# Welcome to BrillAI

Welcome to BrillAI, a serverless inference engine powered by Xinference. To address the limitations of deploying a single model and to meet the needs across various domains and modalities, BrillAI aims to tackle the challenges in compound AI systems. It enables developers and businesses to focus on the conception and implementation of innovative applications rather than the intricate details of models.

### Jump right in

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>User Manual</strong> </td><td>Lab features in BrillAI</td><td><a href="/files/IUADsfFoczl81pPz7U7I">/files/IUADsfFoczl81pPz7U7I</a></td><td></td><td><a href="/pages/CyH2xJQs9yWJ1S8BYNav">/pages/CyH2xJQs9yWJ1S8BYNav</a></td></tr><tr><td><strong>Platform Usage Restrictions</strong></td><td>API access restrictions and file transfer limitations</td><td><a href="/files/NYvcWserHPrxs4fPiKk3">/files/NYvcWserHPrxs4fPiKk3</a></td><td></td><td><a href="/pages/93fyiXrra7pyDPb7z4Em">/pages/93fyiXrra7pyDPb7z4Em</a></td></tr><tr><td><strong>API Documentation</strong></td><td>How to properly use API functions and services</td><td><a href="/files/IUADsfFoczl81pPz7U7I">/files/IUADsfFoczl81pPz7U7I</a></td><td></td><td><a href="/pages/Xq044409w7bHbQMk0g31">/pages/Xq044409w7bHbQMk0g31</a></td></tr><tr><td><strong>FAQ</strong></td><td>Troubleshooting common issues encountered by users</td><td><a href="/files/NYvcWserHPrxs4fPiKk3">/files/NYvcWserHPrxs4fPiKk3</a></td><td></td><td><a href="/pages/7aUFmnCMx9m4smGncsXL">/pages/7aUFmnCMx9m4smGncsXL</a></td></tr><tr><td><strong>Version Release</strong></td><td>Product version updates</td><td><a href="/files/IUADsfFoczl81pPz7U7I">/files/IUADsfFoczl81pPz7U7I</a></td><td></td><td><a href="/pages/QwHFLVleY7QejI9V4gc3">/pages/QwHFLVleY7QejI9V4gc3</a></td></tr><tr><td><strong>Integration</strong></td><td>Integration and interoperability with other applications, such as Dify</td><td><a href="/files/NYvcWserHPrxs4fPiKk3">/files/NYvcWserHPrxs4fPiKk3</a></td><td></td><td><a href="/pages/shg5FQRkOMIkw2m0Yf7R">/pages/shg5FQRkOMIkw2m0Yf7R</a></td></tr></tbody></table>


---

# 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.inference.top/readme.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.