model | Yes | Embedding model id/name | |
| provider | No | Provider instance name. Omit to let the server choose (local providers only, unless LOCAL_AI_ALLOW_HOSTED_FALLBACK is set). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| host | Yes | ||
| local | Yes | ||
| model | Yes | ||
| provider | Yes | ||
| dimensions | Yes | ||
| embeddings | Yes |