# Embeddings

> Use task_type embed to generate vector representations for spatial scenes and objects.

Source: https://fourechelon.com/docs/embeddings · Machine-readable: https://fourechelon.com/openapi.json · Index: https://fourechelon.com/llms.txt

## task

embed

## question

What is the vector representation of this scene or object?

## required

| Field | Type | Description |
| --- | --- | --- |
| input.cad_scene | object | Scene to embed. point_cloud_scene also works. |
| input.object_id | string | Optional. Embed one object instead of the whole scene. |

## returns

| Field | Type | Description |
| --- | --- | --- |
| embedding.vector | Float array for similarity search. |
| embedding.dimensions | Vector length, so you can size your index. |

## notes

Embeddings are for retrieval and clustering over your own corpus. Vectors are not stable across model versions — re-embed when the model id changes.

## Example

```bash
curl https://fourechelon.com/api/v1/responses \
  -H "Authorization: Bearer $FOUR_ECHELON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rowe-1.0",
    "input": {
      "task_type": "embed",
      "cad_scene": { "schema": "four-cad.cad_scene.v1", "solids": [] }
    }
  }'
```