Spaces:
Sleeping
Sleeping
File size: 1,196 Bytes
77a690a 6cf9896 55c872e 6cf9896 93b086c 55c872e 93b086c 55c872e 93b086c 55c872e 93b086c 7d8680a 55c872e 93b086c 55c872e 93b086c 7d8680a 6cf9896 77a690a 35766a3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | import gradio as gr
from huggingface_hub import InferenceClient
# Initialize client
client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
def chat_function(message, history):
messages = [
{"role": "system", "content": "You are a helpful and professional AI assistant."}
]
for user_msg, bot_msg in history:
messages.append({"role": "user", "content": user_msg})
messages.append({"role": "assistant", "content": bot_msg})
messages.append({"role": "user", "content": message})
response = ""
for message_obj in client.chat_completion(
messages=messages,
max_tokens=512,
stream=True,
temperature=0.7,
top_p=0.95,
):
token = message_obj.choices[0].delta.content or ""
response += token
yield response
demo = gr.ChatInterface(
fn=chat_function,
title="Premium AI Chatbot",
description="A high-performance assistant hosted on Hugging Face.",
examples=[
"What are the benefits of RPA?",
"How to optimize SIP investments?",
"Explain financial planning."
],
cache_examples=False,
)
if __name__ == "__main__":
demo.launch() |