Skip to main content
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.

​
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 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.
You can also attach documents from your terminal with nito ask --file .... See Ask and fusion from the terminal.

​
Worked Example

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

Multimodal Overview

What Nito accepts beyond text.

File Parser

The general mechanism behind attaching documents.

Image Input

Send a picture to a vision-capable model instead.

How Nito Works

Understand how Nito handles your prompt.