Create app.py

app.py

@@ -0,0 +1,104 @@
+# App
+# 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
+from pyngrok import ngrok
+
+# Set up Hugging Face API token
+
+api_key = os.getenv("HF_API_KEY")        # Replace with your Hugging Face API token
+
+
+# Load the CSV dataset
+data = pd.read_csv('/content/genetic_diseases_dataset.csv')
+
+
+# Initialize Sentence Transformer model for RAG-based retrieval
+retriever_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+
+# Create embeddings for the entire dataset for retrieval
+# data['embeddings'] = data['description'].apply(lambda x: retriever_model.encode(x))
+
+# Drop unnecessary columns (Unnamed columns)
+data = data.drop(columns=['Unnamed: 0', 'Unnamed: 11', 'Unnamed: 12', 'Unnamed: 13'])
+
+# Combine relevant columns into one combined description field
+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('')
+)
+
+# Initialize the Sentence Transformer model for embeddings
+retriever_model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+
+# Function to safely generate embeddings for each row
+def generate_embedding(description):
+    if description:  # Check if the description is not empty or NaN
+        return retriever_model.encode(description).tolist()  # Convert the numpy array to list
+    else:
+        return []
+
+# Generate embeddings for the combined description
+data['embeddings'] = data['combined_description'].apply(generate_embedding)
+
+# Function to retrieve relevant information from CSV dataset 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):
+    api_url = "https://api-inference.huggingface.co/models/m42-health/Llama3-Med42-8B"
+    headers = {"Authorization": f"Bearer {os.environ['HUGGINGFACEHUB_API_TOKEN']}"}
+    payload = {"inputs": input_text}
+
+    response = requests.post(api_url, headers=headers, json=payload)
+    return json.loads(response.content.decode("utf-8"))[0]["generated_text"]
+
+# Streamlit UI for the Chatbot
+def main():
+    st.title("Medical Report and Analysis Chatbot")
+    st.sidebar.header("Upload Medical Report or Enter Query")
+
+    # Text input for user queries
+    user_query = st.sidebar.text_input("Type your question or query")
+
+    # File uploader for medical report
+    uploaded_file = st.sidebar.file_uploader("Upload a medical report (optional)", type=["txt", "pdf", "csv"])
+
+    # Process the query if provided
+    if user_query:
+        st.write("### Query Response:")
+
+        # Retrieve relevant information from dataset
+        relevant_info = get_relevant_info(user_query)
+        st.write("#### Relevant Medical Information:")
+        for i, row in relevant_info.iterrows():
+            st.write(f"- {row['description']}")
+
+        # Generate a response from the Llama3-Med42-8B model
+        response = generate_response(user_query)
+        st.write("#### Model's Response:")
+        st.write(response)
+
+    # Process the uploaded file (if any)
+    if uploaded_file:
+        # Display analysis of the uploaded report file
+        st.write("### Uploaded Report Analysis:")
+        report_text = "Extracted report content here"  # Placeholder for file processing logic
+        st.write(report_text)
+
+if __name__ == "__main__":
+  main()