Spaces:
Running
[NEW] HuggingChat Omni
Introducing: HuggingChat Omni 💫
HuggingChat returns and it's smarter and faster than ever 🚀
Stop picking models. Start chatting.
- 115+ available models - https://huggingface.co/chat/models
- 15+ providers available - powered by Hugging Face Inference Providers.
- One chat interface: HuggingChat
Available now for all Hugging Face users. Free users can use their inference credits, PRO users get 20x more credits to use.
🧭 Omni: the new default routing model
When you send a message, Omni analyzes what you need and routes you to the best model for that specific task.
Each route uses the best model for its task. You see which model handled your request while it streams.
📊 Examples
| What you ask | Route | Model |
|---|---|---|
| "Help me decide between two job offers. One pays 20% more but requires relocation." | decision_support |
deepseek-ai/DeepSeek-R1-0528 |
| "Create a React component for an image carousel with lazy loading" | code_generation |
Qwen/Qwen3-Coder-480B-A35B-Instruct |
| "Write a short mystery story set in a lighthouse during a storm" | creative_writing |
moonshotai/Kimi-K2-Instruct-0905 |
| "Translate this to French: The meeting has been rescheduled to next Tuesday" | translation |
CohereLabs/command-a-translate-08-2025 |
⚙️ Under the hood
Omni uses a policy-based routing system. Each route has:
- A clear description of what it handles
- A primary model best suited for that task
- Fallback models if the primary is unavailable
The router model analyzes your conversation and picks the matching route. Fast (10 second timeout) and runs on every message. Credits to Katanemo for their routing model: katanemo/Arch-Router-1.5B
✨ What else is new
- Background generation tracking: Multiple conversations can generate at the same time. Switch between tabs and the app tracks what's still generating. Updates appear automatically when responses finish.
- Better streaming: Text renders faster and smoother. The app only updates what changed instead of re-rendering everything. Less flickering, especially in long responses with code blocks.
- Better UX: UX was refined throughout the app. Fewer bugs and rough edges. Preview for code, beautiful streaming and more polish and attention to detail everywhere.
- Speed optimizations: Sessions stay active longer with automatic token refresh. Response times improved across the board. The whole app feels faster.
🛠️ Run it yourself
HuggingChat is of course still 100% open source. It has never been easier to self-host your own instance.
Quick setup:
git clone https://github.com/huggingface/chat-ui
cd chat-ui
npm install
npm run dev
Only 3 env variables to set to get it working in .env:
MONGODB_URL- Your MongoDB connectionOPENAI_API_KEY- Your API keyOPENAI_BASE_URL- Your endpoint URL
You can also configure your own routes in a JSON file. Each route defines which models to use for specific tasks.
Check out the repo: github.com/huggingface/chat-ui
Hope you are as excited as we are about HuggingChat Omni! Please share your feedback and ideas in this thread 🤗
Is it possible to import my conversations from the previous version of HuggingChat?
Yeah this dumbing down the system was totally worth nuking everyone's logs and assistants...? The performance improvements are nice if true, but how can you call this a better UX when so many basic features are missing from the last version? Even simple settings are gone, like no options to delete or edit output? There isn't even a way to tweak temperature/repetition minimizing settings, or give different chats different system prompts??
wow, I'm kind of surprised it's back. feels like a tad bit of a downgrade, but I'm assuming that it was a complete rework? hoping that more QoL features will be reintroduced again.
we're so back
edit:
nevermind, cant delete the conversation branch like before😢
edit 2:
and it now has a limit. Its been over six hours and i still cant continue the conversation 😭
I’m trying to search HuggingFace docs to understand inference credits better - i’m a pro member and ran out of inference credits the first time i tried it out. I wanted to see what you all wrote about inference and credits and whatnot. So I used the search field in the docs to search for “inference” as a starting point.
That kicked me over to Omni to do some ai-assisted search, i guess. except that since i’m out of credits the chat fails until i buy more credits.
What the actual frack? You’re using an AI assistant to help with searching topics but you expect me to pay for that inference cost out of my credits? That’s frelling ridiculous and beyond the pale that i can’t even search the docs without buying credits.
I certainly hope this is some oversight or early bug and not policy.
I agree with this, I hope hf rethinks it.
Just shut it down at this point. Was a good run.
Just shut it down at this point. Was a good run.
Just shut it down at this point. Was a good run.
Did anyone else pay for their £9 Pro subscription this month and not get their free £2 uses?
In light of the Nvidia purchase, is there a way to download all chat data, like when the previous chat interface ended?
If not, can one be implemented soon?
Did it seriously go from like 50 messages a month to just fucking 5...?