Update app.py

app.py

@@ -77,8 +77,9 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    image: Image
+    image: Image,  # Add image input to the function
 ):
+    # Prepare the system message and history for the conversation
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -87,43 +88,38 @@ def respond(
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
+    # Add the current user message
     messages.append({"role": "user", "content": message})
 
-    # Convert image to the format expected by the model
+    # Convert the PIL image to a byte stream
     image_bytes = io.BytesIO()
     image.save(image_bytes, format='PNG')
     image_bytes.seek(0)
 
-    # Use a different method for image inputs if chat_completion does not support it
-    response = ""
-
-    # Modify here to use the correct API for image + text queries (check model docs)
-    response_data = client.text2image(images=image_bytes, text=message)  # example method; adjust according to actual API
+    # Use InferenceClient to handle the image and text input to the model
+    # Use the correct method text_to_image
+    response_data = client.text_to_image(images=image_bytes, text=message)  # Corrected method name
 
-    # Process the response (if any) from the image model
-    for result in response_data:
-        response += result['text']  # or adjust based on response format
+    # Process the response from the model
+    response = ""
+    if response_data:
+        for result in response_data:
+            response += result.get('text', '')  # Process based on the response format
 
     return response
 
+# Create the Gradio interface with an image input
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
         gr.Image(type="pil", label="Upload an Image"),  # Image input for vision tasks
     ],
 )
 
 if __name__ == "__main__":
-    demo.launch()
-
+    demo.launch(share=True)  # Set share=True to create a public link