# Toolbox

### **Embedding Models (RAG)**

Embedding models transform file content into numerical representations, allowing language models) to process and interpret data efficiently. This capability enables you to [interact with supported files](/file-manager.md#chat-with-files).

By default, Sanctum utilizes the BAAI BGE Small EN model for embedding file content. However, you can explore additional models on the Toolbox page to find the one that best suits your requirements.

### **Audio-to-Text Model**

These models convert audio into text, making it accessible for language models to analyze and process. The[ audio transcription feature](/file-manager.md#audio-transcription) leverages this technology.

For audio processing, we propose OpenAI’s Whisper, a robust solution available in various versions. Visit the Toolbox page to select the version that aligns with your specific needs.

### Image Recognition (coming soon)

### **Model Configuration**

If you want to customize the performance of a downloaded Toolbox models:

1. Go to the **Settings** page.
2. Explore the available configuration options to adjust the models for your specific requirements.


---

# 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://help.sanctum.ai/models/toolbox.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.