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

# Supported File Formats

> Reference list of file formats Vaquill can ingest and search, with notes on OCR and special handling

Vaquill ingests over 50 file formats - the ones that show up in real legal practice. Upload them as-is; the system extracts text, runs OCR where needed, and makes the content searchable across your matter.

<Frame caption="Uploaded files organized in the document library">
  <img src="https://mintcdn.com/vaquill/NNZLwmIqu4MrnJz-/images/documents.png?fit=max&auto=format&n=NNZLwmIqu4MrnJz-&q=85&s=1339dedd272089ca78eba620a3e5fcb3" alt="Document library showing tagged cards (CONTRACT, JUDGMENT, ARTICLE) with matter filtering, bulk actions, preview, and chat" style={{ borderRadius: '0.5rem' }} width="3004" height="1376" data-path="images/documents.png" />
</Frame>

<AccordionGroup>
  <Accordion title="Documents (PDF, Word, RTF, TXT, Markdown, HTML)">
    | Format        | Notes                                                               |
    | ------------- | ------------------------------------------------------------------- |
    | **PDF**       | Native and image-only; OCR runs automatically on scanned pages      |
    | **DOCX**      | Modern Word format; preserves headings and tracked changes metadata |
    | **DOCM**      | Macro-enabled Word; macros are ignored, text is extracted           |
    | **DOC**       | Legacy Word; converted before extraction                            |
    | **DOT, DOTX** | Word templates                                                      |
    | **RTF**       | Rich Text Format                                                    |
    | **TXT**       | Plain text                                                          |
    | **MD**        | Markdown                                                            |
    | **HTML, HTM** | Web pages and HTML exports                                          |
  </Accordion>

  <Accordion title="Spreadsheets (Excel, CSV)">
    | Format              | Notes                             |
    | ------------------- | --------------------------------- |
    | **XLSX**            | Modern Excel; all sheets ingested |
    | **XLSM**            | Macro-enabled Excel               |
    | **XLS**             | Legacy Excel                      |
    | **XLTX, XLTM, XLT** | Excel templates                   |
    | **CSV**             | Tabular data                      |
  </Accordion>

  <Accordion title="Presentations (PowerPoint)">
    | Format        | Notes                                              |
    | ------------- | -------------------------------------------------- |
    | **PPTX**      | Modern PowerPoint; slide content and speaker notes |
    | **PPTM**      | Macro-enabled PowerPoint                           |
    | **PPT**       | Legacy PowerPoint                                  |
    | **POT, POTX** | PowerPoint templates                               |
  </Accordion>

  <Accordion title="Images (OCR applied automatically)">
    | Format        | Notes                       |
    | ------------- | --------------------------- |
    | **PNG**       | OCR runs automatically      |
    | **JPG, JPEG** | OCR runs automatically      |
    | **GIF**       | OCR runs on the first frame |
    | **WebP**      | OCR runs automatically      |
    | **TIFF, TIF** | Multi-page TIFFs supported  |
    | **BMP**       | OCR runs automatically      |
    | **SVG**       | Text elements extracted     |
  </Accordion>

  <Accordion title="Email (EML, MSG, MBOX, PST)">
    | Format   | Notes                                                  |
    | -------- | ------------------------------------------------------ |
    | **EML**  | Single message export; attachments ingested separately |
    | **MSG**  | Outlook message format                                 |
    | **MBOX** | Mailbox archive; all messages ingested                 |
    | **PST**  | Outlook archive; all folders ingested                  |

    Attachments within email files are extracted and ingested as separate searchable documents, with a link back to the parent message.
  </Accordion>

  <Accordion title="Code and data (source files, JSON, XML)">
    | Format                              | Notes                                                    |
    | ----------------------------------- | -------------------------------------------------------- |
    | **PY, JS, TS, JAVA, CPP, GO, RUST** | Source code files; useful for IP and code-review matters |
    | **JSON, XML**                       | Structured data                                          |
  </Accordion>

  <Accordion title="Archives (ZIP, TAR, RAR, 7Z)">
    | Format          | Notes                          |
    | --------------- | ------------------------------ |
    | **ZIP**         | Contents extracted recursively |
    | **TAR, TAR.GZ** | Contents extracted recursively |
    | **RAR**         | Contents extracted recursively |
    | **7Z**          | Contents extracted recursively |

    When you upload an archive, the system extracts and ingests each file inside as a separate searchable document. Folder structure is preserved.
  </Accordion>
</AccordionGroup>

<Warning>
  Password-protected files (encrypted PDFs, password-locked archives, protected Office files) cannot be processed automatically. Remove the password before upload, or supply the password via the per-file ingestion options.
</Warning>

## OCR for Scanned Documents

For image-based files and scanned PDFs:

* OCR runs automatically on upload
* The resulting text is searchable like any other document
* The original image is preserved; click any citation to see the highlighted passage on the page
* Handwritten content is recognized where legible
* Common OCR artifacts (broken hyphens, mis-recognized characters) are cleaned up automatically

## Size and Page Limits

Upload limits vary by plan - see your [dashboard](https://app.vaquill.ai/settings) for current per-plan caps on file size, page count, and batch size. For very large files or batches, contact support to discuss enterprise ingestion options.

## What Happens After Upload

<Steps>
  <Step title="Safety scan">
    The file is scanned for safety. No untrusted code is executed.
  </Step>

  <Step title="Text extraction and OCR">
    Text is extracted; OCR runs on image-based content.
  </Step>

  <Step title="Indexing">
    The document is indexed for search across your matter.
  </Step>

  <Step title="Citation detection">
    Citations within the document are detected and linked to authorities.
  </Step>

  <Step title="Ready for analysis">
    The document is available for analysis in any tool.
  </Step>
</Steps>

Upload progress and processing status are visible in the matter document list.

## Tips

<Tip>
  **Group with archives.** Upload a ZIP of all documents in a discovery production to preserve folder structure.
</Tip>

<Tip>
  **Email-to-matter.** Forward EML or MSG files to the matter's unique email address for automatic ingestion (see [Email Ingestion](/docs/guides/email-to-rag)).
</Tip>

<Tip>
  **Re-OCR if needed.** If the OCR quality is poor on a scanned document, you can request a re-OCR pass with stricter settings.
</Tip>

## Related

<CardGroup cols={2}>
  <Card title="Document Search" icon="magnifying-glass" href="/docs/guides/document-search">
    Search across everything you have uploaded.
  </Card>

  <Card title="Email Ingestion" icon="envelope" href="/docs/guides/email-to-rag">
    Forward emails to ingest documents and attachments.
  </Card>

  <Card title="Drive Import" icon="google-drive" href="/docs/guides/google-drive-import">
    Pull documents directly from Google Drive.
  </Card>
</CardGroup>