File size: 1,855 Bytes
9622166 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
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("literallybannedfromcallingbob/Aegis-1B-Agent")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# Build prompt with history and system message
prompt = f"{system_message}\n"
for user, assistant in history:
if user:
prompt += f"User: {user}\n"
if assistant:
prompt += f"Assistant: {assistant}\n"
prompt += f"User: {message}\nAssistant:"
# Call the text_generation endpoint
response = client.text_generation(
prompt,
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
stream=True,
)
output = ""
for r in response:
output += r.token.text
yield output
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond,
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)",
),
],
title="Transformer Chatbot Demo (currently trained with ATIS dataset)",
description="Ask flight-related questions and get an answer."
)
if __name__ == "__main__":
demo.launch()
|