app.py

import gradio as gr
from huggingface_hub import InferenceClient
from googletrans import Translator
from langdetect import detect

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
translator = Translator()

def detect_and_translate(text: str, target_lang='en') -> tuple[str, str]:
    """
    Detect language and translate to target language if needed.
    Returns tuple of (translated_text, detected_language)
    """
    try:
        detected_lang = detect(text)
        if detected_lang != target_lang:
            translation = translator.translate(text, dest=target_lang)
            return translation.text, detected_lang
        return text, detected_lang
    except:
        return text, 'en'  # Fallback to original text if translation fails

def translate_to_original(text: str, original_lang: str) -> str:
    """Translate response back to original language if needed"""
    if original_lang != 'en':
        try:
            translation = translator.translate(text, dest=original_lang)
            return translation.text
        except:
            return text
    return text

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 respond(
    message, 
    history: list[tuple[str, str]], 
    system_message, 
    max_tokens, 
    temperature, 
    top_p,
):
    # First check for custom responses
    custom_response = check_custom_responses(message)
    if custom_response:
        yield custom_response
        return

    # Detect language and translate to English if needed
    translated_msg, detected_lang = detect_and_translate(message)
    
    # Prepare conversation history
    messages = [{"role": "system", "content": system_message}]
    for val in history:
        if val[0]:
            # Translate user message from history if needed
            trans_user_msg, _ = detect_and_translate(val[0])
            messages.append({"role": "user", "content": trans_user_msg})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})
    
    messages.append({"role": "user", "content": translated_msg})
    
    # Get response from model
    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
        
        # Translate accumulated response if original message wasn't in English
        if detected_lang != 'en':
            translated_response = translate_to_original(response, detected_lang)
            yield translated_response
        else:
            yield response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(
            value="You are a friendly Chatbot.",
            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)"
        ),
    ]
)

if __name__ == "__main__":
    demo.launch(share=True)