Update app.py

app.py

@@ -1,39 +1,148 @@
 import gradio as gr
 from geminisearch import webSearch
+import speech_recognition as sr
+import pyttsx3
+import threading
+import io
+import wave
+import numpy as np
 
-# Concise example questions for MCP interface
-mcp_examples = [
+class QuasarAudioChat:
+    def __init__(self):
+        self.tts_engine = pyttsx3.init()
+        self.tts_engine.setProperty('rate', 150)
+        self.tts_engine.setProperty('volume', 0.9)
+        self.recognizer = sr.Recognizer()
+        self.is_listening = False
+        
+    def speech_to_text(self, audio_data):
+        """Convert speech to text"""
+        try:
+            if audio_data is None:
+                return "No audio received"
+            
+            # Convert audio to the format expected by speech_recognition
+            with sr.AudioFile(io.BytesIO(audio_data)) as source:
+                audio = self.recognizer.record(source)
+                text = self.recognizer.recognize_google(audio)
+                return text
+        except sr.UnknownValueError:
+            return "Could not understand audio"
+        except sr.RequestError as e:
+            return f"Speech recognition error: {e}"
+    
+    def text_to_speech(self, text):
+        """Convert text to speech"""
+        try:
+            # Remove markdown and special characters for cleaner speech
+            clean_text = text.replace('*', '').replace('#', '').replace('`', '')
+            self.tts_engine.say(clean_text)
+            self.tts_engine.runAndWait()
+        except Exception as e:
+            print(f"TTS Error: {e}")
+    
+    def process_audio_message(self, audio, chat_history):
+        """Process audio input and return response"""
+        if audio is None:
+            return chat_history, "Please provide audio input"
+        
+        # Convert audio to text
+        user_text = self.speech_to_text(audio)
+        
+        if "error" in user_text.lower() or "could not" in user_text.lower():
+            chat_history.append({"role": "user", "content": "[Audio Error]"})
+            chat_history.append({"role": "assistant", "content": user_text})
+            return chat_history, user_text
+        
+        # Add user message to chat
+        chat_history.append({"role": "user", "content": f"🎤 {user_text}"})
+        
+        # Get response from webSearch
+        try:
+            response = webSearch(user_text)
+            chat_history.append({"role": "assistant", "content": response})
+            
+            # Convert response to speech in background thread
+            threading.Thread(target=self.text_to_speech, args=(response,), daemon=True).start()
+            
+            return chat_history, response
+        except Exception as e:
+            error_msg = f"Search error: {str(e)}"
+            chat_history.append({"role": "assistant", "content": error_msg})
+            return chat_history, error_msg
+
+# Initialize audio chat
+audio_chat = QuasarAudioChat()
+
+# Predefined questions for Quasar LLM
+quasar_examples = [
     "What are the latest AI technology developments?",
     "What's happening in global news today?",
     "What's the current cryptocurrency market status?"
 ]
 
-# Custom CSS for better styling
+# Enhanced CSS with audio-focused styling
 custom_css = """
 .gradio-container {
     max-width: 1200px !important;
     margin: auto !important;
+    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%) !important;
+    min-height: 100vh !important;
+}
+
+.main-container {
+    background: rgba(255, 255, 255, 0.95) !important;
+    border-radius: 20px !important;
+    padding: 2rem !important;
+    margin: 1rem !important;
+    box-shadow: 0 20px 40px rgba(0,0,0,0.1) !important;
 }
 
 .chatbot {
     border-radius: 15px !important;
-    box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1) !important;
+    box-shadow: 0 8px 20px rgba(0, 0, 0, 0.1) !important;
+    border: 2px solid #e1e5e9 !important;
 }
 
