Embed text as a vector
embed_textConverts text into a raw embedding vector using the engine’s configured model, returning the vector, dimensions, and model name for storage or custom comparison. Nothing is stored.
Instructions
Turn a piece of text into an embedding vector with the engine's configured embedding model and return {embedding, dimensions, model}. Use it when you need the raw vector, for example to store it or compare it yourself; to search, use semantic_search for vector collections or query with EMBED() and COSINE_SIMILARITY() for table columns. Nothing is stored.
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": {
"text": "<text>"
},
"name": "embed_text"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to embed, such as a sentence or short passage. | |
| model | No | Accepted for compatibility; the engine always uses its configured embedding model, reported in the response's `model` field. |