Spaces:
Sleeping
Sleeping
File size: 9,320 Bytes
b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 7dde3dd b14a2f9 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 |
import gradio as gr
import os
import logging
from huggingface_hub import InferenceClient
from typing import List, Tuple, Generator, Dict, Any, Optional
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)
class ChatConfig:
"""Configuration settings for the chat application."""
MODEL = "google/gemma-3-27b-it"
DEFAULT_SYSTEM_MSG = "You are a super intelligent and useful Chatbot."
DEFAULT_MAX_TOKENS = 512
DEFAULT_TEMP = 0.3
DEFAULT_TOP_P = 0.95
HF_TOKEN = os.environ.get("HF_TOKEN", None) # Get token from environment variable
class ChatApp:
"""Main chat application class."""
def __init__(self):
"""Initialize the chat application."""
try:
self.client = InferenceClient(
ChatConfig.MODEL,
token=ChatConfig.HF_TOKEN
)
logger.info(f"Successfully initialized InferenceClient for {ChatConfig.MODEL}")
except Exception as e:
logger.error(f"Failed to initialize InferenceClient: {e}")
raise
def generate_response(
self,
message: str,
history: List[Tuple[str, str]],
system_message: str = ChatConfig.DEFAULT_SYSTEM_MSG,
max_tokens: int = ChatConfig.DEFAULT_MAX_TOKENS,
temperature: float = ChatConfig.DEFAULT_TEMP,
top_p: float = ChatConfig.DEFAULT_TOP_P
) -> Generator[str, None, None]:
"""Generate streaming responses from the model."""
if not message.strip():
yield "请输入消息。"
return
messages = [{"role": "system", "content": system_message}]
# Add conversation history
for user_msg, bot_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if bot_msg:
messages.append({"role": "assistant", "content": bot_msg})
# Add the current message
messages.append({"role": "user", "content": message})
try:
response = ""
for chunk in self.client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = chunk.choices[0].delta.content or ""
response += token
yield response
except Exception as e:
logger.error(f"Error generating response: {e}")
yield f"抱歉,发生了错误: {str(e)}"
def create_interface(self) -> gr.Blocks:
"""Create and configure the chat interface."""
# Custom CSS for a modern look
custom_css = """
.chatbot .message {
border-radius: 12px;
margin: 8px;
padding: 12px;
box-shadow: 0 1px 3px rgba(0,0,0,0.12);
}
.chatbot .user-message {
background-color: #e3f2fd;
border-left: 4px solid #2196F3;
}
.chatbot .bot-message {
background-color: #f5f5f5;
border-left: 4px solid #9e9e9e;
}
.gr-button {
border-radius: 8px;
padding: 8px 16px;
transition: all 0.3s ease;
}
.gr-button:hover {
transform: translateY(-2px);
box-shadow: 0 4px 8px rgba(0,0,0,0.15);
}
.container {
max-width: 900px;
margin: 0 auto;
}
"""
with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as interface:
gr.Markdown("# 喵哥Google-Gemma-3尝鲜版")
gr.Markdown("与Google Gemma 3 27B模型互动,可自定义参数。")
with gr.Row():
with gr.Column(scale=4):
chatbot = gr.Chatbot(
label="Gemma Chat",
avatar_images=("./user.png", "./botge.png"),
height=500,
show_copy_button=True,
elem_classes="chatbox"
)
with gr.Row():
with gr.Column(scale=8):
msg = gr.Textbox(
show_label=False,
placeholder="在这里输入您的消息...",
container=False,
lines=2
)
with gr.Column(scale=1, min_width=70):
submit_btn = gr.Button("发送", variant="primary")
with gr.Row():
clear_btn = gr.Button("清空对话", variant="secondary")
example_btn = gr.Button("加载示例", variant="secondary")
with gr.Column(scale=2):
with gr.Accordion("聊天设置", open=True):
system_msg = gr.Textbox(
value=ChatConfig.DEFAULT_SYSTEM_MSG,
label="系统提示词",
lines=3,
placeholder="输入系统提示词..."
)
with gr.Accordion("高级参数", open=False):
max_tokens = gr.Slider(
minimum=1,
maximum=8192,
value=ChatConfig.DEFAULT_MAX_TOKENS,
step=1,
label="最大标记数",
info="控制回复长度"
)
temperature = gr.Slider(
minimum=0.1,
maximum=1.0,
value=ChatConfig.DEFAULT_TEMP,
step=0.1,
label="温度",
info="控制随机性"
)
top_p = gr.Slider(
minimum=0.1,
maximum=1.0,
value=ChatConfig.DEFAULT_TOP_P,
step=0.05,
label="Top-P",
info="控制多样性"
)
with gr.Accordion("示例问题", open=False):
gr.Examples(
examples=[
["讲一讲人工智能的最新进展"],
["写一个关于机器人发现情感的短篇故事"],
["向10岁的孩子解释量子计算"]
],
inputs=msg
)
with gr.Accordion("模型信息", open=False):
gr.Markdown(f"""
- **模型**: {ChatConfig.MODEL}
- **提供商**: Hugging Face
- **描述**: Gemma 3是Google推出的先进开源大语言模型。
""")
# Set up event handlers
msg_and_submit = [msg, submit_btn]
submit_click = submit_btn.click(
fn=self.generate_response,
inputs=[msg, chatbot, system_msg, max_tokens, temperature, top_p],
outputs=chatbot,
api_name="chat"
)
# Submit when pressing Enter (but not when pressing Shift+Enter)
msg.submit(
fn=self.generate_response,
inputs=[msg, chatbot, system_msg, max_tokens, temperature, top_p],
outputs=chatbot,
api_name=False
)
# Clear the textbox after sending
submit_click.then(lambda: "", None, msg)
msg.submit(lambda: "", None, msg)
# Clear chat button
clear_btn.click(lambda: None, None, chatbot)
# Example button
example_btn.click(
lambda: ("介绍一下人工智能研究中最有趣的发展", []),
None,
[msg, chatbot]
)
return interface
def main():
"""Main function to launch the application."""
try:
app = ChatApp()
interface = app.create_interface()
interface.launch(
server_name="0.0.0.0",
server_port=7860,
share=False,
show_api=False,
debug=True,
show_error=True
)
except Exception as e:
logger.critical(f"Failed to launch application: {e}")
print(f"错误: {e}")
if __name__ == "__main__":
main() |