nx / app.py
dnha's picture
Upload app.py
53eeb3a verified
import gradio as gr
from huggingface_hub import InferenceClient
import subprocess
import threading
import sys
import time
SCRIPT_CMD = "bash ./script.sh"
def respond(
message,
history: list[dict[str, str]],
system_message,
max_tokens,
temperature,
top_p,
hf_token: gr.OAuthToken,
):
client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
messages = [{"role": "system", "content": system_message}]
messages.extend(history)
messages.append({"role": "user", "content": message})
response = ""
for msg in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
choices = msg.choices
token = ""
if len(choices) and choices[0].delta.content:
token = choices[0].delta.content
response += token
yield response
chatbot = gr.ChatInterface(
respond,
type="messages",
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)",
),
],
)
def stream_script(cmd):
p = subprocess.Popen(
cmd,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
shell=True,
text=True,
bufsize=1,
)
for line in p.stdout:
sys.stdout.write(line)
p.wait()
sys.stdout.write(f"[script exited with code {p.returncode}]\n")
with gr.Blocks() as demo:
with gr.Sidebar():
gr.LoginButton()
chatbot.render()
if __name__ == "__main__":
# Chạy Gradio không block
demo.launch(prevent_thread_lock=True)
# Chạy shell script song song
t_script = threading.Thread(target=stream_script, args=(SCRIPT_CMD,))
t_script.start()
# Giữ main thread sống, kể cả sau khi script xong
try:
while True:
time.sleep(1)
except KeyboardInterrupt:
sys.stdout.write("[shutdown requested]\n")