app.py

# Import required libraries
import os
import pandas as pd
import streamlit as st
from transformers import pipeline
from sentence_transformers import SentenceTransformer, util
import requests
import json

# Configure Hugging Face API token securely
api_key = os.getenv("HF_API_KEY")

# Load the CSV dataset
try:
    data = pd.read_csv('genetic-Final.csv')
except FileNotFoundError:
    st.error("Dataset file not found. Please upload it to this directory.")

# Initialize Sentence Transformer model for RAG-based retrieval
retriever_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')

# Preprocess the dataset for embeddings
if 'combined_description' not in data.columns:
    data['combined_description'] = (
        data['Symptoms'].fillna('') + " " +
        data['Severity Level'].fillna('') + " " +
        data['Risk Assessment'].fillna('') + " " +
        data['Treatment Options'].fillna('') + " " +
        data['Suggested Medical Tests'].fillna('') + " " +
        data['Minimum Values for Medical Tests'].fillna('') + " " +
        data['Emergency Treatment'].fillna('')
    )

# Generate embeddings for the combined description if not already done
if 'embeddings' not in data.columns:
    data['embeddings'] = data['combined_description'].apply(lambda x: retriever_model.encode(x).tolist())

# Function to retrieve relevant information based on user query
def get_relevant_info(query, top_k=3):
    query_embedding = retriever_model.encode(query)
    similarities = [util.cos_sim(query_embedding, doc_emb)[0][0].item() for doc_emb in data['embeddings']]
    top_indices = sorted(range(len(similarities)), key=lambda i: similarities[i], reverse=True)[:top_k]
    return data.iloc[top_indices]

# Function to generate response using Hugging Face Model API
# def generate_response(input_text, relevant_info):
#     # Concatenate the relevant information as context for the model
#     context = "\n".join(relevant_info['combined_description'].tolist())
#     input_with_context = f"Context: {context}\n\nUser Query: {input_text}"
    
#     api_url = "https://api-inference.huggingface.co/models/m42-health/Llama3-Med42-8B"
#     headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACEHUB_API_TOKEN')}"}
#     payload = {"inputs": input_with_context}

#     try:
#         response = requests.post(api_url, headers=headers, json=payload)
#         response_data = response.json()
#         if isinstance(response_data, list) and "generated_text" in response_data[0]:
#             return response_data[0]["generated_text"]
#         else:
#             return "Unexpected response format from API."
#     except Exception as e:
#         st.error(f"Error during API request: {e}")
#         return "Error processing your request."

def generate_response(input_text, relevant_info):
    # Concatenate the relevant information as context for the model
    context = "\n".join(relevant_info['combined_description'].tolist())
    input_with_context = f"Context: {context}\n\nUser Query: {input_text}"
    
    api_url = "https://api-inference.huggingface.co/models/m42-health/Llama3-Med42-8B"
    headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACEHUB_API_TOKEN')}"}
    payload = {"inputs": input_with_context}

    try:
        response = requests.post(api_url, headers=headers, json=payload)
        response_data = response.json()
        
        # Print or display the raw response data
        st.write("Raw API response:", response_data)
        
        # Check and parse the response
        if isinstance(response_data, list) and "generated_text" in response_data[0]:
            return response_data[0]["generated_text"]
        else:
            return "Unexpected response format from API."
    except Exception as e:
        st.error(f"Error during API request: {e}")
        return "Error processing your request."

# Check and parse the response if it's a single JSON object
if isinstance(response_data, dict) and "generated_text" in response_data:
    return response_data["generated_text"]


# Streamlit UI for the FAQ Chatbot
def main():
    st.title("Medical FAQ Chatbot")
    st.sidebar.header("Ask a Question or Upload a Medical Report")

    # Text input for user queries
    user_query = st.sidebar.text_input("Type your medical question")

    # File uploader for medical report (optional)
    uploaded_file = st.sidebar.file_uploader("Upload a medical report (optional)", type=["txt", "pdf", "csv"])

    # Process the query if provided
    if user_query:
        # Retrieve relevant information from dataset
        relevant_info = get_relevant_info(user_query)

        # Generate a combined FAQ-style response
        faq_response = generate_response(user_query, relevant_info)
        st.write("### FAQ Response:")
        st.write(faq_response)

    # Process the uploaded file if any
    if uploaded_file:
        # Placeholder for handling file analysis
        st.write("### Uploaded Report Analysis:")
        report_text = "Extracted report content here"  # Placeholder for file processing logic
        st.write(report_text)

if __name__ == "__main__":
    main()