Update app.py

app.py

@@ -1,4 +1,3 @@
-# App
 # Import required libraries
 import os
 import pandas as pd
@@ -7,51 +6,47 @@ from transformers import pipeline
 from sentence_transformers import SentenceTransformer, util
 import requests
 import json
-from pyngrok import ngrok
 
-# Set up Hugging Face API token
+# Configure Hugging Face API token securely
+# Set this in Hugging Face Space Secrets instead of directly in code
+# os.environ["HUGGINGFACEHUB_API_TOKEN"] = "your_hugging_face_api_token"  # Avoid hardcoding
+api_key = os.getenv("HF_API_KEY")
 
-api_key = os.getenv("HF_API_KEY")        # Replace with your Hugging Face API token
-
-
-# Load the CSV dataset
-data = pd.read_csv('genetic-Final.csv')
+# Load the CSV dataset (place the CSV in the same directory as app.py in Hugging Face Spaces)
+# Ensure the dataset is uploaded in your Space or provide a fallback mechanism
 
+try:
+    data = pd.read_csv('genetic-Final.csv')  # Make sure the dataset filename is correct
+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')
 
-# 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
+# Preprocess the dataset for embeddings and drop unnecessary columns
+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('')
+    )
+
+# Function to generate embeddings safely 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
+    if description:
+        return retriever_model.encode(description).tolist()
     else:
         return []
 
-# Generate embeddings for the combined description
-data['embeddings'] = data['combined_description'].apply(generate_embedding)
+# Generate embeddings for the combined description (do this only if not already embedded)
+if 'embeddings' not in data.columns:
+    data['embeddings'] = data['combined_description'].apply(generate_embedding)
 
-# Function to retrieve relevant information from CSV dataset based on user query
+# 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']]
@@ -61,11 +56,20 @@ def get_relevant_info(query, top_k=3):
 # 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']}"}
+    headers = {"Authorization": f"Bearer {os.getenv('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"]
+    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:
+            st.error("Unexpected response structure from API.")
+            return "Sorry, I couldn't generate a response. Please try again."
+    except Exception as e:
+        st.error(f"Error during API request: {e}")
+        return "Sorry, there was an error processing your request. Please try again."
 
 # Streamlit UI for the Chatbot
 def main():
@@ -86,7 +90,7 @@ def main():
         relevant_info = get_relevant_info(user_query)
         st.write("#### Relevant Medical Information:")
         for i, row in relevant_info.iterrows():
-            st.write(f"- {row['description']}")
+            st.write(f"- {row['combined_description']}")  # Adjust to show meaningful info
 
         # Generate a response from the Llama3-Med42-8B model
         response = generate_response(user_query)
@@ -95,10 +99,10 @@ def main():
 
     # Process the uploaded file (if any)
     if uploaded_file:
-        # Display analysis of the uploaded report file
+        # Display analysis of the uploaded report file (process based on file type)
         st.write("### Uploaded Report Analysis:")
         report_text = "Extracted report content here"  # Placeholder for file processing logic
         st.write(report_text)
 
 if __name__ == "__main__":
-  main()
+    main()