Spaces:
Runtime error
Runtime error
File size: 3,413 Bytes
f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 f1ff7a7 6a97a99 |
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 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
import gradio as gr
from huggingface_hub import InferenceClient, InferenceTimeoutError
import logging
# Set up logging
logging.basicConfig(level=logging.INFO)
# Initialize client with timeout
client = InferenceClient("hackergeek/gemma-finetuned", timeout=30)
def respond(
message: str,
history: list[tuple[str, str]],
system_message: str,
max_tokens: int,
temperature: float,
top_p: float,
):
"""
Handles chat responses with error handling and validation
"""
try:
# Validate system message
if not system_message.strip():
system_message = "You are a helpful AI assistant."
# Build message history
messages = [{"role": "system", "content": system_message}]
for user_msg, assistant_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if assistant_msg:
messages.append({"role": "assistant", "content": assistant_msg})
messages.append({"role": "user", "content": message})
response = ""
# Stream the response
for chunk in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
if chunk.choices and chunk.choices[0].delta.content:
token = chunk.choices[0].delta.content
response += token
yield response
except InferenceTimeoutError:
logging.error("API request timed out")
yield "Error: Request timed out. Please try again."
except Exception as e:
logging.error(f"API error: {str(e)}")
yield f"Error: {str(e)}. Please check your input and try again."
# Custom CSS for better appearance
custom_css = """
#chatbot { min-height: 400px; }
.dark #chatbot { font-size: 14px !important; }
footer { visibility: hidden; }
"""
# Configure interface
with gr.Blocks(css=custom_css, title="Gemma Chatbot") as demo:
gr.Markdown("# 🚀 Gemma Fine-Tuned Chatbot")
gr.Markdown("Chat with the fine-tuned Gemma AI assistant!")
with gr.Accordion("⚙️ Advanced Settings", open=False):
system_input = gr.Textbox(
value="You are a helpful AI assistant.",
label="System Role",
info="Initial instructions for the AI"
)
max_tokens = gr.Slider(
minimum=32, maximum=2048, value=512,
step=32, label="Max Response Length"
)
temperature = gr.Slider(
minimum=0.1, maximum=2.0, value=0.7,
step=0.1, label="Creativity (Temperature)"
)
top_p = gr.Slider(
minimum=0.1, maximum=1.0, value=0.95,
step=0.05, label="Focus (Top-p)"
)
chat_interface = gr.ChatInterface(
respond,
additional_inputs=[
system_input,
max_tokens,
temperature,
top_p
],
examples=[
["Explain quantum computing in simple terms"],
["What's the weather like in Paris?"],
["Write a poem about artificial intelligence"]
],
retry_btn=None,
undo_btn=None,
clear_btn="✨ New Chat",
)
if __name__ == "__main__":
demo.launch(server_name="0.0.0.0", server_port=7860) |