# ZeroxPDFLoader

> **Class** in `langchain_community`

📖 [View in docs](https://reference.langchain.com/python/langchain-community/document_loaders/pdf/ZeroxPDFLoader)

Document loader utilizing Zerox library:
https://github.com/getomni-ai/zerox

Zerox converts PDF document to series of images (page-wise) and
uses vision-capable LLM model to generate Markdown representation.

Zerox utilizes anyc operations. Therefore when using this loader
inside Jupyter Notebook (or any environment running async)
you will need to:
```python
    import nest_asyncio
    nest_asyncio.apply()
```

## Signature

```python
ZeroxPDFLoader(
    self,
    file_path: Union[str, PurePath],
    model: str = 'gpt-4o-mini',
    **zerox_kwargs: Any = {},
)
```

## Extends

- `BasePDFLoader`

## Constructors

```python
__init__(
    self,
    file_path: Union[str, PurePath],
    model: str = 'gpt-4o-mini',
    **zerox_kwargs: Any = {},
) -> None
```

| Name | Type |
|------|------|
| `file_path` | `Union[str, PurePath]` |
| `model` | `str` |


## Properties

- `zerox_kwargs`
- `model`

## Methods

- [`lazy_load()`](https://reference.langchain.com/python/langchain-community/document_loaders/pdf/ZeroxPDFLoader/lazy_load)

---

[View source on GitHub](https://github.com/langchain-ai/langchain-community/blob/a6a6079511ac8a5c1293337f88096b8641562e77/libs/community/langchain_community/document_loaders/pdf.py#L1347)