# UnstructuredFileIOLoader

> **Class** in `langchain_community`

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

Load file-like objects opened in read mode using `Unstructured`.

The file loader uses the unstructured partition function and will automatically
detect the file type. You can run the loader in different modes: "single",
"elements", and "paged". The default "single" mode will return a single langchain
Document object. If you use "elements" mode, the unstructured library will split
the document into elements such as Title and NarrativeText and return those as
individual langchain Document objects. In addition to these post-processing modes
(which are specific to the LangChain Loaders), Unstructured has its own "chunking"
parameters for post-processing elements into more useful chunks for uses cases
such as Retrieval Augmented Generation (RAG). You can pass in additional
unstructured kwargs to configure different unstructured settings.

Examples
--------
from langchain_community.document_loaders import UnstructuredFileIOLoader

with open("example.pdf", "rb") as f:
    loader = UnstructuredFileIOLoader(
        f, mode="elements", strategy="fast",
    )
    docs = loader.load()

References
----------
https://docs.unstructured.io/open-source/core-functionality/partitioning
https://docs.unstructured.io/open-source/core-functionality/chunking

## Signature

```python
UnstructuredFileIOLoader(
    self,
    file: IO[bytes],
    *,
    mode: str = 'single',
    **unstructured_kwargs: Any = {},
)
```

## Extends

- `UnstructuredBaseLoader`

## Constructors

```python
__init__(
    self,
    file: IO[bytes],
    *,
    mode: str = 'single',
    **unstructured_kwargs: Any = {},
)
```

| Name | Type |
|------|------|
| `file` | `IO[bytes]` |
| `mode` | `str` |


## Properties

- `file`

## ⚠️ Deprecated

Deprecated since version 0.2.8.

---

[View source on GitHub](https://github.com/langchain-ai/langchain-community/blob/a6a6079511ac8a5c1293337f88096b8641562e77/libs/community/langchain_community/document_loaders/unstructured.py#L352)