Delete app.py

app.py

@@ -1,185 +0,0 @@
-import os
-import streamlit as st
-import numpy as np
-import faiss
-from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModel
-from groq import Groq
-
-# Load API Key from Environment
-groq_api_key = os.environ.get("GROQ_API_KEY")
-if groq_api_key is None:
-    st.error("GROQ_API_KEY environment variable not set.")
-    st.stop()
-
-# Initialize Groq Client
-try:
-    client = Groq(api_key=groq_api_key)
-except Exception as e:
-    st.error(f"Error initializing Groq client: {e}")
-    st.stop()
-
-# Load PubMedBERT Model (Try Groq API first, then Hugging Face)
-try:
-    pubmedbert_tokenizer = AutoTokenizer.from_pretrained("NeuML/pubmedbert-base-embeddings")
-    pubmedbert_model = AutoModel.from_pretrained("NeuML/pubmedbert-base-embeddings")
-    pubmedbert_pipeline = pipeline('feature-extraction', model=pubmedbert_model, tokenizer=pubmedbert_tokenizer, device=-1)
-except Exception:
-    st.warning("Error loading PubMedBERT from Groq API. Using Hugging Face model.")
-    pubmedbert_tokenizer = AutoTokenizer.from_pretrained("microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext")
-    pubmedbert_model = AutoModelForSequenceClassification.from_pretrained("microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext")
-    pubmedbert_pipeline = pipeline('feature-extraction', model=pubmedbert_model, tokenizer=pubmedbert_tokenizer, device=-1)
-
-# Initialize FAISS Index
-embedding_dim = 768
-index = faiss.IndexFlatL2(embedding_dim)
-
-# Function to Check Query Category
-def preprocess_query(query):
-    tokens = query.lower().split()
-    epilepsy_keywords = ["seizure", "epilepsy", "convulsion", "neurology", "brain activity", "headache related to epilepsy"] # Added specific phrase
-    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, is_healthcare_related, is_general
-
-# Function to Generate Response with Chat History
-def generate_response(user_query, chat_history):
-    # Grammatical Correction using LLaMA (Hidden from User)
-    try:
-        correction_prompt = f"""
-        Correct the following user query for grammar and spelling errors, but keep the original intent intact.
-        Do not add or remove any information, just fix the grammar.
-        User Query: {user_query}
-        Corrected Query:
-        """
-        grammar_completion = client.chat.completions.create(
-            messages=[{"role": "user", "content": correction_prompt}],
-            model="llama-3.3-70b-versatile",
-            stream=False,
-        )
-        corrected_query = grammar_completion.choices[0].message.content.strip()
-        # If correction fails or returns empty, use original query
-        if not corrected_query:
-            corrected_query = user_query
-    except Exception as e:
-        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, is_healthcare_related, is_general = preprocess_query(corrected_query) # Get category flags
-
-    # Greeting Responses
-    greetings = ["hello", "hi", "hey"]
-    if any(word in tokens for word in greetings):
-        return "👋 Hello! How can I assist you today?"
-
-    # If Epilepsy Related - Use Epilepsy Focused Response
-    if is_epilepsy_related:
-        # Try Getting Medical Insights from PubMedBERT
-        try:
-            pubmedbert_embeddings = pubmedbert_pipeline(corrected_query) # Use corrected query for PubMedBERT
-            embedding_mean = np.mean(pubmedbert_embeddings[0], axis=0)
-            index.add(np.array([embedding_mean]))
-            pubmedbert_insights = "**PubMedBERT Analysis:** ✅ Query is relevant to epilepsy research."
-        except Exception as e:
-            pubmedbert_insights = f"⚠️ Error during PubMedBERT analysis: {e}"
-
-        # Use LLaMA for Final Response Generation with Chat History Context (Epilepsy Focus)
-        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"
-
-            epilepsy_prompt = f"""
-            {prompt_history}
-            **User Query:** {corrected_query} # Use corrected query for final response generation
-            **Instructions:** Provide a concise, structured, and human-friendly response specifically about epilepsy or seizures, considering the conversation history if available.
-            """
-
-            chat_completion = client.chat.completions.create(
-                messages=[{"role": "user", "content": epilepsy_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}"
-
-        return f"**NeuroGuard:** ✅ **Analysis:**\n{pubmedbert_insights}\n\n**Response:**\n{model_response}"
-
-    # If Healthcare Related but Not Epilepsy - Provide General Wellness Tips and Basic Remedies
-    elif is_healthcare_related:
-        remedy_suggestions = {
-            "headache": "For headaches, you can try resting in a quiet, dark room, staying hydrated, and applying a cold compress to your forehead. Over-the-counter pain relievers like ibuprofen or acetaminophen may also help.",
-            "pain": "For general pain, rest, gentle stretching, and applying heat or ice to the affected area can provide relief. Over-the-counter pain relievers might also be beneficial. ",
-            "legs pain": "For leg pain, try elevating your legs, applying heat or ice, and gentle stretching exercises. Staying hydrated and ensuring good circulation can also help. "
-            # Add more specific remedies as needed
-        }
-        suggested_remedy = "For general wellness:\n" # Default if no specific remedy keyword is found
-        for keyword, remedy in remedy_suggestions.items():
-            if keyword in corrected_query: # Check corrected query for keywords
-                suggested_remedy = remedy + "\n\n" # Use specific remedy if keyword found
-                break # Use only the first matching remedy for now
-
-        general_health_tips = (
-            "- 💧 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 and informational purposes only, and are not medical advice. Always consult a healthcare professional for any specific health concerns or before making significant changes to your health regimen."
-        )
-
-        response_content = f"**NeuroGuard:** 🩺 It seems your question '{user_query}' is about general health. While I focus on epilepsy, here's some information that might help:\n\n" # Use original user_query
-        response_content += suggested_remedy
-        response_content += general_health_tips # Always include general tips
-
-        return response_content
-
-
-    # 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" # Use original user_query
-            "**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."
-        )
-
-    # Fallback - should ideally not reach here
-    else:
-        return "🤔 I'm not sure how to respond to that."
-
-
-# Streamlit UI Setup
-st.set_page_config(page_title="NeuroGuard: Epilepsy & Health Chatbot", layout="wide") # Updated title
-st.title("🧠 NeuroGuard: Epilepsy & Health Chatbot") # Updated title
-st.write("💬 Ask me anything about epilepsy, seizures, and general health. I remember our conversation!") # Updated description
-
-# Initialize Chat History in Session State
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = []
-
-# Display Chat History
-for message in st.session_state.chat_history:
-    with st.chat_message(message["role"]):
-        st.markdown(message["content"])
-
-# User Input
-if prompt := st.chat_input("Type your question here..."):
-    st.session_state.chat_history.append({"role": "user", "content": prompt})
-    with st.chat_message("user"):
-        st.markdown(prompt)
-
-    # Generate Bot Response
-    with st.chat_message("bot"):
-        with st.spinner("🤖 Thinking..."):
-            try:
-                response = generate_response(prompt, st.session_state.chat_history) # Pass chat history here
-                st.markdown(response)
-                st.session_state.chat_history.append({"role": "bot", "content": response})
-            except Exception as e:
-                st.error(f"⚠️ Error processing query: {e}")