File size: 2,249 Bytes
0224a63 7836e24 0224a63 7836e24 0224a63 7836e24 fa106ae 0224a63 7836e24 0224a63 7836e24 0224a63 7836e24 0224a63 fa106ae d668f39 fa106ae 7836e24 fa106ae 44f1efe fa106ae 0224a63 fa106ae | 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 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 | import gradio as gr
from huggingface_hub import InferenceClient
def respond(
message,
history: list[dict[str, str]],
system_message,
max_tokens,
temperature,
top_p,
hf_token: gr.OAuthToken,
):
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
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})
# Stream the text response
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
choices = message.choices
token = ""
if len(choices) and choices[0].delta.content:
token = choices[0].delta.content
response += token
yield response
with gr.Blocks() as demo:
with gr.Row():
with gr.Column(scale=1):
gr.LoginButton()
with gr.Column(scale=4):
chatbot = gr.Chatbot(height=500)
msg = gr.Textbox(label="Your message")
submit_btn = gr.Button("Send")
system_message = gr.Textbox(value="You are a friendly Chhattishgarhi Chatbot.", label="System message")
max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
# On submit, call respond with history, update chatbot and audio
submit_btn.click(
respond,
inputs=[msg, chatbot, system_message, max_tokens, temperature, top_p, gr.State(gr.OAuthToken())],
outputs=[chatbot, audio_output],
).then(
fn=lambda: "", # Clear input box after submit
outputs=msg
)
if __name__ == "__main__":
demo.launch() |