Update app.py

app.py

@@ -8,30 +8,41 @@ from langchain.prompts import PromptTemplate
 from langchain.llms import HuggingFaceHub
 import dotenv
 import yaml
-import zipfile
 
+# Load environment variables
 dotenv.load_dotenv()
 
+# Load YAML config
 def load_config():
     with open("yaml-editor-online.yaml", "r") as f:
-        config = yaml.safe_load(f)
-    return config
+        return yaml.safe_load(f)
 
-hf_token = os.getenv("HUGGING")
 config = load_config()
+hf_token = os.getenv("HUGGING")
 logging.basicConfig(level=logging.INFO)
 
+# Load embedding model
 embeddings_model = HuggingFaceEmbeddings(model_name=config["embedding_model"])
 
+# Load disease data into FAISS in-memory
+def create_vector_db():
+    try:
+        loader = CSVLoader(file_path="disease.csv", source_column="Disease Information")
+        data = loader.load()
+        vectordb = FAISS.from_documents(documents=data, embedding=embeddings_model)
+        return vectordb
+    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 os.path.exists(config["vector_db_path"]):
-            logging.error(f"FAISS index path does not exist: {config['vector_db_path']}")
+        if not vectordb:
             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]
 
@@ -41,9 +52,9 @@ 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)
@@ -65,9 +76,10 @@ 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>
@@ -87,9 +99,9 @@ def main():
             }
         </style>
     """, unsafe_allow_html=True)
-    
+
     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)
@@ -98,4 +110,4 @@ def main():
             st.warning("Please enter a query to get a response.")
 
 if __name__ == "__main__":
-    main()
+    main()