Update app.py

app.py

@@ -16,29 +16,28 @@ def generate_response(input_text, image, openai_api_key, reasoning_effort="mediu
 
     openai.api_key = openai_api_key
 
-    # Process the input depending on whether it's text or an image
+    # If the user uploaded an image, convert it to base64 and use it for API call
     if image:
         # Convert the image to base64 string
         image_info = get_base64_string_from_image(image)
         input_text = f"data:image/png;base64,{image_info}"
 
-    # Prepare the messages for OpenAI API
+    # Check for text input and pass to API
+    if not input_text:
+        return "Error: Please provide either text, image, or voice input."
+
+    # Prepare the messages for OpenAI API based on the selected model
     if model_choice == "o1" and input_text:
-        messages = [
-            {"role": "user", "content": [{"type": "image_url", "image_url": {"url": input_text}}]}
-        ]
+        messages = [{"role": "user", "content": input_text}]
     elif model_choice == "o3-mini" and input_text:
-        messages = [
-            {"role": "user", "content": [{"type": "text", "text": input_text}]}
-        ]
-    
+        messages = [{"role": "user", "content": input_text}]
+
     try:
         # Call OpenAI API with the selected model
         response = openai.ChatCompletion.create(
             model=model_choice,  # Dynamically choose the model (o1 or o3-mini)
             messages=messages,
-            reasoning_effort=reasoning_effort,  # Set reasoning_effort for the response
-            max_completion_tokens=2000  # Limit response tokens to 2000
+            max_tokens=2000  # Limit response tokens to 2000
         )
 
         return response["choices"][0]["message"]["content"]
@@ -277,4 +276,4 @@ def create_interface():
 
 if __name__ == "__main__":
     demo = create_interface()  # Gradio multimodal chatbot
-    demo.launch()
+    demo.launch()