> ## Documentation Index
> Fetch the complete documentation index at: https://cortex-ad5578da.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Supported File Formats

> Comprehensive list of all supported file formats for document processing in Cortex

Cortex supports a comprehensive range of file formats for document processing. Files are automatically parsed and their content extracted for indexing and search. This page provides a complete reference of all supported formats.

<Warning>
  **Unsupported File Formats**: If you attempt to upload a file format that is not supported, you will receive an error response with status code `400` and the message: `"Unsupported file format: [filename]. Please check our supported file formats documentation."` Ensure your files are in one of the supported formats listed below before uploading.
</Warning>

## Word Processing and Presentations

Office documents and presentation files:

* **PDF**
* **ODT (OpenDocument Text)**
* **RTF (Rich Text Format)**
* **DOC**
* **DOCX (Office Open XML)**
* **DOCM, DOT, DOTM**
* **Pages**
* **CWK, LWP, MW, MCW, HWP, PBD, zabw**
* **WPD, WPS**
* **XML**
* **Key**
* **PPT, PPTX, PPTM, POT, POTM, POTX, SDD, SDA, SDP, SGL, STI, SXI, STW, SXW, SXG, UOP**

## Spreadsheets

Data and spreadsheet formats:

* **XLSX**
* **XLS**
* **XLSM, XLSB, XLW, CSV, TSV, DIF, SYLK, SLK, PRN, NUMBERS, ET, ODS, FODS, UOS1, UOS2, DBF, WK1, WK2, WK3, WK4, WKS, 123, WQ1, WQ2, WB1, WB2, WB3, QPW, XLR, ETH**

## Markup and Documentation

These formats are ideal for documentation, wikis, and structured text content:

* **Markdown** (all variants: CommonMark, GitHub-Flavored, MultiMarkdown, Markdown Extra, Djot)
* **HTML, XHTML**
* **LaTeX**
* **reStructuredText**
* **Textile**
* **Emacs Org-Mode**
* **Emacs Muse**
* **OPML**
* **DocBook**
* **AsciiDoc**
* **MediaWiki, TWiki, DokuWiki, TikiWiki, Vimwiki, Muse Wiki**
* **JATS, BITS**
* **FictionBook2 (FB2)**
* **GNU TexInfo**
* **Haddock markup**
* **TEI Simple**
* **Typst**
* **pod, man (roff), mdoc**
* **Creole, Jira wiki markup**
* **Markua, txt2tags**
* **Plain text (TXT)**

## Images

Image files with text content:

* **JPEG, JPG, PNG, GIF, BMP, SVG, TIFF, WEBP**

<Note>
  **Image Processing**: Image files are processed using OCR (Optical Character Recognition) to extract text content. Ensure images have clear, readable text for best results.
</Note>

## Ebooks

Digital book formats:

* **EPUB**
* **FictionBook2 (FB2)**

## Data/Bibliography/Serialization

Structured data and reference formats:

* **BibTeX/BibLaTeX/CSL JSON/CSL YAML**
* **RIS**
* **EndNote XML**
* **Jupyter notebook (ipynb)**
* **JSON**
* **XML**
* **Haskell AST**

## Others (Special Formats)

Specialized and niche formats:

* **InDesign ICML**
* **XWiki, ZimWiki**
* **Beamer, Slidy, Slideous, S5, DZSlides, reveal.js (presentation/slideshow formats)**
* **ANSI-formatted text**

## File Size and Processing Limits

### **File Size Limits**

* **Maximum file size**: 50MB per file
* **Recommended size**: Under 10MB for optimal processing speed
* **Large files**: Files over 100 pages may take longer to process

### **Processing Time**

Cortex is optimized for speed and typically processes files much faster than traditional solutions:

* **Small files** (\< 10 pages): **Under 2 minutes** (typically 30 seconds to 1 minute)
* **Medium files** (10-100 pages): **2-5 minutes** (typically 1-3 minutes)
* **Large files** (100+ pages): **5-15 minutes** (typically 3-8 minutes)

<Note>
  **Performance Note**: Cortex's processing times are significantly faster than traditional document processing solutions. Most files under 10 pages are processed in under 2 minutes, with many completing in under 1 minute.
</Note>

## Best Practices

### **File Preparation**

* Ensure files are not password-protected
* Use clear, well-structured documents for better parsing
* Avoid corrupted or damaged files
* Use descriptive filenames for easier identification

### **Format-Specific Tips**

**PDF Files:**

* Use text-based PDFs rather than scanned images when possible
* Ensure proper text encoding (UTF-8 preferred)
* Avoid password-protected or encrypted PDFs

**Office Documents:**

* Save in the latest format version when possible
* Remove unnecessary formatting that might interfere with parsing
* Ensure all content is accessible (not hidden or in comments only)

**Images:**

* Use high-resolution images with clear, readable text
* Ensure good contrast between text and background
* Avoid heavily stylized fonts that might be difficult to OCR

**Markdown:**

* Use standard Markdown syntax for best compatibility
* Include proper heading structure for better chunking
* Use consistent formatting throughout the document

## Troubleshooting

### **Common Issues**

**File Not Processing:**

* Check if the file format is supported (see list above)
* Verify the file is not corrupted or password-protected
* Ensure the file size is under 50MB
* Check your API key permissions

**Poor Text Extraction:**

* For images: ensure high resolution and clear text
* For PDFs: use text-based rather than scanned PDFs
* For office docs: avoid complex formatting or embedded objects

**Processing Errors:**

* Check the file format against the supported list
* Verify file integrity (not corrupted)
* Ensure proper file permissions
* Contact support with the `file_id` if issues persist

<Info>
  **Need Help?** If you're experiencing issues with file processing or have questions about format support, contact our support team at [founders@usecortex.ai](mailto:founders@usecortex.ai) with the `file_id` for assistance.
</Info>