Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I made a self-hosted ChatGPT UI

github.com

Post reply on HN
Print view View original

41–50 of 54 posts

Re: Show HN: I made a self-hosted ChatGPT UI

#41

Post by helloplanets »

humanistbot wrote: post #39

Is this allowed under OpenAI's ToS? I just don't want to connect my account and then get it banned. Edit: It seems like it is just using the API instead of the web interface, and thus charging my account each time. I originally thought it was injecting into the free web interface. But is changing the system prompt going to get me banned?

Changing the system prompt is not going to get you banned, as it's something OpenAI encourages people to do when making API calls to gpt-3.5-turbo. [0]

[0]: https://platform.openai.com/docs/guides/chat/introduction

Re: Show HN: I made a self-hosted ChatGPT UI

#42

Post by weird-eye-issue »

throwaway71271 wrote: post #16
1xdevloper wrote: post #15

ChatGPT API can be a lot more useful when you use it in context. Like selecting a chunk of text on any web page, right-click, and select summarize/translate/ELI5. Or executing your own custom prompt. I'm building a chrome extension called SublimeGPT[1] to do exactly that. Right now, you can log in to your existing ChatGPT account, go to any page, and open a chat overlay. Next version will have the context options. [1…

you can also just use bookmarklet (or multiple defining different prompts): function __summarize(api_key) { var selection = window.getSelection().toString(); if (selection.length == 0) return; var xhr = new XMLHttpRequest(); xhr.open("POST", "https://api.openai.com/v1/chat/completions"); xhr.setRequestHeader('Content-Type', 'application/json'); xhr.setRequestHeader('Authorization', 'Bearer ' + api_key); window.scroll…

Sorry but I have to ask why the XMLHttpRequest instead of fetch?

Re: Show HN: I made a self-hosted ChatGPT UI

#43

Post by throwaway71271 »

weird-eye-issue wrote: post #42
throwaway71271 wrote: post #16

Earlier quoted context omitted.

you can also just use bookmarklet (or multiple defining different prompts): function __summarize(api_key) { var selection = window.getSelection().toString(); if (selection.length == 0) return; var xhr = new XMLHttpRequest(); xhr.open("POST", "https://api.openai.com/v1/chat/completions"); xhr.setRequestHeader('Content-Type', 'application/json'); xhr.setRequestHeader('Authorization', 'Bearer ' + api_key); window.scroll…

Sorry but I have to ask why the XMLHttpRequest instead of fetch?

no reason really, at the time i was not sure if the api will be too slow (like the chat web ui) and i will need progress bar, but by the time i found out i dont, the code was already written

Re: Show HN: I made a self-hosted ChatGPT UI

#44

Post by winstonprivacy »

tottenval wrote: post #17
neilv wrote: post #2

> Chat with GPT is an open-source, unofficial ChatGPT app with extra features and more ways to customize your experience. It connects ChatGPT with ElevenLabs to give ChatGPT a realistic human voice. Looks like only GUI aspects of the UI are self-hosted, but that the text and speech aspects of the UI (and the bulk of the computation and IP) are provided by two SaaS services. Self-hosted (and some degree of open) ML mo…

It's a self-hosted UI for ChatGPT right now, but my primary goal is to build a good open source chat interface that can be adapted to open source chat models as they become available. Integrating with Alpaca, Llama, ChatGLM, OpenChatBox and whatever comes next should be straightforward once people figure out reliable and fast methods to run the models locally.

I think if you integrated with Llama, this repo would be wildly popular. I downloaded the weights over the weekend and decided I didn't want to spend my free time working on an acceptable UI.

Re: Show HN: I made a self-hosted ChatGPT UI

#45

Post by wongarsu »

whartung wrote: post #3
neilv wrote: post #2

> Chat with GPT is an open-source, unofficial ChatGPT app with extra features and more ways to customize your experience. It connects ChatGPT with ElevenLabs to give ChatGPT a realistic human voice. Looks like only GUI aspects of the UI are self-hosted, but that the text and speech aspects of the UI (and the bulk of the computation and IP) are provided by two SaaS services. Self-hosted (and some degree of open) ML mo…

I honestly am not that familiar with this space. How realistic is it that someone could self-host a ChatGPT instance? Assuming the model was available, how big are the models and what kind of hardware is necessary to run the instance?

If you run it with 4-bit quantization completely on the CPU (similar to llama.cpp), ChatGPT should run in about 90 GB of RAM. Which is easy to get your hands on for a desktop, but it's out of reach for notebooks.

Also expect performance of couple seconds per token in that setup, for now you need something involving GPUs

Re: Show HN: I made a self-hosted ChatGPT UI

#46

Post by lostphilosopher »

kkielhofner wrote: post #30
neilv wrote: post #2

> Chat with GPT is an open-source, unofficial ChatGPT app with extra features and more ways to customize your experience. It connects ChatGPT with ElevenLabs to give ChatGPT a realistic human voice. Looks like only GUI aspects of the UI are self-hosted, but that the text and speech aspects of the UI (and the bulk of the computation and IP) are provided by two SaaS services. Self-hosted (and some degree of open) ML mo…

It's somewhat ambiguous language - "self-hosted ChatGPT UI" could lead many to believe it's completely self-hosted. However, sophisticated readers familiar with ChatGPT will know the model and weights haven't been released and absent a leak/hack/release by OpenAI a completely self-hosted ChatGPT solution is impossible. Eventually we'll almost certainly see a "Completely self-hosted ChatGPT equivalent" (similar to Dal…

"Show HN: I made a self-hosted UI for ChatGPT," perhaps?

Re: Show HN: I made a self-hosted ChatGPT UI

#47

Post by weird-eye-issue »

throwaway71271 wrote: post #43
weird-eye-issue wrote: post #42

Earlier quoted context omitted.

Sorry but I have to ask why the XMLHttpRequest instead of fetch?

no reason really, at the time i was not sure if the api will be too slow (like the chat web ui) and i will need progress bar, but by the time i found out i dont, the code was already written

You can use streaming

Re: Show HN: I made a self-hosted ChatGPT UI

#48

Post by bobobob420 »

neilv wrote: post #2

> Chat with GPT is an open-source, unofficial ChatGPT app with extra features and more ways to customize your experience. It connects ChatGPT with ElevenLabs to give ChatGPT a realistic human voice. Looks like only GUI aspects of the UI are self-hosted, but that the text and speech aspects of the UI (and the bulk of the computation and IP) are provided by two SaaS services. Self-hosted (and some degree of open) ML mo…

I think ifs pretty clear what he meant by self hostef chatgpt ui. To assume the non ui aspected is also self hosted is illogical no?

Edit i think the title name was changed. Dang can you please show revision history otherwise i cant dicuss properly

Re: Show HN: I made a self-hosted ChatGPT UI

#49

Post by thefourthchime »

CharlesW wrote: post #37

Apologies if this is so unrelated as to be off-topic, but I'm new to this and so my mental model is incomplete at best and completely wrong at worst. My question is: How would one create a "domain expert" version of this? The idea would be to feed the model a bunch of specialized, domain-specific content, and then use an app like this as the UX for that.

I just did this exact thing, it's very easy.

https://dev.to/dhanushreddy29/fine-tune-gpt-3-on-custom-data...

Post reply on HN