Spaces:
Runtime error
Runtime error
File size: 6,715 Bytes
5583684 a4111b6 e6601b8 e9d8fd0 8656a35 5583684 e6601b8 1b42ae7 e6601b8 5583684 3f011e2 1b42ae7 5583684 d374366 5583684 cc19933 1b42ae7 cc19933 a4111b6 1b42ae7 8656a35 1b42ae7 f4740ca 8656a35 fcde6bc 92f9195 1b42ae7 8d96fb9 f4740ca d374366 1b42ae7 f4740ca 8d96fb9 f4740ca 1b42ae7 8d96fb9 1b42ae7 f4740ca 8d96fb9 f4740ca 8d96fb9 8656a35 8d96fb9 8656a35 d374366 f4740ca 8d96fb9 f4740ca 5583684 d374366 5583684 f4740ca 1b42ae7 5583684 1b42ae7 5583684 f4740ca d374366 1b42ae7 5583684 d374366 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 | # import os
# import gradio as gr
# from huggingface_hub import InferenceClient
# from dotenv import load_dotenv
# # Load environment variables
# load_dotenv()
# HF_TOKEN = os.getenv("HF_TOKEN")
# # Initialize Hugging Face Inference Client
# client = InferenceClient(
# model="Qwen/Qwen2.5-Coder-7B-Instruct",
# token=HF_TOKEN
# )
# # System prompt for coding assistant
# system_message = (
# "You are a helpful and experienced coding assistant specialized in web development. "
# "Help the user by generating complete and functional code for building websites. "
# "You can provide HTML, CSS, JavaScript, and backend code (like Flask, Node.js, etc.) "
# "based on their requirements."
# )
# # Streaming chatbot logic
# def respond(message, history):
# # Prepare messages with system prompt
# messages = [{"role": "system", "content": system_message}]
# for user_msg, assistant_msg in history:
# messages.append({"role": "user", "content": user_msg})
# messages.append({"role": "assistant", "content": assistant_msg})
# messages.append({"role": "user", "content": message})
# # Stream response from the model
# response = ""
# for chunk in client.chat.completions.create(
# model="Qwen/Qwen2.5-Coder-7B-Instruct",
# messages=messages,
# max_tokens=2048,
# temperature=0.7,
# top_p=0.95,
# stream=True,
# ):
# # Safely handle empty choices
# if not chunk.choices:
# continue
# # Safely extract token content
# token = chunk.choices[0].delta.content or ""
# response += token
# yield response
# # Create Gradio interface
# with gr.Blocks() as demo:
# chatbot = gr.Chatbot(type='messages') # Use modern message format
# gr.ChatInterface(fn=respond, chatbot=chatbot, type="messages") # Match format
# # Launch app
# if __name__ == "__main__":
# demo.launch()
# import os
# import gradio as gr
# from dotenv import load_dotenv
# from huggingface_hub import InferenceClient
# # Load environment variables
# load_dotenv()
# HF_TOKEN = os.getenv("HF_TOKEN")
# if not HF_TOKEN:
# raise ValueError("HF_TOKEN is missing.")
# # Initialize client
# client = InferenceClient(
# api_key=HF_TOKEN
# )
# # System prompt
# system_message = (
# "You are a helpful and experienced coding assistant specialized in web development. "
# "Help the user by generating complete and functional code for building websites. "
# "You can provide HTML, CSS, JavaScript, and backend code like Flask, Node.js, etc. "
# "based on their requirements."
# )
# def chat_function(message, history):
# messages = [
# {
# "role": "system",
# "content": system_message
# }
# ]
# history = history or []
# for item in history:
# if isinstance(item, dict):
# role = item.get("role")
# content = item.get("content", "")
# if role in ["user", "assistant"]:
# messages.append({
# "role": role,
# "content": content
# })
# elif isinstance(item, (list, tuple)) and len(item) == 2:
# user_msg, assistant_msg = item
# 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
# })
# try:
# completion = client.chat.completions.create(
# model="Qwen/Qwen2.5-Coder-7B-Instruct:nscale",
# messages=messages,
# max_tokens=2048,
# temperature=0.7,
# top_p=0.95,
# )
# return completion.choices[0].message.content
# except Exception as e:
# return f"Error: {str(e)}"
# # Interface
# demo = gr.ChatInterface(
# fn=chat_function,
# type="messages",
# title="AI Coding Assistant",
# description="A coding assistant powered by Qwen2.5-Coder."
# )
# # Launch
# if __name__ == "__main__":
# demo.launch()
import os
import gradio as gr
from dotenv import load_dotenv
from huggingface_hub import InferenceClient
# Load environment variables
load_dotenv()
HF_TOKEN = os.getenv("HF_TOKEN")
if not HF_TOKEN:
raise ValueError("HF_TOKEN is missing.")
# Initialize client with featherless-ai router
client = InferenceClient(
base_url="https://router.huggingface.co/featherless-ai/v1",
api_key=HF_TOKEN,
)
# System prompt
system_message = (
"You are a helpful and experienced coding assistant specialized in web development. "
"Help the user by generating complete and functional code for building websites. "
"You can provide HTML, CSS, JavaScript, and backend code like Flask, Node.js, etc. "
"based on their requirements."
)
def chat_function(message, history):
messages = [
{
"role": "system",
"content": system_message
}
]
history = history or []
for item in history:
if isinstance(item, dict):
role = item.get("role")
content = item.get("content", "")
if role in ["user", "assistant"]:
messages.append({
"role": role,
"content": content
})
elif isinstance(item, (list, tuple)) and len(item) == 2:
user_msg, assistant_msg = item
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
})
try:
completion = client.chat.completions.create(
model="Qwen/Qwen2.5-Coder-7B-Instruct",
messages=messages,
max_tokens=2048,
temperature=0.7,
top_p=0.95,
)
return completion.choices[0].message.content
except Exception as e:
return f"Error: {str(e)}"
# Interface
demo = gr.ChatInterface(
fn=chat_function,
type="messages",
title="AI Coding Assistant",
description="A coding assistant powered by Qwen2.5-Coder."
)
if __name__ == "__main__":
demo.launch() |