-.input-container {
+.audio-input {
+    border-radius: 50px !important;
+    background: linear-gradient(135deg, #ff6b6b, #ffd93d) !important;
+    border: none !important;
+    color: white !important;
+    font-weight: bold !important;
+    box-shadow: 0 4px 15px rgba(255, 107, 107, 0.3) !important;
+    transition: all 0.3s ease !important;
+}
+
+.audio-input:hover {
+    transform: translateY(-2px) !important;
+    box-shadow: 0 8px 25px rgba(255, 107, 107, 0.4) !important;
+}
+
+.text-input {
     border-radius: 25px !important;
     border: 2px solid #e1e5e9 !important;
+    background: rgba(255, 255, 255, 0.9) !important;
 }
 
-.input-container:focus-within {
-    border-color: #4285f4 !important;
-    box-shadow: 0 0 0 3px rgba(66, 133, 244, 0.1) !important;
+.text-input:focus-within {
+    border-color: #667eea !important;
+    box-shadow: 0 0 0 3px rgba(102, 126, 234, 0.1) !important;
 }
 
 h1 {
     text-align: center !important;
-    color: #1a73e8 !important;
-    font-weight: 600 !important;
+    background: linear-gradient(135deg, #667eea, #764ba2) !important;
+    -webkit-background-clip: text !important;
+    -webkit-text-fill-color: transparent !important;
+    font-weight: 700 !important;
+    font-size: 2.5rem !important;
+    margin-bottom: 1rem !important;
+}
+
+.description {
+    text-align: center !important;
+    color: #666 !important;
     margin-bottom: 2rem !important;
 }
 
@@ -47,54 +156,179 @@ h1 {
     color: white !important;
     border: none !important;
     transition: all 0.3s ease !important;
+    font-weight: 500 !important;
 }
 
 .example:hover {
     transform: translateY(-2px) !important;
-    box-shadow: 0 8px 25px rgba(0,0,0,0.2) !important;
+    box-shadow: 0 8px 25px rgba(102, 126, 234, 0.3) !important;
+}
+
+.audio-controls {
+    display: flex !important;
+    justify-content: center !important;
+    gap: 1rem !important;
+    margin: 1rem 0 !important;
+}
+
+.status-indicator {
+    padding: 0.5rem 1rem !important;
+    border-radius: 20px !important;
+    background: #e8f4f8 !important;
+    color: #1976d2 !important;
+    font-weight: 500 !important;
+    text-align: center !important;
 }
 """
 
