11–20 of 95 posts
One possible improvement: I had accidentally mistyped my API key and it popped up an HTTP 500 error instead of going "That doesn't seem to be a valid API key, could you make sure you pasted it in correctly" or something...
This looks very nice, lots of great extra features over the vanilla UI. One possible improvement: I had accidentally mistyped my API key and it popped up an HTTP 500 error instead of going "That doesn't seem to be a valid API key, could you make sure you pasted it in correctly" or something...
Well done! I wonder if it's worth it to also hide a "select model" option somewhere, since we're putting in our own api keys i'd be interested in trying out other models even though they arent "chat" models. Also would be great to see which messages are included in the computation, since chat gpt limits total characters per request to 4K? so inevitably some past messages will be rendered useless. Overall well done!
As per your question, currently all the previous messages of the same chat will be included in the request. If you hit the 4k token limit, there will be an error message. I'll look into improving this too.
I was annoyed by the default OpenAI ChatGPT slow-typing animation and logging me out every day, so I built a new UI client on top of its API. It's a static web app, you can host it yourself, data is stored locally on your browser, API requests are made directly to OpenAI API without any middle server. It has some more convenient features that make your that experience way better. Like search chat history, prompt libr…
It's basically doing the same thing. I found that using API keys is also significantly cheaper than using the subscription with moderate usage.
Congrats on the release.
That would be great, something like a button\action with a promt that would load and split if needed large amounts of text and promt it in conversation. (maybe add format some parsing, like markdown or plain text)
I was annoyed by the default OpenAI ChatGPT slow-typing animation and logging me out every day, so I built a new UI client on top of its API. It's a static web app, you can host it yourself, data is stored locally on your browser, API requests are made directly to OpenAI API without any middle server. It has some more convenient features that make your that experience way better. Like search chat history, prompt libr…
I’d assumed ChatGPT’s slow-typing was actually the model’s real-time output, streamed to the browser token-by-token. When I’ve made GPT3 API calls it’s worked like this, with streaming switched off I might need to wait ~20 seconds for a long response back.
I just tried your UI, and it’s so much faster! Was my assumption about real-time output wrong?
Great project, looking forward to using it more :)
I was annoyed by the default OpenAI ChatGPT slow-typing animation and logging me out every day, so I built a new UI client on top of its API. It's a static web app, you can host it yourself, data is stored locally on your browser, API requests are made directly to OpenAI API without any middle server. It has some more convenient features that make your that experience way better. Like search chat history, prompt libr…
> I was annoyed by the default OpenAI ChatGPT slow-typing animation I’d assumed ChatGPT’s slow-typing was actually the model’s real-time output, streamed to the browser token-by-token. When I’ve made GPT3 API calls it’s worked like this, with streaming switched off I might need to wait ~20 seconds for a long response back. I just tried your UI, and it’s so much faster ! Was my assumption about real-time output wrong?…
I was annoyed by the default OpenAI ChatGPT slow-typing animation and logging me out every day, so I built a new UI client on top of its API. It's a static web app, you can host it yourself, data is stored locally on your browser, API requests are made directly to OpenAI API without any middle server. It has some more convenient features that make your that experience way better. Like search chat history, prompt libr…
> I was annoyed by the default OpenAI ChatGPT slow-typing animation I’d assumed ChatGPT’s slow-typing was actually the model’s real-time output, streamed to the browser token-by-token. When I’ve made GPT3 API calls it’s worked like this, with streaming switched off I might need to wait ~20 seconds for a long response back. I just tried your UI, and it’s so much faster ! Was my assumption about real-time output wrong?…