Update app.py

app.py

@@ -140,118 +140,6 @@
 # if __name__ == "__main__":
 #     demo.launch()
 
-# import gradio as gr
-# from huggingface_hub import InferenceClient
-# import tempfile
-
-# # Initialize clients
-# chat_client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
-# stt_client = InferenceClient("openai/whisper-large-v3")
-
-# def transcribe_audio(audio_file):
-#     """Convert audio to text using Whisper model"""
-#     with open(audio_file, "rb") as f:
-#         result = stt_client.automatic_speech_recognition(f.read())
-#     return result.text  # Extract only the text from the response
-
-# def respond(history, query):
-#     system_message = """You are a friendly Product Assistant. Follow these rules:
-#     1. If the query is product-related, provide structured recommendations
-#     2. Consider both voice and text inputs equally
-#     3. Format responses with bullet points and emojis
-#     4. Always acknowledge voice queries specifically"""
-    
-#     product_prompt = f"""Analyze this {'voice' if history[-1][0] == query else 'text'} query:
-#     "{query}"
-#     Recommend products considering:
-#     - User intent
-#     - Semantic meaning
-#     - Potential use cases
-#     - Price ranges
-#     Provide ranked list with brief explanations"""
-    
-#     messages = [
-#         {"role": "system", "content": system_message},
-#         {"role": "user", "content": product_prompt}
-#     ]
-
-#     # Build conversation history
-#     for entry in history[:-1]:  # Exclude current query
-#         messages.extend([
-#             {"role": "user", "content": entry[0]},
-#             {"role": "assistant", "content": entry[1]}
-#         ])
-
-#     # Generate streamed response
-#     response = ""
-#     for chunk in chat_client.chat_completion(
-#         messages,
-#         max_tokens=2048,
-#         stream=True,
-#         temperature=0.7,
-#         top_p=0.95,
-#     ):
-#         token = chunk.choices[0].delta.content
-#         response += token
-#         history[-1] = (history[-1][0], response)  # Update last entry
-#         yield history
-
-# # Custom styling
-# css = """
-# .gradio-container { background: #f5f7fa !important; }
-# .audio-input { background: white !important; border-radius: 10px; }
-# """
-
-# with gr.Blocks(css=css) as demo:
-#     gr.Markdown("# 🎤 Voice-Activated Product Advisor 🛍️")
-    
-#     with gr.Row():
-#         chatbot = gr.Chatbot(height=600, bubble_full_width=False)
-        
-#         with gr.Column():
-#             with gr.Tab("🎙️ Voice Input"):
-#                 audio_input = gr.Audio(
-#                     sources="microphone",
-#                     type="filepath",
-#                     label="Speak your product request",
-#                     elem_classes="audio-input"
-#                 )
-#             with gr.Tab("📝 Text Input"):
-#                 text_input = gr.Textbox(label="Type your request")
-#             submit_btn = gr.Button("🚀 Get Recommendations", variant="primary")
-
-#     def process_inputs(text, audio, history):
-#         """Handle both input types"""
-#         query = text.strip()
-#         if audio:
-#             query = transcribe_audio(audio)
-#             # Add voice-specific marker
-#             query = f"🎤 Voice Query: {query}"
-        
-#         if query:
-#             return history + [(query, None)]  # Proper tuple format
-#         return history
-
-#     submit_btn.click(
-#         process_inputs,
-#         [text_input, audio_input, chatbot],
-#         chatbot,
-#         queue=False
-#     ).then(
-#         respond,
-#         [chatbot, text_input],
-#         chatbot
-#     )
-
-#     # Clear inputs after submission
-#     submit_btn.click(
-#         lambda: [None, None],  # Clear audio and text inputs
-#         outputs=[text_input, audio_input]
-#     )
-
-# if __name__ == "__main__":
-#     demo.launch()
-
 import gradio as gr
 from huggingface_hub import InferenceClient
 import tempfile
@@ -262,33 +150,38 @@ stt_client = InferenceClient("openai/whisper-large-v3")
 
 def transcribe_audio(audio_file):
     """Convert audio to text using Whisper model"""
-    try:
-        with open(audio_file, "rb") as f:
-            result = stt_client.automatic_speech_recognition(f.read())
-        return result.text
-    except Exception as e:
-        print(f"Transcription error: {e}")
-        return "Could not process audio. Please try again."
+    with open(audio_file, "rb") as f:
+        result = stt_client.automatic_speech_recognition(f.read())
+    return result.text  # Extract only the text from the response
 
