Spaces:
Runtime error
Runtime error
File size: 2,445 Bytes
b4e2225 2c1e198 b4e2225 0b9fe9d b4e2225 0b9fe9d ac86bff b4e2225 ac86bff b4e2225 c2c63c7 b4e2225 8b52d2b b4e2225 ac86bff b4e2225 ac86bff b4e2225 ac86bff b4e2225 ff48fa7 5a8581f 0b9fe9d b4e2225 5b97a1c 7382b20 b4e2225 |
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 71 72 |
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("HuggingFaceH4/zephyr-7b-beta")
demo = gr.ChatInterface(..., title="Wiser AI Assistant")
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 = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond,
title="🤖 Wiser AI Assistant",
description="Your smart manufacturing assistant powered by Wiser Machines. Ask me anything about automation, productivity, factory operations, or how Wiser can help!",
additional_inputs=[
gr.Textbox(value="You are Wiser, an AI assistant specializing in smart manufacturing and factory automation. Respond clearly, concisely, and use real-world manufacturing examples when needed.", 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)"),
],
)
demo = gr.ChatInterface(..., title="Wiser AI Assistant")
if __name__ == "__main__":
with gr.Blocks() as demo:
gr.Markdown("## Welcome to Wiser AI Assistant")
gr.Markdown("Ask questions about factory automation, productivity, or how Wiser Machines can help streamline your operations.")
chat = gr.ChatInterface(
respond,
additional_inputs=[...], # your sliders and system message
)
demo.launch() |