Update app.py

app.py

@@ -63,48 +63,50 @@
 # if __name__ == "__main__":
 #     demo.launch()
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    image: Image,  # Image input
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    # Add current user message
-    messages.append({"role": "user", "content": message})
-
+from PIL import Image
+import base64
+import io
+import gradio as gr
+from huggingface_hub import InferenceClient
+import requests
+
+# Function to convert image to base64
+def image_to_base64(image: Image):
+    buffered = io.BytesIO()
+    image.save(buffered, format="PNG")
+    return base64.b64encode(buffered.getvalue()).decode("utf-8")
+
+# Function to respond to input
+def respond(message: str, image: Image):
     # Convert image to base64
-    image_bytes = io.BytesIO()
-    image.save(image_bytes, format='PNG')
-    image_bytes.seek(0)
-    image_base64 = base64.b64encode(image_bytes.getvalue()).decode('utf-8')
+    image_base64 = image_to_base64(image)
+
+    # Initialize the Hugging Face client
+    client = InferenceClient("your_huggingface_model")
 
     try:
-        # Pass the base64 image and prompt
+        # Call the text-to-image method
         response_data = client.text_to_image(images=image_base64, prompt=message)
+
+        # Convert the response data (image) into a PIL Image
+        image_response = Image.open(io.BytesIO(response_data))
         
-        # Print out the response data for debugging
-        print("Response Data:", response_data)
-
-        # Check if the response contains an image
-        if isinstance(response_data, dict) and 'image' in response_data:
-            # Decode the base64 image response
-            image_response = response_data['image']
-            image_bytes = base64.b64decode(image_response)
-            image = Image.open(io.BytesIO(image_bytes))
-            image.show()  # Display the image or return it
-            return "Image processed successfully"
-        else:
-            return f"Error: No valid image found in response. Response: {response_data}"
+        return image_response
     except Exception as e:
-        return f"Error processing image: {e}"
+        return str(e)
+
+# Define the Gradio interface
+def create_interface():
+    with gr.Blocks() as demo:
+        chatbot = gr.Chatbot(type='messages')  # 'messages' format for chatbot
+        message_input = gr.Textbox()
+        image_input = gr.Image(type='pil')  # Image input as PIL image
+
+        # Define the interaction
+        message_input.submit(respond, inputs=[message_input, image_input], outputs=[chatbot])
+
+    return demo
+
+# Launch the interface
+if __name__ == "__main__":
+    create_interface().launch(share=True)  # Set share=True if you want to share the link publicly