Update app.py

app.py

@@ -5,7 +5,7 @@ from PIL import Image
 import io
 
 # Function to send the request to OpenAI API with an image or text input
-def generate_response(input_text, image, openai_api_key, reasoning_effort="medium"):
+def generate_response(input_text, image, openai_api_key, reasoning_effort="medium", model_choice="o1"):
     if not openai_api_key:
         return "Error: No API key provided."
 
@@ -18,14 +18,19 @@ def generate_response(input_text, image, openai_api_key, reasoning_effort="mediu
         input_text = f"data:image/png;base64,{image_info}"
 
     # Prepare the messages for OpenAI API
-    messages = [
-        {"role": "user", "content": [{"type": "image_url", "image_url": {"url": input_text}}]}
-    ]
-
+    if model_choice == "o1":
+        messages = [
+            {"role": "user", "content": [{"type": "image_url", "image_url": {"url": input_text}}]}
+        ]
+    elif model_choice == "o3-mini":
+        messages = [
+            {"role": "user", "content": [{"type": "text", "text": input_text}]}
+        ]
+    
     try:
-        # Call OpenAI API with the "o1" model
+        # Call OpenAI API with the selected model
         response = openai.ChatCompletion.create(
-            model="o1",  # Using model "o1"
+            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
@@ -45,8 +50,8 @@ def get_base64_string_from_image(pil_image):
     return base64_str
 
 # The function that will be used by Gradio interface
-def chatbot(input_text, image, openai_api_key, reasoning_effort, history=[]):
-    response = generate_response(input_text, image, openai_api_key, reasoning_effort)
+def chatbot(input_text, image, openai_api_key, reasoning_effort, model_choice, history=[]):
+    response = generate_response(input_text, image, openai_api_key, reasoning_effort, model_choice)
     
     # Append the response to the history
     history.append((f"User: {input_text}", f"Assistant: {response}"))
@@ -85,13 +90,19 @@ def create_interface():
                 choices=["low", "medium", "high"],
                 value="medium"
             )
+            model_choice = gr.Dropdown(
+                label="Select Model",
+                choices=["o1", "o3-mini"],
+                value="o1",  # Default to 'o1' for image-related tasks
+                description="Choose 'o1' for image-related questions and 'o3-mini' for text-related questions."
+            )
             submit_btn = gr.Button("Send")
             clear_btn = gr.Button("Clear History")
 
         chat_history = gr.Chatbot()
 
         # Button interactions
-        submit_btn.click(fn=chatbot, inputs=[input_text, image_input, openai_api_key, reasoning_effort, chat_history], outputs=[input_text, chat_history])
+        submit_btn.click(fn=chatbot, inputs=[input_text, image_input, openai_api_key, reasoning_effort, model_choice, chat_history], outputs=[input_text, chat_history])
         clear_btn.click(fn=clear_history, inputs=[], outputs=[chat_history, chat_history])
 
     return demo