Spaces:

---

huggingchat

/

chat-ui

like 1.13k

Running

A preview of the incoming web search:

Possibility to add plugins? which is already available in open assistant but generic no authentication plugins like https://www.klarna.com/.well-known/ai-plugin.json

Editing past prompts, similar to ChatGPT. For instance, I ask a question, and it gives a response. Then I ask another question, and it gives a response. I can then go back and re-word my second question, in an attempt to get the AI to respond the way I wanted.

A continue feature, so that if the AI is cut off in the middle of a response, you can continue it. For instance, I ask it to write some code. The AI writes it, but gets cut off. I am unable to get the AI to continue the code. It also seems that the AI also has very little ability to build from past questions and responses, so asking it "Please continue" ends up with the AI changing topic, in my case, from Tensorflow code to a Flask webpage.

being able to edit prompts and reduce the max length would be useful

the main issue I am seeing with this model is that it often gives very verbose answers to simple questions and the more its memory fills with its own word vomit the more unhinged it gets

Ability for the user to change the generation parameters?

Possibility to add plugins? which is already available in open assistant but generic no authentication plugins like https://www.klarna.com/.well-known/ai-plugin.json

From my tests, plugins don't work very well with current open models, so I wouldn't rush into it. But I am open to your feedback on plugins.

being able to edit prompts and reduce the max length would be useful

Ability for the user to change the generation parameters?

Yes, I think it makes sense if it's not directly visible - maybe in the settings menu.

Ability to summarise and provide key points of a webpage from the URL provided by user.

Ability to connect to user's own vector store with documents and provide answers?

Might be overkill or irrelevant, but just saying.

more modularity would be amazing: an easy way to toggle the automatic title generation, the tree system, etc.

we would suggest that all models should support image copying and pasting from clipboard, since it would be a nuisance for us to just having to rely on meta llama3.2-11b-vision-instruct on just handling all the images for us.
Here is the full issue for our suggestion:
https://github.com/huggingface/chat-ui/issues/1727

hi there!
we wonder it would be great if the devs allow us to edit code generated by AI models in huggingchat, right inside the codebase. That means, the devs should have a new "edit code" button inside the codebase generated by huggingchat's AI so the user can edit right on the chat without having to copy and paste into the IDE and edit again.
btw, this feature already exists in chatgpt's UI, hope the devs will consider this!

another feature we would suggest is the ability to delete a message from the user or the chatbot, or both (depending on the user's choice)

plus it would be a lot much better if the devs can give the user more options to choose different search engines (google, bing, duckduckgo, .....) to conduct web searches on the settings page

I second the tts suggestion. It would be really useful. Maybe edit the tts tool so that it autotriggers upon the completion of every ai message?

we hope that huggingchat can add a "copy button" in the user prompt besides "edit" and "download". this is to allow the user to copy the entire prompt to the clipboard.
and don't forget to fix the "delete" button, since it is not working when we expect the button to delete the user (and/or) bot message.

please don't forget to release hugginchat as a mobile app for ios and android, its a great addition for those who want to seek an alternative to chatgpt and gemini for mobile without having to go to the web and type hf.co/chat.