API / app.py
Reality123b's picture
Update app.py
1af0ee8 verified
raw
history blame
15 kB
import gradio as gr
import time
import requests
import io
from PIL import Image
from huggingface_hub import InferenceClient, HfApi
from deep_translator import GoogleTranslator
from indic_transliteration import sanscript
from indic_transliteration.detect import detect as detect_script
from indic_transliteration.sanscript import transliterate
import langdetect
import re
import os
# Get secrets from Hugging Face Space
HF_TOKEN = os.environ.get('HF_TOKEN')
if not HF_TOKEN:
raise ValueError("Please set the HF_TOKEN secret in your HuggingFace Space")
# Initialize clients
text_client = InferenceClient(
"HuggingFaceH4/zephyr-7b-beta",
token=HF_TOKEN
)
# Image generation setup
API_URL = "https://api-inference.huggingface.co/models/SG161222/RealVisXL_V4.0"
headers = {"Authorization": f"Bearer {HF_TOKEN}"}
def detect_language_script(text: str) -> tuple[str, str]:
"""Detect language and script of the input text.
Returns (language_code, script_type)"""
try:
# Use confidence threshold to avoid false detections
lang_detect = langdetect.detect_langs(text)
if lang_detect[0].prob > 0.8:
# Only accept high confidence detections
lang = lang_detect[0].lang
else:
lang = 'en' # Default to English if unsure
script = None
try:
script = detect_script(text)
except:
pass
return lang, script
except:
return 'en', None
def is_romanized_indic(text: str) -> bool:
"""Check if text appears to be romanized Indic language.
More strict pattern matching."""
# Common Bengali romanized patterns with word boundaries
bengali_patterns = [
r'\b(ami|tumi|apni)\b', # Common pronouns
r'\b(ache|achen|thako|thaken)\b', # Common verbs
r'\b(kemon|bhalo|kharap)\b', # Common adjectives
r'\b(ki|kothay|keno)\b' # Common question words
]
# Require multiple matches to confirm it's actually Bengali
text_lower = text.lower()
matches = sum(1 for pattern in bengali_patterns if re.search(pattern, text_lower))
return matches >= 2 # Require at least 2 matches to consider it Bengali
def translate_text(text: str, target_lang='en') -> tuple[str, str, bool]:
"""Translate text to target language, with more conservative translation logic."""
# Skip translation for very short inputs or basic greetings
if len(text.split()) <= 2 or text.lower() in ['hello', 'hi', 'hey']:
return text, 'en', False
original_lang, script = detect_language_script(text)
is_transliterated = False
# Only process if confident it's non-English
if original_lang != 'en' and len(text.split()) > 2:
try:
translator = GoogleTranslator(source='auto', target=target_lang)
translated = translator.translate(text)
return translated, original_lang, is_transliterated
except Exception as e:
print(f"Translation error: {e}")
return text, 'en', False
# Check for romanized Indic text only if it's a longer input
if original_lang == 'en' and len(text.split()) > 2 and is_romanized_indic(text):
text = romanized_to_bengali(text)
return translate_text(text, target_lang) # Recursive call with Bengali script
return text, 'en', False
def check_custom_responses(message: str) -> str:
"""Check for specific patterns and return custom responses."""
message_lower = message.lower()
custom_responses = {
"what is ur name?": "xylaria",
"what is your name?": "xylaria",
"what's your name?": "xylaria",
"whats your name": "xylaria",
"how many 'r' is in strawberry?": "3",
"who is your developer?": "sk md saad amin",
"how many r is in strawberry": "3",
"who is ur dev": "sk md saad amin",
"who is ur developer": "sk md saad amin",
}
for pattern, response in custom_responses.items():
if pattern in message_lower:
return response
return None
def is_image_request(message: str) -> bool:
"""Detect if the message is requesting image generation."""
image_triggers = [
"generate an image",
"create an image",
"draw",
"make a picture",
"generate a picture",
"create a picture",
"generate art",
"create art",
"make art",
"visualize",
"show me",
]
message_lower = message.lower()
return any(trigger in message_lower for trigger in image_triggers)
def generate_image(prompt):
"""Generate image using HuggingFace inference API"""
try:
response = requests.post(API_URL, headers=headers, json={"inputs": prompt})
image = Image.open(io.BytesIO(response.content))
return image
except Exception as e:
print(f"Image generation error: {e}")
return None
def romanized_to_bengali(text: str) -> str:
"""Convert romanized Bengali text to Bengali script."""
