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

# Introduction

## Overview

The `AnyParser` is a real-time parser designed to extract content from various file formats. It's easiest to get started using the [AnyParser SDK](https://pypi.org/project/any-parser/).

### File formats

The SDK processes the following types of files:

* **PDF files**
* **Office files**: `docx`, `pptx`
* **Image files**: `png`, `jpg`, `jpeg`

### Features

The SDK has the following features:

* Full content parsing
* Key-value extraction
* Tables extraction

### Sync vs Async API

* **Sync API**: This is a blocking API that will return the results of the extraction. It will time out after 30 seconds.
  * [Example Notebook](https://github.com/CambioML/any-parser/blob/main/examples/parse_pdf.ipynb)

* **Async API**: This is an asynchronous API that will return a file ID. You can use this file ID to fetch the results of the extraction at a later time.
  * [Example Notebook](https://github.com/CambioML/any-parser/blob/main/examples/async_parse_pdf.ipynb)

### API

If you'd prefer to call the RESTful API directly, please refer to the [API Reference](/api-reference/)