Update app.py

app.py

@@ -3,6 +3,7 @@ import os
 import tensorflow as tf
 import numpy as np
 import requests
+import time
 
 from langchain_groq import ChatGroq
 from langchain.agents import initialize_agent
@@ -35,23 +36,21 @@ def classify_image_and_stats(image_input):
     img_norm = img / 255.0
     img_batch = np.expand_dims(img_norm, axis=0)
 
-    prediction = model.predict(img_batch)[0]  # (256, 256, 1)
+    prediction = model.predict(img_batch)[0]
     mask = (prediction > 0.5).astype(np.uint8)
 
     if mask.ndim == 3 and mask.shape[-1] == 1:
         mask = np.squeeze(mask, axis=-1)
 
-    # Tumor stats
     tumor_area = np.sum(mask)
     total_area = IMG_HEIGHT * IMG_WIDTH
     tumor_ratio = tumor_area / total_area
 
-    tumor_label = "Tumor Detected" if tumor_ratio > 0.005 else "No Tumor Detected"
+    tumor_label = "Tumor Detected" if tumor_ratio > 0.0025 else "No Tumor Detected"
 
-    # === Overlay mask on original ===
-    overlay = np.array(img)  # original resized input
+    overlay = np.array(img)
     red_mask = np.zeros_like(overlay)
-    red_mask[..., 0] = mask * 255  # Red channel
+    red_mask[..., 0] = mask * 255
 
     overlay_img = np.clip(0.6 * overlay + 0.4 * red_mask, 0, 255).astype(np.uint8)
 
@@ -65,7 +64,7 @@ def classify_image_and_stats(image_input):
     return overlay_img, stats
 
 
-# === Gradio handler ===
+# === Gradio handler with typing effect ===
 def rishigpt_handler(image_input, groq_api_key):
     os.environ["GROQ_API_KEY"] = groq_api_key
 
@@ -99,22 +98,24 @@ def rishigpt_handler(image_input, groq_api_key):
     user_query = "Give me the segmentation details"
     classification = agent.run(user_query)
 
-    # Better prompt + output parser
     prompt = PromptTemplate(
         input_variables=["result"],
         template=(
             "You are a compassionate AI radiologist. "
             "Read this tumor analysis result: {result}. "
-            "Summarize the situation like you're talking to the patient in calm, clear language. "
-            "Add any recommendations for next steps too, but keep it easy to understand."
+            "Summarize the situation for the patient in natural paragraphs, calm, clear tone, with next steps."
         )
     )
 
     chain = prompt | llm
-    description = chain.invoke({"result": classification}).content.strip()
-
-    return overlay_img, description
+    final_text = chain.invoke({"result": classification}).content.strip()
 
+    # === Yield mask and typing chunks ===
+    displayed_text = ""
+    for char in final_text:
+        displayed_text += char
+        time.sleep(0.015)
+        yield overlay_img, displayed_text
 
 # === Gradio UI ===
 inputs = [
@@ -124,7 +125,7 @@ inputs = [
 
 outputs = [
     gr.Image(type="numpy", label="Overlay: Brain MRI + Tumor Mask"),
-    gr.Textbox(label="Doctor's Explanation")
+    gr.Textbox(label="Doctor's Explanation (Typing...)")
 ]
 
 if __name__ == "__main__":
@@ -132,6 +133,6 @@ if __name__ == "__main__":
         fn=rishigpt_handler,
         inputs=inputs,
         outputs=outputs,
-        title="🧠 RishiGPT Medical Brain Segmentation",
-        description="UNet++ Brain Tumor Segmentation with mask overlay, detailed stats, and human-like explanation."
+        title="RishiGPT Medical Brain Segmentation",
+        description="UNet++ Brain Tumor Segmentation with live mask overlay, detailed stats, and human-like typing explanation."
     ).launch()