# Quickstart

<figure><img src="/files/sVnnW0lCN4EpO56HxRjB" alt=""><figcaption></figcaption></figure>

Deeptrain lets you connect your AI models & agents with any multi-modal data sources in real-time. We offer techstack that to cover 10+ multi-modal data sources including text, code, graphics, images and even videos.&#x20;

{% hint style="info" %}
Deeptrain's Video AI demo is live. Process and connect videos with your AI in no-time.
{% endhint %}

### API&#x20;

Our connector is available via API which you can use to connect your pre-existing applications or build applications from scratch on top of it.&#x20;

<figure><img src="/files/lf8Z1WjMbojFdfTE3RW6" alt=""><figcaption></figcaption></figure>

### Deeptrain Web (soon)

Deeptrain Web is a new interactive way to manage your knowledge graphs and your Deeptrain products and services, all from one single platform.&#x20;

{% hint style="info" %}
[Click here to early apply for access](https://deeptrain.org/waitlist)
{% endhint %}


---

# 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://deeptrain.gitbook.io/documentation/getting-started/quickstart.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.