 def respond(history, query):
-    system_message = """You are a Voice-Aware Product Assistant. Rules:
-    1. Always acknowledge voice queries with 🎧 icon
-    2. Provide structured recommendations with emojis
-    3. Consider both voice and text inputs equally"""
+    system_message = """You are a friendly Product Assistant. Follow these rules:
+    1. If the query is product-related, provide structured recommendations
+    2. Consider both voice and text inputs equally
+    3. Format responses with bullet points and emojis
+    4. Always acknowledge voice queries specifically"""
     
-    product_prompt = f"""Analyze this {'🎧 VOICE' if '🎧' in query else '📝 TEXT'} query:
-    "{query.replace('🎧 VOICE: ', '')}"
+    product_prompt = f"""Analyze this {'voice' if history[-1][0] == query else 'text'} query:
+    "{query}"
     Recommend products considering:
-    - Voice tone analysis (if audio)
-    - Semantic meaning
     - User intent
-    - Price context"""
+    - Semantic meaning
+    - Potential use cases
+    - Price ranges
+    Provide ranked list with brief explanations"""
     
     messages = [
         {"role": "system", "content": system_message},
         {"role": "user", "content": product_prompt}
     ]
 
+    # Build conversation history
+    for entry in history[:-1]:  # Exclude current query
+        messages.extend([
+            {"role": "user", "content": entry[0]},
+            {"role": "assistant", "content": entry[1]}
+        ])
+
     # Generate streamed response
     response = ""
     for chunk in chat_client.chat_completion(
@@ -300,65 +193,49 @@ def respond(history, query):
     ):
         token = chunk.choices[0].delta.content
         response += token
-        history[-1] = (history[-1][0], response)
+        history[-1] = (history[-1][0], response)  # Update last entry
         yield history
 
+# Custom styling
 css = """
-.gradio-container { background: #f8f9fa !important; }
+.gradio-container { background: #f5f7fa !important; }
 .audio-input { background: white !important; border-radius: 10px; }
-.mic-status { color: #4a90e2; font-weight: bold; }
 """
 
-with gr.Blocks(css=css, title="Voice Product Assistant") as demo:
-    gr.Markdown("# 🎧 Voice-Activated Product Advisor 🛒")
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("# 🎤 Voice-Activated Product Advisor 🛍️")
     
     with gr.Row():
         chatbot = gr.Chatbot(height=600, bubble_full_width=False)
         
         with gr.Column():
-            # Audio input with status indicator
-            with gr.Group():
+            with gr.Tab("🎙️ Voice Input"):
                 audio_input = gr.Audio(
                     sources="microphone",
                     type="filepath",
-                    label="Click mic & speak",
-                    elem_classes="audio-input",
-                    interactive=True
+                    label="Speak your product request",
+                    elem_classes="audio-input"
                 )
-                mic_status = gr.Markdown("🔴 Mic offline", elem_classes="mic-status")
-            
-            # Text input
-            text_input = gr.Textbox(label="Or type your request")
-            
-            # Unified submit button
+            with gr.Tab("📝 Text Input"):
+                text_input = gr.Textbox(label="Type your request")
             submit_btn = gr.Button("🚀 Get Recommendations", variant="primary")
 
-    # Handle audio permissions
-    def request_mic_access():
-        return gr.update(text="🟢 Mic ready") if audio_input.is_enabled else gr.update(text="🔴 Mic blocked")
-
-    # Process inputs
     def process_inputs(text, audio, history):
+        """Handle both input types"""
         query = text.strip()
         if audio:
-            transcript = transcribe_audio(audio)
-            query = f"🎧 VOICE: {transcript}"
+            query = transcribe_audio(audio)
+            # Add voice-specific marker
+            query = f"🎤 Voice Query: {query}"
         
         if query:
-            return history + [(query, None)], ""
-        return history, ""
+            return history + [(query, None)]  # Proper tuple format
+        return history
 
-    # Connect all components
-    audio_input.change(
-        request_mic_access,
-        outputs=mic_status,
-        queue=False
-    )
-    
     submit_btn.click(
         process_inputs,
         [text_input, audio_input, chatbot],
-        [chatbot, text_input],
+        chatbot,
         queue=False
     ).then(
         respond,
@@ -366,5 +243,128 @@ with gr.Blocks(css=css, title="Voice Product Assistant") as demo:
         chatbot
     )
 
