ai-chat-bot / app.py
hamz011's picture
Update app.py
043541f verified
import gradio as gr
from openai import OpenAI
client = OpenAI(
base_url="https://integrate.api.nvidia.com/v1",
api_key="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"
)
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
completion = client.chat.completions.create(
model="nvidia/nemotron-4-340b-instruct",
messages=messages,
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
stream=True,
)
for chunk in completion:
if chunk.choices[0].delta.content is not None:
token = chunk.choices[0].delta.content
response += token
yield response
demo = gr.ChatInterface(
respond,
title="Friendly Chatbot",
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()