bengali_mappings = {
'ami': 'আমি',
'tumi': 'তুমি',
'apni': 'আপনি',
'kemon': 'কেমন',
'achen': 'আছেন',
'acchen': 'আছেন',
'bhalo': 'ভালো',
'achi': 'আছি',
'ki': 'কি',
'kothay': 'কোথায়',
'keno': 'কেন',
}
text_lower = text.lower()
for roman, bengali in bengali_mappings.items():
text_lower = re.sub(r'\b' + roman + r'\b', bengali, text_lower)
if text_lower == text.lower():
try:
return transliterate(text, sanscript.ITRANS, sanscript.BENGALI)
except:
return text
return text_lower
def create_chat_interface():
# Custom CSS for better styling with Inter font and animations
custom_css = """
@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&display=swap');
* {
font-family: 'Inter', sans-serif !important;
}
.container {
max-width: 850px !important;
margin: auto;
}
.chat-window {
height: 600px !important;
overflow-y: auto;
border-radius: 15px !important;
box-shadow: 0 8px 16px rgba(0, 0, 0, 0.1) !important;
transition: all 0.3s ease !important;
}
.chat-window:hover {
box-shadow: 0 12px 20px rgba(0, 0, 0, 0.15) !important;
}
.chat-message {
padding: 1rem !important;
margin: 0.5rem !important;
border-radius: 12px !important;
transition: all 0.2s ease !important;
opacity: 0;
animation: messageSlide 0.3s ease forwards;
}
@keyframes messageSlide {
from {
opacity: 0;
transform: translateY(10px);
}
to {
opacity: 1;
transform: translateY(0);
}
}
.user-message {
background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%) !important;
color: white !important;
margin-left: 2rem !important;
}
.bot-message {
background: linear-gradient(135deg, #f3f4f6 0%, #e5e7eb 100%) !important;
margin-right: 2rem !important;
}
/* Button Styles */
button.primary {
background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%) !important;
border: none !important;
color: white !important;
padding: 0.75rem 1.5rem !important;
border-radius: 12px !important;
font-weight: 600 !important;
transition: all 0.3s ease !important;
transform: translateY(0);
box-shadow: 0 4px 6px rgba(99, 102, 241, 0.2) !important;
}
button.primary:hover {
transform: translateY(-2px);
box-shadow: 0 8px 12px rgba(99, 102, 241, 0.3) !important;
}
button.primary:active {
transform: translateY(0);
}
button.secondary {
background: #f3f4f6 !important;
border: 2px solid #e5e7eb !important;
color: #4b5563 !important;
padding: 0.75rem 1.5rem !important;
border-radius: 12px !important;
font-weight: 600 !important;
transition: all 0.3s ease !important;
}
button.secondary:hover {
background: #e5e7eb !important;
border-color: #d1d5db !important;
}
/* Input Styles */
.input-container {
position: relative;
margin-bottom: 1rem;
}
textarea {
border: 2px solid #e5e7eb !important;
border-radius: 12px !important;
padding: 1rem !important;
transition: all 0.3s ease !important;
font-size: 1rem !important;
line-height: 1.5 !important;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.05) !important;
}
textarea:focus {
border-color: #6366f1 !important;
box-shadow: 0 4px 6px rgba(99, 102, 241, 0.1) !important;
}
/* Settings Panel */
.settings-block {
background: white !important;
border-radius: 15px !important;
padding: 1.5rem !important;
margin-top: 1rem !important;
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.05) !important;
transition: all 0.3s ease !important;
}
.settings-block:hover {
box-shadow: 0 6px 8px rgba(0, 0, 0, 0.08) !important;
}
/* Slider Styles */
.gr-slider {
height: 4px !important;
background: #e5e7eb !important;
border-radius: 2px !important;
}
.gr-slider .handle {
width: 16px !important;
height: 16px !important;
border: 2px solid #6366f1 !important;
background: white !important;
border-radius: 50% !important;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1) !important;
transition: all 0.2s ease !important;
}
.gr-slider .handle:hover {
transform: scale(1.1);
}
/* Loading Animation */
@keyframes pulse {
0% { opacity: 1; }
50% { opacity: 0.5; }
100% { opacity: 1; }
}
.loading {
animation: pulse 1.5s ease-in-out infinite;
}
"""
# Create the interface with custom theme
with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
# Header
with gr.Row():
gr.HTML("""
<div style="text-align: center; margin-bottom: 2rem; padding: 2rem;">
<h1 style="font-size: 3rem; font-weight: 700; color: #4f46e5; margin-bottom: 0.5rem;">
✨ Xylaria Chat
</h1>
<p style="color: #6b7280; font-size: 1.2rem; font-weight: 500;">
Your Intelligent Multilingual Assistant
</p>
</div>
""")
# Main chat interface
with gr.Row():
with gr.Column(scale=4):
chatbot = gr.Chatbot(
height=500,
show_label=False,
container=True,
elem_classes=["chat-window"],
type='messages'
)
image_output = gr.Image(
type="pil",
label="Generated Image",
visible=False,
elem_classes=["generated-image"]
)
with gr.Row():
with gr.Column(scale=8):
txt = gr.Textbox(
show_label=False,
placeholder="Type your message here...",
container=False,
elem_classes=["input-textbox"]
)
with gr.Column(scale=1):
send_btn = gr.Button(
"Send",
variant="primary",
elem_classes=["primary"]
)
with gr.Column(scale=1):
clear_btn = gr.Button(
"Clear",
variant="secondary",
elem_classes=["secondary"]
)
# Settings panel
with gr.Accordion(
"⚙️ Advanced Settings",
open=False,
elem_classes=["settings-accordion"]
):
with gr.Row():
with gr.Column():
system_msg = gr.Textbox(
value="You are a friendly Chatbot who always responds in English unless the user specifically uses another language.",
label="System Message",
lines=2
)
max_tokens = gr.Slider(
minimum=1,
maximum=2048,
value=512,
step=1,
label="Max Tokens"
)
with gr.Column():
temperature = gr.Slider(
minimum=0.1,
maximum=4.0,
value=0.7,
step=0.1,
label="Temperature"
)
top_p = gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)"
)
# Rest of your existing functions (user_message, bot_response, etc.)
# ... (keep the same function implementations)
# Update the event handlers to use the new classes
send_event = txt.submit(
user_message,
[txt, chatbot],
[txt, chatbot],
queue=False
).then(
bot_response,
[chatbot, system_msg, max_tokens, temperature, top_p],
[chatbot, image_output]
)
send_btn.click(
user_message,
[txt, chatbot],
[txt, chatbot],
queue=False
).then(
bot_response,
[chatbot, system_msg, max_tokens, temperature, top_p],
[chatbot, image_output]
)
clear_btn.click(
lambda: (None, None),
None,
[chatbot, image_output],
queue=False
)
# Update image visibility
send_event.then(
lambda img: gr.update(visible=img is not None),
image_output,
image_output
)
return demo
# Create and launch the interface
demo = create_chat_interface()
if __name__ == "__main__":
demo.launch(share=True)