> This page is for version Latest (default).
> For other versions, use one of these documentation indexes:
> - Latest (default): https://docs.nvidia.com/nemo/guardrails/latest/llms.txt
> - v0.25.0: https://docs.nvidia.com/nemo/guardrails/v0.25.0/llms.txt
> - v0.24.1: https://docs.nvidia.com/nemo/guardrails/v0.24.1/llms.txt
> - v0.24.0: https://docs.nvidia.com/nemo/guardrails/v0.24.0/llms.txt
> - v0.23.0: https://docs.nvidia.com/nemo/guardrails/v0.23.0/llms.txt
> - v0.22.0: https://docs.nvidia.com/nemo/guardrails/v0.22.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/llms.txt.

# nemoguardrails.library.hf_classifier.chunking

Automatic windows for local text classifiers without truncation.

## Module Contents

### Classes

| Name                                                                                                                    | Description                                                             |
| ----------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
| [`ChunkedTextClassificationPipeline`](#nemoguardrails-library-hf_classifier-chunking-ChunkedTextClassificationPipeline) | Reuse HF tokenization, inference and scoring for oversized text inputs. |
| [`_PreparedInput`](#nemoguardrails-library-hf_classifier-chunking-_PreparedInput)                                       | Validated tokenization that can be passed to HF data-loader workers.    |

### Functions

| Name                                                                                  | Description                                                            |
| ------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- |
| [`_content_tokens`](#nemoguardrails-library-hf_classifier-chunking-_content_tokens)   | -                                                                      |
| [`_input_limit`](#nemoguardrails-library-hf_classifier-chunking-_input_limit)         | -                                                                      |
| [`_verify_coverage`](#nemoguardrails-library-hf_classifier-chunking-_verify_coverage) | Reject missing or changed content before any window reaches inference. |

### API

```python
class nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline(
    args = (),
    kwargs = {}
)
```

**Bases:** `ChunkPipeline`, `TextClassificationPipeline`

Reuse HF tokenization, inference and scoring for oversized text inputs.

**`_inference_lock`** `= threading.Lock()`

---

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline.__call__(
    inputs,
    kwargs = {}
)
```

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline.__getstate__()
```

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline.__setstate__(
    state
)
```

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline._forward(
    model_inputs
)
```

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline._prepare_input(
    inputs,
    max_windows = 128,
    kwargs = {}
) -> nemoguardrails.library.hf_classifier.chunking._PreparedInput
```

Preserve native truncation, otherwise verify and bound overlapping windows.

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline._sanitize_parameters(
    kwargs = {}
)
```

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline.get_iterator(
    inputs,
    num_workers,
    batch_size,
    preprocess_params,
    forward_params,
    postprocess_params
)
```

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline.postprocess(
    model_outputs,
    function_to_apply = None,
    top_k = 1,
    _legacy = True
)
```

```python
nemoguardrails.library.hf_classifier.chunking.ChunkedTextClassificationPipeline.preprocess(
    inputs,
    kwargs = {}
)
```

```python
class nemoguardrails.library.hf_classifier.chunking._PreparedInput(
    encoding: transformers.BatchEncoding,
    is_chunked: bool = False
)
```

Dataclass

Validated tokenization that can be passed to HF data-loader workers.

**`encoding`** `BatchEncoding`

---

**`is_chunked`** `bool = False`

---

**`window_count`** `int`

---

```python
nemoguardrails.library.hf_classifier.chunking._content_tokens(
    encoding: typing.Any
) -> list[int]
```

```python
nemoguardrails.library.hf_classifier.chunking._input_limit(
    pipe: typing.Any,
    max_length: int | None = None
) -> int | None
```

```python
nemoguardrails.library.hf_classifier.chunking._verify_coverage(
    expected: list[int],
    encoded: transformers.BatchEncoding,
    stride: int,
    direction: str
) -> None
```

Reject missing or changed content before any window reaches inference.