Fix API key validation and Gradio chatbot format issues

- Remove unused OPENAI_API_KEY requirement and update to use GEMINI_API_KEY
- Fix Gradio chatbot format errors by ensuring all functions return proper [user, assistant] tuple format
- Resolve 'Data incompatible with tuples format' errors in respond() and response_audio() functions

app.py

@@ -226,7 +226,7 @@ class AppState:
 
 def validate_api_keys():
     """Validate required API keys for Spaces deployment"""
-    required_keys = ["GROQ_API_KEY", "OPENAI_API_KEY", "GOOGLE_API_KEY"]
+    required_keys = ["GROQ_API_KEY",  "GEMINI_API_KEY"]
     missing_keys = []
     
     for key in required_keys:
@@ -399,7 +399,14 @@ def respond(message, state):
     except Exception as e:
         error_response = f"Sorry, I encountered an error: {str(e)}"
         state.conversation.append({"role": "assistant", "content": error_response})
-        return "", state.conversation, state
+        
+        # Format conversation for display
+        conversation_display = []
+        for msg in state.conversation:
+            conversation_display.append([msg["content"] if msg["role"] == "user" else None, 
+                                       msg["content"] if msg["role"] == "assistant" else None])
+        
+        return "", conversation_display, state
 
 def build_interface():
     """Build the Gradio interface optimized for Spaces with high performance"""
@@ -666,7 +673,7 @@ def response_audio(state: AppState, audio: tuple, genre_value, mood_value, theme
     Process recorded audio and generate a response based on transcription.
     """
     if not audio:
-        return state, state.conversation
+        return state, []
 
     # Update state with current dropdown values
     state.genre, state.mood, state.theme = genre_value, mood_value, theme_value
@@ -698,7 +705,13 @@ def response_audio(state: AppState, audio: tuple, genre_value, mood_value, theme
 
         os.remove(file_name)
 
-    return state, state.conversation
+    # Format conversation for display
+    conversation_display = []
+    for msg in state.conversation:
+        conversation_display.append([msg["content"] if msg["role"] == "user" else None, 
+                                   msg["content"] if msg["role"] == "assistant" else None])
+    
+    return state, conversation_display
 
 def extract_lyrics_from_conversation(conversation):
     """