Update app.py

app.py

@@ -1,58 +1,54 @@
 import streamlit as st
 import logging
 import os
-import pandas as pd
 from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import CSVLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.prompts import PromptTemplate
 from langchain.llms import HuggingFaceHub
 import dotenv
 import yaml
+import os
+import zipfile
+
+zip_file = "faiss_index.zip"
 
-# Load environment variables
+with zipfile.ZipFile(zip_file, 'r') as zip_ref:
+    zip_ref.extractall(".")  # Extract to the current directory
+
+print("Unzipping completed successfully.")
 dotenv.load_dotenv()
 
-# Load YAML config
 def load_config():
     with open("yaml-editor-online.yaml", "r") as f:
-        return yaml.safe_load(f)
+        config = yaml.safe_load(f)
+    return config
 
-config = load_config()
 hf_token = os.getenv("HUGGING")
+config = load_config()
 logging.basicConfig(level=logging.INFO)
 
-# Load embedding model
 embeddings_model = HuggingFaceEmbeddings(model_name=config["embedding_model"])
 
-# Load disease data manually using pandas
 def create_vector_db():
     try:
-        if not os.path.exists("disease.csv"):
-            logging.error("Error: disease.csv file not found.")
-            return None
-
-        df = pd.read_csv("disease.csv")
-
-        # Check if the expected column exists
-        if "Disease Information" not in df.columns:
-            logging.error("Error: 'Disease Information' column not found in CSV.")
-            return None
-
-        data = [{"page_content": row["Disease Information"]} for _, row in df.iterrows()]
+        loader = CSVLoader(file_path="disease.csv", source_column="Disease Information")
+        data = loader.load()
         vectordb = FAISS.from_documents(documents=data, embedding=embeddings_model)
-        return vectordb
+        vectordb.save_local(config["vector_db_path"])
+        logging.info("Vector database successfully created and saved.")
     except Exception as e:
         logging.error("Error creating vector database:", exc_info=e)
-        return None
 
-vectordb = create_vector_db()
-
-# Function to get responses
 def get_qa_chain(query):
     try:
-        if not vectordb:
+        if not os.path.exists(config["vector_db_path"]):
+            logging.error(f"FAISS index path does not exist: {config['vector_db_path']}")
             return "Error: No data found."
 
+        vectordb = FAISS.load_local(
+            config["vector_db_path"], embeddings_model, allow_dangerous_deserialization=True
+        )
         retriever = vectordb.as_retriever(score_threshold=config["score_threshold"])
         relevant_docs = retriever.get_relevant_documents(query)[:3]
 
@@ -62,9 +58,9 @@ def get_qa_chain(query):
         summarized_context = " ".join(doc.page_content for doc in relevant_docs)
         prompt_template = """
         Given the following health-related context and a question, generate a structured answer:
-
+        
         QUESTION: {query}
-
+        
         Ensure the response is easy to understand and medically accurate.
         """
         prompt = PromptTemplate(input_variables=["query"], template=prompt_template).format(query=query)
@@ -86,38 +82,50 @@ def get_qa_chain(query):
         logging.error("Error getting response:", exc_info=e)
         return "Sorry, there was an error processing your request."
 
-# Streamlit UI
 def main():
     st.set_page_config(page_title="Health Disease Chatbot", page_icon="🩺", layout="centered")
-
-    st.markdown("""
-        <h1 style='text-align: center; color: #2E7D32;'>🩺 Health Disease Chatbot</h1>
-        <p style='text-align: center; font-size: 18px;'>Enter a question related to health conditions, symptoms, or treatments.</p>
+    
+    st.markdown(
+        """
         <style>
-            .stTextInput > div > div > input {
-                border-radius: 10px;
-                padding: 10px;
-                border: 1px solid #2E7D32;
-            }
-            .response-box {
-                background-color: #ffffff;
-                padding: 15px;
-                border-radius: 8px;
-                box-shadow: 2px 2px 10px rgba(0,0,0,0.1);
-                margin-top: 15px;
-                font-size: 16px;
-            }
+        .stApp {
+            background-color: #f0f2f6;
+            color: #333;
+            font-family: 'Arial', sans-serif;
+        }
+        .title {
+            color: #2E7D32;
+            text-align: center;
+        }
+        .query-input {
+            border-radius: 10px;
+            padding: 10px;
+        }
+        .response-box {
+            background-color: #ffffff;
+            padding: 15px;
+            border-radius: 8px;
+            box-shadow: 2px 2px 10px rgba(0,0,0,0.1);
+        }
         </style>
-    """, unsafe_allow_html=True)
-
+        """,
+        unsafe_allow_html=True
+    )
+    
+    st.markdown("<h1 class='title'>🩺 Health Disease Chatbot</h1>", unsafe_allow_html=True)
+    st.write("Enter a question related to health conditions, symptoms, or treatments.")
+    
     query = st.text_input("Your health-related question:", key="query", help="Ask about diseases, symptoms, or treatments.")
-
+    
     if st.button("Get Information"):
         if query:
             response = get_qa_chain(query)
-            st.markdown(f"""<div class='response-box'><b>Response:</b><br>{response}</div>""", unsafe_allow_html=True)
+            st.markdown(f"<div class='response-box'><b>Response:</b><br>{response}</div>", unsafe_allow_html=True)
         else:
             st.warning("Please enter a query to get a response.")
 
 if __name__ == "__main__":
+    if not os.path.exists(config["vector_db_path"]):
+        logging.info(f"Vector database not found at {config['vector_db_path']}, creating it now.")
+        create_vector_db()
     main()