+    # Clear inputs after submission
+    submit_btn.click(
+        lambda: [None, None],  # Clear audio and text inputs
+        outputs=[text_input, audio_input]
+    )
+
 if __name__ == "__main__":
-    demo.launch(server_port=7860, share=False)
+    demo.launch()
+
+# import gradio as gr
+# from huggingface_hub import InferenceClient
+# import tempfile
+
+# # Initialize clients
+# chat_client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
+# stt_client = InferenceClient("openai/whisper-large-v3")
+
+# def transcribe_audio(audio_file):
+#     """Convert audio to text using Whisper model"""
+#     try:
+#         with open(audio_file, "rb") as f:
+#             result = stt_client.automatic_speech_recognition(f.read())
+#         return result.text
+#     except Exception as e:
+#         print(f"Transcription error: {e}")
+#         return "Could not process audio. Please try again."
+
+# def respond(history, query):
+#     system_message = """You are a Voice-Aware Product Assistant. Rules:
+#     1. Always acknowledge voice queries with 🎧 icon
+#     2. Provide structured recommendations with emojis
+#     3. Consider both voice and text inputs equally"""
+    
+#     product_prompt = f"""Analyze this {'🎧 VOICE' if '🎧' in query else '📝 TEXT'} query:
+#     "{query.replace('🎧 VOICE: ', '')}"
+#     Recommend products considering:
+#     - Voice tone analysis (if audio)
+#     - Semantic meaning
+#     - User intent
+#     - Price context"""
+    
+#     messages = [
+#         {"role": "system", "content": system_message},
+#         {"role": "user", "content": product_prompt}
+#     ]
+
+#     # Generate streamed response
+#     response = ""
+#     for chunk in chat_client.chat_completion(
+#         messages,
+#         max_tokens=2048,
+#         stream=True,
+#         temperature=0.7,
+#         top_p=0.95,
+#     ):
+#         token = chunk.choices[0].delta.content
+#         response += token
+#         history[-1] = (history[-1][0], response)
+#         yield history
+
+# css = """
+# .gradio-container { background: #f8f9fa !important; }
+# .audio-input { background: white !important; border-radius: 10px; }
+# .mic-status { color: #4a90e2; font-weight: bold; }
+# """
+
+# with gr.Blocks(css=css, title="Voice Product Assistant") as demo:
+#     gr.Markdown("# 🎧 Voice-Activated Product Advisor 🛒")
+    
+#     with gr.Row():
+#         chatbot = gr.Chatbot(height=600, bubble_full_width=False)
+        
+#         with gr.Column():
+#             # Audio input with status indicator
+#             with gr.Group():
+#                 audio_input = gr.Audio(
+#                     sources="microphone",
+#                     type="filepath",
+#                     label="Click mic & speak",
+#                     elem_classes="audio-input",
+#                     interactive=True
+#                 )
+#                 mic_status = gr.Markdown("🔴 Mic offline", elem_classes="mic-status")
+            
+#             # Text input
+#             text_input = gr.Textbox(label="Or type your request")
+            
+#             # Unified submit button
+#             submit_btn = gr.Button("🚀 Get Recommendations", variant="primary")
+
+#     # Handle audio permissions
+#     def request_mic_access():
+#         return gr.update(text="🟢 Mic ready") if audio_input.is_enabled else gr.update(text="🔴 Mic blocked")
+
+#     # Process inputs
+#     def process_inputs(text, audio, history):
+#         query = text.strip()
+#         if audio:
+#             transcript = transcribe_audio(audio)
+#             query = f"🎧 VOICE: {transcript}"
+        
+#         if query:
+#             return history + [(query, None)], ""
+#         return history, ""
+
+#     # Connect all components
+#     audio_input.change(
+#         request_mic_access,
+#         outputs=mic_status,
+#         queue=False
+#     )
+    
+#     submit_btn.click(
+#         process_inputs,
+#         [text_input, audio_input, chatbot],
+#         [chatbot, text_input],
+#         queue=False
+#     ).then(
+#         respond,
+#         [chatbot, text_input],
+#         chatbot
+#     )
+
+# if __name__ == "__main__":
+#     demo.launch(server_port=7860, share=False)