> ## Documentation Index
> Fetch the complete documentation index at: https://docs.stateset.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Classify input features using VSA similarity against feature-based class…

> **Required scope:** write

**Required scope:** `write`

### Request body

`VSAClassifyRequest`

<ParamField body="class_prototypes" type="VSAClassPrototype[]" required>
  Class prototypes expressed as feature bundles
</ParamField>

<ParamField body="input_features" type="string[]" required>
  Input feature concept names (e.g., \['has\_fur', 'meows'])
</ParamField>

<ParamField body="top_k" type="integer">
  Number of results to return (default: 5)
</ParamField>

### Response

`VSAClassifyResponse`

<ResponseField name="dimension" type="integer" required>
  Vector dimension
</ResponseField>

<ResponseField name="enabled" type="boolean" required>
  Whether VSA is enabled
</ResponseField>

<ResponseField name="prediction" type="string">
  Predicted class label (highest similarity)
</ResponseField>

<ResponseField name="results" type="object[][]" required>
  Ranked results (label, similarity)
</ResponseField>

<ResponseField name="score" type="number (double)">
  Similarity score for the predicted class
</ResponseField>

### Status codes

| Code  | Meaning                                            |
| ----- | -------------------------------------------------- |
| `200` | Classification result                              |
| `400` | Invalid request                                    |
| `401` | Unauthorized — missing or invalid credentials      |
| `403` | Forbidden — the key/token lacks the required scope |
| `429` | Rate limited — see Retry-After / X-RateLimit-Reset |
| `503` | VSA not enabled                                    |

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url 'https://api.nsr.stateset.com/api/v1/nsr/vsa/classify' \
    --header 'X-API-Key: YOUR_API_KEY' \
    --header 'Content-Type: application/json' \
    --data '{
    "class_prototypes": [
      {
        "features": [],
        "label": "Replacement tent pole set"
      }
    ],
    "input_features": [
      "string"
    ],
    "top_k": 1
  }'
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "dimension": 1,
    "enabled": true,
    "prediction": "string",
    "results": [
      [
        {
          "0": "s",
          "1": "t",
          "2": "r",
          "3": "i",
          "4": "n",
          "5": "g"
        }
      ]
    ],
    "score": 7.5
  }
  ```
</ResponseExample>