Sanctum
  • โœจOverview
  • ๐Ÿ–ฅ๏ธSystem Requirements
  • ๐Ÿ”Architecture & Privacy
  • ๐Ÿ“‚File manager
  • โŒจ๏ธKeyboard Shortcuts
  • MODELS
    • โš™๏ธModels Management
    • โšกModel Performance
    • ๐Ÿ“ฆToolbox
  • DEV MODE
    • ๐Ÿ› ๏ธAdvanced Model Settings
    • ๐Ÿ—„๏ธLocal Server
  • USEFUL LINKS
    • โฌ‡๏ธDownload Sanctum
    • โœ–๏ธJoin us on X
    • ๐Ÿ‘€Join us on Discord
Powered by GitBook
On this page
  • Embedding Models (RAG)
  • Audio-to-Text Model
  • Image Recognition (coming soon)
  • Model Configuration

Was this helpful?

  1. MODELS

Toolbox

The Toolbox is a collection of helper models designed to extract and transform information from various file formats into a structure that LLMs can easily read and interact with.

PreviousModel PerformanceNextAdvanced Model Settings

Last updated 5 months ago

Was this helpful?

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 .

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 leverages this technology.

For audio processing, we propose OpenAIโ€™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.

๐Ÿ“ฆ
interact with supported files
audio transcription feature