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

# Files

> Attach a document and the assistant searches inside it

An attached document is not pasted into the conversation. It is chunked,
indexed and searched, so a 200 page PDF costs about as much context as the few
paragraphs that turn out to matter.

Send the whole thing.

## What you can attach

Plain text and markdown, CSV and JSON, source files in most common languages,
PDF, Word, Excel and PowerPoint.

| Limit                 | Value |
| --------------------- | ----- |
| File size             | 10 MB |
| Documents per message | 5     |
| Images per message    | 10    |
| Repositories per chat | 3     |

Images are different. They are not indexed, they go straight to the model, so
they need a model that can see. A model without vision says so rather than
failing quietly. Animated GIFs are rejected.

## How search works

Each document is split into overlapping chunks of about 200 tokens. Two indexes
are built: a keyword index and a vector index. A search runs both, takes the top
30 from each, merges them by rank, and returns the best five.

That combination is why an exact identifier and a vaguely worded question both
find the right passage. Keyword search catches the first, meaning search catches
the second.

## Identical files are free

A file is identified by its content. Attaching the same document again in
another chat reuses the existing index and does not count against your upload
quota.

## Upload quotas

|        | Free | Starter |   Pro |   Max | Enterprise |
| ------ | ---: | ------: | ----: | ----: | ---------: |
| A day  |    5 |     100 |   300 |   600 |  1,000,000 |
| A week |   20 |     500 | 1,500 | 3,000 |  1,000,000 |

Images do not count against these.