-# Create the enhanced interface
-app = gr.ChatInterface(
-    webSearch,
-    chatbot=gr.Chatbot(
-        height=500,
-        show_label=False,
-        container=True,
-        bubble_full_width=False,
-        render_markdown=True
-    ),
-    type="messages",
-    textbox=gr.Textbox(
-        placeholder="🔍 Ask me anything about current events, news, or real-time information...",
-        container=False,
-        scale=7,
-        show_label=False,
-        lines=1,
-        max_lines=3
-    ),
-    title="✨ Quasar LLM Web Chat",
-    description="Quasar LLM powered interface for real-time web search and intelligent responses.",
+# Create the Quasar LLM interface with audio capabilities
+with gr.Blocks(
     theme=gr.themes.Soft(
         primary_hue="blue",
         secondary_hue="slate",
         neutral_hue="slate",
         font=gr.themes.GoogleFont("Inter")
     ),
-    examples=mcp_examples,
-    cache_examples=False,
     css=custom_css,
-    analytics_enabled=False,
-    show_progress="minimal"
-)
-
-# Additional configuration
-app.queue(
-    default_concurrency_limit=20,
-    max_size=50
-)
+    title="Quasar LLM Audio Chat"
+) as app:
+    
+    gr.HTML("""
+        <div style="text-align: center; margin-bottom: 2rem;">
+            <h1>✨ Quasar LLM Audio Chat</h1>
+            <p class="description">
+                🎤 Real-time voice-powered web search with intelligent responses<br>
+                Speak your questions or type them - get instant answers with audio feedback!
+            </p>
+        </div>
+    """)
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            # Chat interface
+            chatbot = gr.Chatbot(
+                value=[],
+                height=400,
+                show_label=False,
+                container=True,
+                bubble_full_width=False,
+                render_markdown=True,
+                type="messages"
+            )
+            
+            # Audio input section
+            with gr.Row():
+                with gr.Column(scale=3):
+                    audio_input = gr.Audio(
+                        sources=["microphone"],
+                        type="numpy",
+                        label="🎤 Voice Input",
+                        show_label=True,
+                        container=True,
+                        elem_classes=["audio-input"]
+                    )
+                
+                with gr.Column(scale=1):
+                    audio_submit = gr.Button(
+                        "🎤 Send Voice",
+                        variant="primary",
+                        size="lg",
+                        elem_classes=["audio-input"]
+                    )
+            
+            # Text input as backup
+            with gr.Row():
+                text_input = gr.Textbox(
+                    placeholder="💬 Or type your message here...",
+                    container=False,
+                    scale=7,
+                    show_label=False,
+                    lines=1,
+                    max_lines=3,
+                    elem_classes=["text-input"]
+                )
+                text_submit = gr.Button("Send", variant="secondary")
+            
+            # Status indicator
+            status = gr.Textbox(
+                value="Ready for voice or text input",
+                label="Status",
+                interactive=False,
+                elem_classes=["status-indicator"]
+            )
+    
+    # Example questions
+    gr.Examples(
+        examples=quasar_examples,
+        inputs=[text_input],
+        label="✨ Try these questions:",
+        elem_classes=["examples"]
+    )
+    
+    # Audio processing function
+    def process_audio(audio, history):
+        if audio is None:
+            return history, "Please record some audio first"
+        
+        try:
+            # Convert numpy array to audio format for speech recognition
+            sample_rate, audio_data = audio
+            
+            # Convert to WAV format
+            wav_buffer = io.BytesIO()
+            with wave.open(wav_buffer, 'wb') as wav_file:
+                wav_file.setnchannels(1)
+                wav_file.setsampwidth(2)
+                wav_file.setframerate(sample_rate)
+                wav_file.writeframes((audio_data * 32767).astype(np.int16).tobytes())
+            
+            wav_buffer.seek(0)
+            return audio_chat.process_audio_message(wav_buffer.read(), history)
+        except Exception as e:
+            error_msg = f"Audio processing error: {str(e)}"
+            history.append({"role": "assistant", "content": error_msg})
+            return history, error_msg
+    
+    # Text processing function
+    def process_text(text, history):
+        if not text.strip():
+            return history, "", "Please enter a message"
+        
+        history.append({"role": "user", "content": text})
+        
+        try:
+            response = webSearch(text)
+            history.append({"role": "assistant", "content": response})
+            
+            # Convert response to speech
+            threading.Thread(target=audio_chat.text_to_speech, args=(response,), daemon=True).start()
+            
+            return history, "", f"Processed: {text[:50]}..."
+        except Exception as e:
+            error_msg = f"Search error: {str(e)}"
+            history.append({"role": "assistant", "content": error_msg})
+            return history, "", error_msg
+    
+    # Event handlers
+    audio_submit.click(
+        process_audio,
+        inputs=[audio_input, chatbot],
+        outputs=[chatbot, status]
+    )
+    
+    text_submit.click(
+        process_text,
+        inputs=[text_input, chatbot],
+        outputs=[chatbot, text_input, status]
+    )
+    
+    text_input.submit(
+        process_text,
+        inputs=[text_input, chatbot],
+        outputs=[chatbot, text_input, status]
+    )
 
+# Launch configuration
 if __name__ == "__main__":
     app.launch(
         mcp_server=True,
@@ -102,6 +336,6 @@ if __name__ == "__main__":
         inbrowser=True,
         show_error=True,
         quiet=False,
-        favicon_path=None,
-        ssl_verify=False
+        server_name="0.0.0.0",
+        server_port=7860
     )