Hugging Face Chat UI

Azure Artificial Intelligence (AI)

Hugging Face Chat UI, the open source chat interface behind HuggingChat, self hosted and pointed at the model endpoint you choose.

Base
Hardened build
minimal ports, security patches applied at build time
Access
Unique credentials
generated on first boot, readable only by root
Verified
Boots working
services pass a health gate before release
Support
24/7, 365 days
by email and live chat, 24 hour response SLA

Overview

Hugging Face Chat UI is the open source codebase that powers HuggingChat: a fast, familiar chat interface for large language models. It gives a team one private front end for the model endpoint they already use, with conversations organised in a sidebar, model switching per conversation, image upload for multimodal models, replies that stream token by token, and one click data export.

Chat UI is a front end, not a model host. It calls any OpenAI compatible endpoint and discovers that endpoint's model list automatically, so it runs on a small CPU only machine with no GPU. Conversation history is kept in a MongoDB that ships alongside it and never leaves the instance.

Why the cloudimg image

The cloudimg image ships Chat UI and MongoDB as the official upstream containers, both pinned by image digest so the instance never silently upgrades. No model provider token is ever baked in: you supply your own in one configuration file, and it stays on your machine. Chat UI has no password login of its own, so the image puts an access gateway in front of it that denies every route by default; a unique credential and a unique database password are generated on first boot, and both the application service and the gateway refuse to start without them. MongoDB is bound to loopback with authorization enforced. A paired step by step deployment guide and 24/7 cloudimg support are included.

Common uses

  • A private team chat front end for the model provider you already pay for
  • A self hosted interface for your own Ollama, vLLM or TGI endpoint
  • Keeping chat transcripts inside your own subscription rather than a vendor's

See it running

Real screenshots taken while testing this image against its deployment guide.

Hugging Face Chat UI screenshot 1 Hugging Face Chat UI screenshot 2 Hugging Face Chat UI screenshot 3 Hugging Face Chat UI screenshot 4