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

# PDF and Document Input

> Attach PDFs and office documents with --file and ask a question about them, no copy-paste required.

To have a model reason over a contract, a slide deck, or a spreadsheet, attach it with `--file` and Nito reads it for you. This works with any model, because Nito extracts the document's text before the model sees it. For the general mechanism, see [File parser](/features/server-side-tools/file-parser).

## Supported Document Kinds

* PDF
* DOCX
* PPTX
* XLSX
* XLS
* Plain text

Images are separate. A picture is not attached this way, it goes to a vision-capable model instead. See [Image input](/features/multimodal/image-input) for that path.

## Attach and Ask

Attach the document with `--file`, then ask your question in the same prompt. The flag is repeatable, so you can attach several documents at once.

<Tabs>
  <Tab title="Claude Code">
    ```text theme={"theme":{"light":"github-light","dark":"github-dark"},"languages":{"custom":["typescript","python","curl"]}}
    /nito:ask --file report.pdf Summarize the key risks in this document.
    ```
  </Tab>

  <Tab title="Codex">
    ```text theme={"theme":{"light":"github-light","dark":"github-dark"},"languages":{"custom":["typescript","python","curl"]}}
    $nito:ask --file report.pdf Summarize the key risks in this document.
    ```
  </Tab>
</Tabs>

You can also attach documents from your terminal with `nito ask --file ...`. See [Ask and fusion from the terminal](/cli/ask-and-fusion-from-terminal).

## Worked Example

Attach a document and pull specific fields out of it. Here we ask about a small report using the default model:

<Tabs>
  <Tab title="Claude Code">
    ```text theme={"theme":{"light":"github-light","dark":"github-dark"},"languages":{"custom":["typescript","python","curl"]}}
    /nito:ask --file report.txt What is the top region and the Q3 risk?
    ```
  </Tab>

  <Tab title="Codex">
    ```text theme={"theme":{"light":"github-light","dark":"github-dark"},"languages":{"custom":["typescript","python","curl"]}}
    $nito:ask --file report.txt What is the top region and the Q3 risk?
    ```
  </Tab>
</Tabs>

Nito extracts the report's text and the model answers from it, returning the top region and the Q3 risk straight from the document. The same flow works for summarizing a PDF, listing the payment deadlines in a contract, or reading a spreadsheet.

## Related Resources

<CardGroup cols={2}>
  <Card title="Multimodal Overview" icon="cubes" href="/features/multimodal">
    What Nito accepts beyond text.
  </Card>

  <Card title="File Parser" icon="square-code" href="/features/server-side-tools/file-parser">
    The general mechanism behind attaching documents.
  </Card>

  <Card title="Image Input" icon="image" href="/features/multimodal/image-input">
    Send a picture to a vision-capable model instead.
  </Card>

  <Card title="How Nito Works" icon="gears" href="/get-started/how-it-works">
    Understand how Nito handles your prompt.
  </Card>
</CardGroup>