<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/84b3ae8ecf0242b88beba23294d9744a&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/84b3ae8ecf0242b88beba23294d9744a-7811d13687899f57.gif</thumbnail_url><duration>285.461</duration><title>Batuk - Open Source Enterprise AI Chat Workspace on Open Models</title><description>This Loom introduces Patok Sovereign AI Chat, an enterprise workspace for chatting with multiple model providers through open source tooling. It explains authentication with BetterAuth, model selection (including Quen 3.8 via Olama), adjustable temperature, guardrails, temporary chat, theme changes, and memory injection. It covers chat library features like saving chats to JSON, searching, creating workspaces and folders, exporting and importing chats, and resetting token usage. It also demonstrates document chat with EnableDocumentChat, supporting embeddings via local or OpenAI keys and vector stores such as LocalJsonVectors, ChromaDB, and Pinecone. Finally, it highlights enterprise administration for team access and white labeling, plus audit and compliance options with data locking and export for GDPR, ISO 27001, and SOC2 evidence.</description></oembed>