> For the complete documentation index, see [llms.txt](https://minara.ai/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://minara.ai/docs/reference/multimodal-input.md).

# Multimodal input

You can upload images and files directly in the chat input alongside your prompt. Minara reads the content and incorporates it into its response.

**Limits:** up to 5 files per upload, 10 MB per file.

**Supported formats:** images (PNG, JPG, etc.), Excel/CSV, PDF.

***

## How to use it

Click the attachment icon in the chat input, select your files, then type your question or instruction. Minara processes the files together with your text and responds in one message.

For best results, enable **Quality mode** when working with large or complex files.

***

## What you can do with it

**Chart analysis**

Upload a candlestick chart screenshot — raw or with your own annotations (trend lines, arrows, support/resistance levels). Minara reads the price structure and evaluates the logic of any annotations you've added.

**Tweet or news screenshot review**

Upload a screenshot of a tweet or news article. For tweets, Minara assesses the account and content for credibility signals. For news articles, Minara extracts the source, claims, and context, and flags anything that may be missing or misrepresented.

**Excel/CSV analysis**

Upload trading records or a dataset. Minara reads the structure, identifies patterns, summarizes P\&L drivers, and suggests improvements based on the data.

**PDF summary**

Upload a whitepaper or report. Minara summarizes the key claims, evaluates technical feasibility, tokenomics (if applicable), team credibility, and highlights risks.

***

## Tips

* Pair files with a specific question — the more precise your prompt, the more useful the response.
* You can upload multiple related files at once and ask questions that span all of them.
* Well-formatted spreadsheets and text-selectable PDFs produce better results than scanned images of documents.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://minara.ai/docs/reference/multimodal-input.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.