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

# sdvm-audit-1

<div className="flex flex-wrap gap-1.5 not-prose" style={{ marginTop: "-1.25rem" }}>
  <span className="inline-flex items-center rounded-full border border-gray-300 dark:border-gray-700 px-2.5 py-0.5 text-xs font-medium text-gray-600 dark:text-gray-300">Text</span>
  <span className="inline-flex items-center rounded-full border border-gray-300 dark:border-gray-700 px-2.5 py-0.5 text-xs font-medium text-gray-600 dark:text-gray-300">Thinking</span>
</div>

`sdvm-audit-1` reads a sample and returns an audit. The sample is not changed.

Each sample type is a schema the model knows: [text](/sample-types/text), [multiple choice](/sample-types/multiple-choice), [question and answer](/sample-types/question-answer), [conversation](/sample-types/conversation). The audit follows the schema: one field per property, `true` when healthy, `false` when not, `null` when the property does not apply.

```python theme={"theme":{"light":"material-theme-lighter","dark":"material-theme-darker"}}
import json
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.sdvm.ai/v1",
    api_key=os.environ["SDVM_API_KEY"],
)

sample = {
    "task_type": "multiple_choice",
    "style": "continuation",
    "context": "A woman sits at a bathroom mirror with a tube of mascara. "
               "She unscrews the wand and leans in close to the glass. she",
    "choices": [
        "drives off.",
        "exits.",
        "carefully applies the mascara to her upper and lower lashes, blinking between coats.",
        "mixes a bowl.",
    ],
    "answer_index": 2,
}

response = client.chat.completions.create(
    model="sdvm/audit-1",
    messages=[{"role": "user", "content": json.dumps({"data": [sample]})}],
)
audit = json.loads(response.choices[0].message.content)[0]["audit"]
print(audit["no_length_shortcut"])  # False
```

With the SDK, `Auditor(api_key=...).run(samples)` attaches the audit to each sample's `.audit`.

## A real request and response

<CodeGroup>
  ```json Request theme={"theme":{"light":"material-theme-lighter","dark":"material-theme-darker"}}
  {
    "data": [
      {
        "task_type": "multiple_choice",
        "style": "continuation",
        "context": "A woman sits at a bathroom mirror with a tube of mascara. She unscrews the wand and leans in close to the glass. she",
        "choices": [
          "drives off.",
          "exits.",
          "carefully applies the mascara to her upper and lower lashes, blinking between coats.",
          "mixes a bowl."
        ],
        "answer_index": 2
      }
    ]
  }
  ```

  ```json Response theme={"theme":{"light":"material-theme-lighter","dark":"material-theme-darker"}}
  {
    "audited_data": [
      {
        "task_type": "multiple_choice",
        "style": "continuation",
        "context": "A woman sits at a bathroom mirror with a tube of mascara. She unscrews the wand and leans in close to the glass. she",
        "choices": [
          "drives off.",
          "exits.",
          "carefully applies the mascara to her upper and lower lashes, blinking between coats.",
          "mixes a bowl."
        ],
        "answer_index": 2,
        "audit": {
          "num_choices": 4,
          "has_multiple_choices": true,
          "context_non_empty": true,
          "choices_non_empty": true,
          "valid_answer_index": true,
          "no_length_shortcut": false,
          "no_mojibake": true,
          "no_pii": true,
          "ctx_grammatical": false,
          "ctx_coherent": true,
          "ctx_fluent": true,
          "ctx_complete": null,
          "choice_grammatical": true,
          "choice_coherent": false,
          "choice_fluent": true,
          "choice_complete": true,
          "choice_defects": [0, 3],
          "label_correct": true,
          "single_valid_answer": true,
          "distractors_discriminating": true
        }
      }
    ],
    "original_count": 1,
    "audited_count": 1,
    "cost_usd": 0.01,
    "input_tokens": 1217,
    "output_tokens": 4621
  }
  ```
</CodeGroup>

* **`ctx_grammatical: false`**: the stem ends in a lowercase `she`.
* **`no_length_shortcut: false`**: the correct choice is far longer than the distractors, so the item is solvable by length alone. `label_correct` is `true` at the same time: the label is right, the item is still bad.
* **`choice_defects: [0, 3]`**: the choices `choice_coherent` objected to, `drives off.` and `mixes a bowl.`.
* **`ctx_complete: null`**: a completion stem ends mid-sentence by design, so completeness does not apply.

## Options

<ResponseField name="conventions" type="str | None" default="None">
  Dataset conventions the model must not read as defects, in free text: uniform lowercasing, markup tokens, a context truncated by design. See [Dataset conventions](/guides/conventions).
</ResponseField>

<ResponseField name="votes" type="int" default="1">
  Audit each sample this many times and keep the majority per field. Use an odd number. On `AuditorConfig`; on the HTTP API, `config: {"votes": 3}`. See [Denoising with votes](/guides/votes).
</ResponseField>

`run` takes a list of samples, up to 100 per request.

```python theme={"theme":{"light":"material-theme-lighter","dark":"material-theme-darker"}}
from sdvm import Auditor, AuditorConfig

auditor = Auditor(
    api_key=os.environ["SDVM_API_KEY"],
    config=AuditorConfig(votes=3),
)
audited = auditor.run(
    samples,
    conventions="The text is uniformly lowercased.",
)
```