Update app.py

app.py

@@ -33,14 +33,17 @@ except Exception:
 embedding_dim = 768
 index = faiss.IndexFlatL2(embedding_dim)
 
-# Function to Check if Query is Related to Epilepsy
+# Function to Check Query Category
 def preprocess_query(query):
     tokens = query.lower().split()
     epilepsy_keywords = ["seizure", "epilepsy", "convulsion", "neurology", "brain activity"]
+    healthcare_keywords = ["headache", "fever", "blood pressure", "diabetes", "cough", "flu", "nutrition", "mental health", "pain", "legs", "body pain", "health", "medical", "symptoms", "treatment", "disease"] # Extended healthcare keywords
 
     is_epilepsy_related = any(k in tokens for k in epilepsy_keywords)
+    is_healthcare_related = any(k in tokens for k in healthcare_keywords) and not is_epilepsy_related # Healthcare but NOT epilepsy
+    is_general = not is_epilepsy_related and not is_healthcare_related # Truly general queries
 
-    return tokens, is_epilepsy_related
+    return tokens, is_epilepsy_related, is_healthcare_related, is_general
 
 # Function to Generate Response with Chat History
 def generate_response(user_query, chat_history):
@@ -65,7 +68,7 @@ def generate_response(user_query, chat_history):
         corrected_query = user_query # Fallback to original query if correction fails
         print(f"⚠️ Grammar correction error: {e}") # Optional: Log the error for debugging
 
-    tokens, is_epilepsy_related = preprocess_query(corrected_query) # Use corrected query for processing
+    tokens, is_epilepsy_related, is_healthcare_related, is_general = preprocess_query(corrected_query) # Get category flags
 
     # Greeting Responses
     greetings = ["hello", "hi", "hey"]
@@ -109,43 +112,33 @@ def generate_response(user_query, chat_history):
 
         return f"**NeuroGuard:** ✅ **Analysis:**\n{pubmedbert_insights}\n\n**Response:**\n{model_response}"
 
+    # If Healthcare Related but Not Epilepsy - Provide General Wellness Tips
+    elif is_healthcare_related:
+        general_health_tips = (
+            "For general health and well-being:\n"
+            "- 💧 Stay hydrated by drinking plenty of water throughout the day.\n"
+            "- 🍎 Maintain a balanced diet rich in fruits, vegetables, and whole grains.\n"
+            "- 🚶‍♀️ Incorporate regular physical activity into your daily routine.\n"
+            "- 😴 Ensure you get adequate sleep to allow your body to rest and recover.\n"
+            "- 🧘 Practice stress-reducing activities such as deep breathing or meditation.\n"
+            "- 🩺 **Important:** These tips are for general wellness. Always consult a healthcare professional for any specific health concerns or before making significant changes to your health regimen."
+        )
+        return (
+            f"**NeuroGuard:** 🩺 It sounds like your question '{user_query}' is about general health. While I specialize in epilepsy, here are some general wellness tips that might be helpful:\n\n" # Use original user_query in response
+            f"{general_health_tips}"
+        )
 
-    # If Not Epilepsy Related - Try to Answer as General Health Query
-    else:
-        # Try Getting Medical Insights from PubMedBERT (even for general health)
-        try:
-            pubmedbert_embeddings = pubmedbert_pipeline(corrected_query)
-            embedding_mean = np.mean(pubmedbert_embeddings[0], axis=0)
-            index.add(np.array([embedding_mean]))
-            pubmedbert_insights = "**PubMedBERT Analysis:**  PubMed analysis performed for health-related context." # General analysis message
-        except Exception as e:
-            pubmedbert_insights = f"⚠️ Error during PubMedBERT analysis: {e}"
-
-        # Use LLaMA for General Health Response Generation with Chat History Context
-        try:
-            prompt_history = ""
-            if chat_history:
-                prompt_history += "**Chat History:**\n"
-                for message in chat_history:
-                    prompt_history += f"{message['role'].capitalize()}: {message['content']}\n"
-                prompt_history += "\n"
-
-            general_health_prompt = f"""
-            {prompt_history}
-            **User Query:** {corrected_query}
-            **Instructions:** Provide a concise, structured, and human-friendly response to the general health query, considering the conversation history if available. If the query is clearly not health-related, respond generally.
-            """
 
-            chat_completion = client.chat.completions.create(
-                messages=[{"role": "user", "content": general_health_prompt}],
-                model="llama-3.3-70b-versatile",
-                stream=False,
-            )
-            model_response = chat_completion.choices[0].message.content.strip()
-        except Exception as e:
-            model_response = f"⚠️ Error generating response with LLaMA: {e}"
+    # If General Query (Not Healthcare or Epilepsy Related) - Provide a different response
+    elif is_general:
+        return (
+            f"**NeuroGuard:** 💡  My expertise is focused on epilepsy and general health.  For topics outside of these areas, like '{user_query}', I may not be the best resource. \n\n"
+            "**Tip:** For general knowledge questions, you might find better answers using a general search engine or a chatbot trained on a broader range of topics."
+        )
 
-        return f"**NeuroGuard:** ✅ **Analysis:**\n{pubmedbert_insights}\n\n**Response:**\n{model_response}"
+    # Fallback - should ideally not reach here
+    else:
+        return "🤔 I'm not sure how to respond to that."
 
 
 # Streamlit UI Setup