> 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 models are what a lot of people might want, so we should probably be careful when saying "self-hosted" right now, to not disappoint people or confuse discussion when talking about what we want.

I have tried this and many, many other ChatGPT frontends. I recently did a search for "chatgpt" on GitHub and filtered for frontends, but I was a bit disappointed with the results. Most of them seemed to be pretty similar and didn't offer anything new or unique.

I'm really interested in finding a frontend with LangChain integration that can switch between chat mode and doc mode or something along those lines. It would be great to have a more versatile tool for communication and collaboration.

Do any of you have any recommendations or know of any projects that fit this description?

It's a shame that the screencast has no sound. I was curious about what it would sound like. I could try it myself via the netlify app but I don't feel very comfortable sharing my API key somewhere...

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] https://sublimegpt.com

Looks great! I have something very similar:

https://github.com/Niek/chatgpt-web

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?

Thanks for sharing. It's really quick with responses. At least compared to couple of other frontend projects for chatgpt/OpenAI API clients I've used in the past few days.

What I think i need is something like this, but in bookmarklet form. I click it, it prompt()s me for the prompt and displays the output in a textarea so i can quickly paste it. Thinking of it it should be possible to put the output straight into the clipboard, right? The use case of course would be email/forum communication. The problem is that you have to make a UI to embed the API key into the code, because pasting it into an urlencoded script is bound to be a pain.

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.

Would be cool if they add support for llama.cpp

I like it. The chat.openai.com frontend is very slow and frequently breaks, so I would consider using this. Have you considered adding different tts providers? It doesn't get better than elevenlabs right now, but they are also much more expensive than for example the azure neural voices.

This would be really useful if the API key could be stored in the config file

Do you know if people get charged for prompts now on the original chatGPT site now that the API is out? Or is it still free for users that use the original site?

A simple ChatGPT client can be very simple .html and a .js file that runs all locally and stores data in browser local storage.

Thank you!

I can't wait to test this! As other have mentioned, the "free" chat frontend is slow and the "Plus" one, not much better. Also, at $20/month, based on my usage, it's actually more expensive than using the API.

The last hurdle: as ChatGPT is not GDPR compliant, it would be really interesting/useful to find a way to "hide" the queries from openai and prevent the usage of your input in future training - basically, a self-hosted, non-leaking, chatGPT.

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.scrollTo({top: 0})
        document.body.innerHTML = 'asking...'
        document.body.style.backgroundColor = "white";
        document.body.style.color = "black";
        document.body.style.fontFamily = 'monospace'
        document.body.style.fontSize = "16px"
        document.body.style.margin = "auto"
        document.body.style.padding = "1rem"
        document.body.style.maxWidth = "60rem"
        xhr.onreadystatechange = function() {
            if (xhr.readyState == 4) {
                if (xhr.status == 200) {
                    var response = JSON.parse(xhr.responseText);
                    var summary = response.choices[0].message.content;
                    document.body.innerHTML = summary
                } else {
                    try {
                        var e = JSON.parse(xhr.responseText);
                        document.body.innerHTML = e.error.message
                    } catch(e) {
                        document.body.innerHTML = 'error asking.. check the console'
                        console.log(xhr)
                    }
                }
            }
        }
    
        var data = JSON.stringify({
            "model": "gpt-3.5-turbo",
            "messages": [
                {"role": "system", "content": "Summarize the following text as if you are Richard Feynman"},
                {"role": "user", "content": selection}
            ]
        });
        xhr.send(data);
    }

(i have it as bookmarklet here https://gist.github.com/jackdoe/ce5a60b97e6d8487553cb00aa43f... change "YOUR API KEY HERE" with your key)