# Supported file types

Hirize's AI-powered extraction technology is engineered to handle a wide range of document formats, offering flexibility and adaptability to meet diverse processing needs. Whether you're dealing with scanned images, digital PDFs, editable documents, or plain text files, Hirize delivers precise and efficient data extraction.

***

### Currently Supported Formats

<mark style="color:purple;">**Image Files**</mark> Ideal for scanned documents, photographs of documents, and screenshots.

{% code fullWidth="false" %}

```
image/jpeg
```

{% endcode %}

```
image/jpg
```

```
image/png
```

```
image/tiff
```

```
image/bmp
```

<mark style="color:purple;">**PDF**</mark> Perfect for digital documents that retain their formatting across various platforms.

```
application/pdf
```

<mark style="color:purple;">**Microsoft Word Documents**</mark> Suitable for editable text documents created in Microsoft Word.

```
DOC application/msword
```

```
DOCX application/vnd.openxmlformats-officedocument.wordprocessingml.document
```

<mark style="color:purple;">**Text Files**</mark> Essential for parsing data from plain text files, facilitating straightforward text extraction without formatting complexities.

```
TXT text/plain
```

***

### Processing Capabilities

Hirize's sophisticated document parsing technology not only supports a diverse range of file types but also ensures high accuracy in data extraction. Leveraging advanced Optical Character Recognition (OCR) and Natural Language Processing (NLP) techniques, Hirize efficiently extracts text and data even from complex document layouts.

* **Optical Character Recognition (OCR)**\
  Converts different types of documents, such as scanned paper documents or images, into editable and searchable data with high precision.
* **Natural Language Processing (NLP)**\
  Analyzes and understands the context of the extracted text, enabling accurate data categorization and extraction from unstructured content.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://hirize.gitbook.io/hirize/getting-started/publish-your-docs/supported-file-types.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.