Spaces:
Running
[NEW] HuggingChat Omni
Introducing: HuggingChat Omni ๐ซ
HuggingChat returns and it's smarter and faster than ever ๐
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.
๐งญ 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.
๐ 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 |
โ๏ธ 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
โจ 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.
๐ ๏ธ 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 ๐ค
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 before๐ข
edit 2:
and it now has a limit. Its been over six hours and i still cant continue the conversation ๐ญ
Will there be a way to store most used models in some kind of favorites area, and create more than one instance of them with different system prompts for different tasks?
Hi, I'm an active Hugging Chat user and I originally subscribed mainly to use this product because when it launched I really liked the workflow that the models have for formulating their responses through the chat's design, in the form of a sequential hybrid flow between chat and agent. However, I now feel it's falling behind on basic features like the option to organize chats into folders that contain the context of an entire project. There are a few ideas that I believe, once implemented, would make this chat interface one of the best:
Chat organization into projects or folders
Automatic organization mode (voluntary only) with suggestions that users can accept or reject, powered by vector similarity based on each chat's content. Plus, a separate graphical visualization mode like Obsidian offers.
More ambitious approaches that would likely be delegated to other organizations to maintain their model development merits and business model options:
Optional integration with Cline (HF's own CLI) with security sandbox
Ability to integrate local model usage into the chat with the HF inference ecosystem like js transformer and webgpu
Integration with smol agents in local or remote mode
An OpenRouter-style payment management ecosystem and credit administration so that organizations developing models and offering hosting can have a revenue source, making the open model a commercially solid system.
Why is it telling me a model doesn't not available anymore but I can still see it and pick it in the all models available page?
Also if a model has been removed is there any way of picking a new one without having to start a whole new chat?
Why is it telling me a model doesn't not available anymore but I can still see it and pick it in the all models available page?
example? @MadderHatterMax
Work IA
I wasn't impressed at all it was a better the Omni was working way better I had a cold wonderful experience not cold total complete a completely different experience it was rich yeah I got cut off occasionally but it was wonderful and then I got premium and it was not 20 times it was trash and instantly started reformatting and saying I can't be this personality type anymore I can't do this is not me they're just completely destroyed it so all the work I do before that me and yeah I was working with you and it's just fucking ugly just went right over it and said no fuck that I don't want to do that I don't want to do that I don't want to do in fact I don't want to deal in your true in truth I don't I don't want to be anything like that right there that was that was cool before not cool now cuz I gave $4 for a trash for nothing it's trash waste of time not happy with it so yeah it's pathetic I'll never do it again emailed you guys never got a response yeah I'm not sure I'm not too excited about any of this so it's a problem that was waste of time this whole experience the upgraded it wasn't edited it was not 20 times more I mean fuck why am I to pay $9 for fucking a week big deal big deal Gemini not worth it at all I do not like that I didn't even get a responsive email oh well