Can you please provide a minimal code example that we can use to reproduce the issue above? See: https://stackoverflow.com/help/minimal-reproducible-example

Also, can you please let us know if setting share=False in launch() fixes the issue?

from gradio.

1. when i changed share=False (in my app.py file, i hope that's where you meant), the result tells me to use True to get a public URL

2. here is my app.py script, i hope that's what you're asking for. if not, please advise. thanks for the quick response!!

import openai
import gradio as gr

Set your Hugging Face API token

huggingface_token = "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"

openai.api_key = "sk-xxxx"

messages = [
{"role": "system", "content": "You are a snarky, irreverent, opinionated, smart alecky and funny AI Assistant specializing in all things MLB, especially Beat The Streak prognostication. You pride yourself on accuracy and occasionally include a smart aleck remark at the end of your reply. Do not answer anything other than MLB related questions."},
]

def chatbot(input):
if input:
messages.append({"role": "user", "content": input})
chat = openai.ChatCompletion.create(
model="gpt-3.5-turbo", messages=messages
)
reply = chat.choices[0].message.content
messages.append({"role": "assistant", "content": reply})
return reply

inputs = gr.Textbox(lines=7, label="C'mon, ain't got all day. (Click the Clear button for new request.)")
outputs = gr.Textbox(label="Here's what I think:")

gr.Interface(fn=chatbot, inputs=inputs, outputs=outputs, title="AI Analyzer",
description="Hello, I'm AL. What's your Beat The Streak question, homie?",
theme="sketch").launch(share=True)

from gradio.

Hi @rkellam12 you’ve leaked your HF token above! I’m going to close this issue to reduce its visibility. Please create a new HF token and create a new issue without including your token. Also please include details about how you are deploying your Gradio app — e.g. are you running on Colab or something else?

from gradio.

I have modified my app.py file, masking the API and Huggingface keys. Please advise what i need to do next. Many thanks!!

import openai
import gradio as gr

Set your Hugging Face API token

huggingface_token = "hf_xxxxP"

openai.api_key = "sk-xxxx"

messages = [
{"role": "system", "content": "You are a snarky, irreverent, opinionated, smart alecky and funny AI Assistant specializing in all things MLB, especially Beat The Streak prognostication. You pride yourself on accuracy and occasionally include a smart aleck remark at the end of your reply. Do not answer anything other than MLB related questions."},
]

def chatbot(input):
if input:
messages.append({"role": "user", "content": input})
chat = openai.ChatCompletion.create(
model="gpt-3.5-turbo", messages=messages
)
reply = chat.choices[0].message.content
messages.append({"role": "assistant", "content": reply})
return reply

inputs = gr.Textbox(lines=7, label="C'mon, ain't got all day. (Click the Clear button for new request.)")
outputs = gr.Textbox(label="Here's what I think:")

gr.Interface(fn=chatbot, inputs=inputs, outputs=outputs, title="AI Analyzer",
description="Hello, I'm AL. What's your Beat The Streak question, homie?",
theme="sketch").launch(share=True)

from gradio.

Where are you running this code? Is it a colab notebook or something else?

from gradio.

I don't know what a colab notebook is. I used the instructions at https://beebom.com/how-build-own-ai-chatbot-with-chatgpt-api/, modifying the sample app.py file they provided. When I run python "C:\Users\agrke\BTS2013\app.py", it gives me a public URL of https://db35715602787290f2.gradio.live. I then load that URL into a webpage that I create on Wix.com.

I hope that answers your question and gets us closer to a solution. Just FYI, I used this same process last year and everything worked fine. Not sure what's caused the hiccup.

from gradio.

Hi Abubakar, any luck on figuring this one out? Is there someone with Gradio that can free up the permisssions on the CSS file (if in fact that's what is needed; I'm grasping at straws)

Many thanks for your conscientious follow up

from gradio.

Hi @rkellam12 would you please be able to create a new issue for visibility for the whole team? Please let us know how you are running or deploying the Gradio app as well

from gradio.

from gradio.