# A.I. Agents - File Analysis

Setting up file analysis

To use AI file analysis, you need to configure a Gemini API key on the instance and enable this feature. In the settings, you can choose the maximum file size and the file extensions that the AI will be able to read.

If extensions are not specified, all possible options may be analyzed. The currently supported formats are: mp4 (video), mp3 (audio), pdf (document), png (image), \
jpeg (image),
 csv (spreadsheet), txt (document), mpeg (audio), wav (audio), avi (video)
 and mpg (video).

<figure><img src="/files/55539aa142de49c6f5729c69f4837ba7bb527cce" alt=""><figcaption><p><em>Agent abilities.</em></p></figcaption></figure>

<figure><img src="/files/c003f8ec367cd3b7bcd5a2c3230cac24f4e779d3" alt=""><figcaption><p><em>File analysis limitations.</em></p></figcaption></figure>

## Testing the functionality

In the example below, the lead was interacting with the AI Agent when they sent a PDF with information relevant to the conversation. The agent analyzed the document's content and replied based both on its training and the available database — in this case, the store's product inventory.

<figure><img src="/files/8870e24cb407e7ef6b4f88f702925178cd9553c0" alt=""><figcaption><p><em>Conversation with the lead.</em></p></figcaption></figure>


---

# Agent Instructions: 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://docs.sprinthub.com/en/topics/artificial-intelligence/ai-agents/ai-agents-file-analysis.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.