Update app.py

app.py

@@ -1,22 +1,6 @@
 import streamlit as st
 from transformers import pipeline, AutoModelForImageClassification, AutoFeatureExtractor
 from PIL import Image
-import openai
-import os
-from dotenv import load_dotenv
-
-# =======================
-# Load Environment Variables from .env File
-# =======================
-load_dotenv()  # Explicitly load the .env file
-
-# Set OpenAI API key
-openai.api_key = os.getenv("OPENAI_API_KEY")
-
-# Debugging: Check if API key is loaded
-if not openai.api_key or not openai.api_key.startswith("sk-"):
-    st.error("OpenAI API key is not set or is invalid. Please check the `.env` file or your environment variable setup.")
-    st.stop()
 
 # =======================
 # Streamlit Page Config
@@ -35,7 +19,6 @@ st.set_page_config(
 def load_model():
     """
     Load the pre-trained skin cancer classification model using PyTorch.
-    Use the AutoModelForImageClassification and AutoFeatureExtractor for explicit local caching.
     """
     try:
         extractor = AutoFeatureExtractor.from_pretrained("Anwarkh1/Skin_Cancer-Image_Classification")
@@ -48,28 +31,33 @@ def load_model():
 model = load_model()
 
 # =======================
-# Generate OpenAI Explanation
+# Local Explanation Generator
 # =======================
-def generate_openai_explanation(label, confidence):
+def generate_local_explanation(label, confidence):
     """
-    Generate a detailed explanation for the classification result using OpenAI's GPT model.
+    Generate a simple explanation for the classification result.
     """
-    prompt = (
-        f"The AI model has classified an image of a skin lesion as **{label}** with a confidence of **{confidence:.2%}**.\n"
-        f"Explain what this classification means, including potential characteristics of this lesion type, "
-        f"what steps a patient should take next, and how the AI might have arrived at this conclusion. "
-        f"Use language that is easy for a non-medical audience to understand."
-    )
-    try:
-        response = openai.Completion.create(
-            model="text-davinci-003",  # Replace with "gpt-4" if available
-            prompt=prompt,
-            max_tokens=300,
-            temperature=0.7
+    explanations = {
+        "Melanoma": (
+            "Melanoma is a serious type of skin cancer that develops in the cells that produce melanin. "
+            "If detected early, it is often treatable. You should consult a dermatologist immediately."
+        ),
+        "Basal Cell Carcinoma": (
+            "Basal Cell Carcinoma is a common form of skin cancer that grows slowly and is typically not life-threatening. "
+            "Still, it requires medical attention to prevent further complications."
+        ),
+        "Benign Lesion": (
+            "A benign lesion is a non-cancerous growth on the skin. While it is usually harmless, "
+            "consulting a dermatologist can help ensure no further treatment is needed."
+        ),
+        "Other": (
+            "The AI could not confidently classify the lesion. It's strongly recommended to consult a dermatologist for further evaluation."
         )
-        return response.choices[0].text.strip()
-    except Exception as e:
-        return f"Error generating explanation: {e}"
+    }
+
+    explanation = explanations.get(label, explanations["Other"])
+    confidence_msg = f"The model is {confidence:.2%} confident in this prediction. "
+    return confidence_msg + explanation
 
 # =======================
 # Streamlit App Title and Sidebar
@@ -116,8 +104,7 @@ if uploaded_image:
                     st.error("Low confidence in the prediction. Results should be interpreted with caution.")
 
                 # Generate explanation
-                with st.spinner("Generating a detailed explanation..."):
-                    explanation = generate_openai_explanation(label, confidence)
+                explanation = generate_local_explanation(label, confidence)
 
                 st.markdown("### Explanation")
                 st.write(explanation)