Updated app.py

app.py

@@ -3,6 +3,7 @@ from transformers import AutoProcessor, LlavaForConditionalGeneration
 from PIL import Image
 import torch
 
+# Load model & processor
 model_id = "llava-hf/llava-1.5-7b-hf"
 processor = AutoProcessor.from_pretrained(model_id)
 model = LlavaForConditionalGeneration.from_pretrained(
@@ -12,12 +13,13 @@ model = LlavaForConditionalGeneration.from_pretrained(
     device_map="auto",
 )
 
-def chat_with_llava(image, question, history=[]):
+
+# Main prediction function
+def analyze_palm(image, question, history):
     if image is None or not question.strip():
-        history.append([question, "Please provide both an image and a question."])
-        return history
+        history.append((question, "Please provide both image and question."))
+        return history, ""
 
-    # Format multimodal prompt
     conversation = [
         {"role": "user", "content": [
             {"type": "text", "text": question},
@@ -25,19 +27,34 @@ def chat_with_llava(image, question, history=[]):
         ]}
     ]
     prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
-
-    # Encode inputs
     inputs = processor(images=image, text=prompt, return_tensors="pt").to(model.device)
-    outputs = model.generate(**inputs, max_new_tokens=512)
-    answer = processor.decode(outputs[0], skip_special_tokens=True)
 
-    history.append([question, answer])
-    return history
+    output = model.generate(**inputs, max_new_tokens=512)
+    response = processor.decode(output[0], skip_special_tokens=True)
 
-chat_interface = gr.ChatInterface(
-    fn=chat_with_llava,
-    inputs=[gr.Image(type="pil", label="Palm Image"), gr.Textbox(label="Your Question")],
-    title="🖐️ AI Palm Reader",
-    description="Upload your palm image and ask a question—LLaVA will respond with a palmistry-style reading."
-)
-chat_interface.launch()
+    history.append((question, response))
+    return history, ""
+
+
+# Build UI using Blocks
+with gr.Blocks() as demo:
+    gr.Markdown("## 🖐️ AI Palm Reader\nUpload a palm image and ask a question. Get a palmistry-style response.")
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            image_input = gr.Image(type="pil", label="Palm Image")
+            prompt_input = gr.Textbox(lines=2, label="Your Question", placeholder="What does my palm say?")
+            submit_btn = gr.Button("Ask")
+
+        with gr.Column(scale=2):
+            chatbot = gr.Chatbot(label="Palmistry Chat")
+
+    state = gr.State([])
+
+    submit_btn.click(
+        fn=analyze_palm,
+        inputs=[image_input, prompt_input, state],
+        outputs=[chatbot, prompt_input]
+    )
+
+demo.launch()