#ChatGPT Clone
misty anvil
worn peak
The project is very intuitive. The speed in producing responses is also impressive. Kudos 
rose tree
excellent work. how did you speed up responses ?
swift nebula
how?
misty anvil
I am not sure what makes it fast. maybe because of the vercel edge function!
pastel oasis
excellent work. how did you speed up responses ?
API tends to be faster at responses
finite vapor
Hi, there!
Hope you are doing well.
As an experienced full stack developer with over 15 years of
development experience, I am interested in you.
Play an important role on Strategic Software Engineer skilled in
application development, testing and optimization
I have enough experience in completing your task.https://github.com/lucalysoft/GPTs
Look forward to collaborating with you on this work.
Best regards.
undone nebula
very impressive. does it work with database to store the conversation history?
finite vapor
ofc, MongoDB
misty anvil
very impressive. does it work with database to store the conversation history?
no, history is stored in browser.
storm rune
how did u get the live output?
misty anvil
how did u get the live output?
through streaming
storm rune
how can i stream it to my gradio application?
ps. i am new to this
when i set stream=True i can no longer index responses
i dont understand whats going on
misty anvil
how can i stream it to my gradio application?
I don't know python!
radiant basin
The response is blazingly fast, amazing, di you just paid the api for this? or its just free credits? I read someone's chat that if you add your billing method in the api you will likely to get faster response. I dont know if its true
radiant basin
I also notice that you did not include the system message in api
{
"content": "You're a helpful bot that responds every question i ask",
"role": "system"
},
This could improve the bot responses.
Additionally, you did not add the AI's response when you send a request to the server which could impacts the availability to provide continuous conversation.
misty anvil
The response is blazingly fast, amazing, di you just paid the api for this? or i...
I pay for it and once it hit hard limit, …
frigid beacon
when i set stream=True i can no longer index responses
@storm rune U can use chatgpt to do this, it helps.
frigid beacon
Hi, there!
Hope you are doing well.
As an experienced full stack developer with ...
@finite vapor This repo doesn’t seem to accessible .can u r share the repo. I would love to check and collaborate. Has anyone done this on js / react js application
misty anvil
Is this using gpt 3.5 turbo or
turbo gpt 3.5
copper radish
How to boost the reposne i am also using chatgpt api but at start it give fast response now it is giving slow response
misty anvil
How to boost the reposne i am also using chatgpt api but at start it give fast r...
fetch from the edge!
misty anvil
@copper radish
here is the doc for Nextjs edge runtime
https://nextjs.org/docs/api-routes/edge-api-routes
and you can check the repo for how I implement it. the repo is available on GitHub
copper radish
i am using python and gradio for interface
can you see my codebase.
your module is giving response very fast
i liked it
@misty anvil
can i use requests library
misty anvil
@copper radish I don't python and gradio
copper radish
k
copper radish
@misty anvil
but how to add that animation when response come
one by one text intizilize
misty anvil
That's not an animation, it is streaming
glossy sedge
why not bettergpt?
restive arch
why not bettergpt?
Depends on user opinion