Update main.py

main.py

@@ -1,8 +1,5 @@
 import os
-import shutil
 from flask import Flask, render_template, request, jsonify
-from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate, Settings
-from sentence_transformers import SentenceTransformer  # Fallback for embeddings
 from deep_translator import GoogleTranslator
 import google.generativeai as genai
 
@@ -15,83 +12,40 @@ if not GOOGLE_API_KEY:
 genai.configure(api_key=GOOGLE_API_KEY)
 gemini_model = genai.GenerativeModel('gemini-flash-1.0')
 
-# Custom Embedding Model (Fallback for HuggingFaceEmbedding)
-class CustomEmbedding:
-    def __init__(self, model_name):
-        self.model = SentenceTransformer(model_name)
-
-    def get_text_embedding(self, text):
-        return self.model.encode(text).tolist()
-
-# Configure Llama index settings with Custom Embedding
-Settings.embed_model = CustomEmbedding("sentence-transformers/paraphrase-multilingual-mpnet-base-v2")
-
-PERSIST_DIR = "db"
+# Directory for storing PDFs (optional if you want to load raw text data)
 PDF_DIRECTORY = 'data'
 
-# Ensure directories exist
-os.makedirs(PDF_DIRECTORY, exist_ok=True)
-os.makedirs(PERSIST_DIR, exist_ok=True)
+# Chat history
 chat_history = []
-current_chat_history = []
-
-def data_ingestion_from_directory():
-    # Clear previous data by removing the persist directory
-    if os.path.exists(PERSIST_DIR):
-        shutil.rmtree(PERSIST_DIR)  # Remove the persist directory and all its contents
 
-    # Recreate the persist directory after removal
-    os.makedirs(PERSIST_DIR, exist_ok=True)
+def load_data_from_directory():
+    """Load raw text data from the directory."""
+    data = ""
+    for filename in os.listdir(PDF_DIRECTORY):
+        file_path = os.path.join(PDF_DIRECTORY, filename)
+        if os.path.isfile(file_path):
+            with open(file_path, 'r', encoding='utf-8') as file:
+                data += file.read() + "\n"
+    return data
 
-    # Load new documents from the directory
-    new_documents = SimpleDirectoryReader(PDF_DIRECTORY).load_data()
-
-    # Create a new index with the new documents
-    index = VectorStoreIndex.from_documents(new_documents)
-
-    # Persist the new index
-    index.storage_context.persist(persist_dir=PERSIST_DIR)
+# Load hotel data (context) from the directory
+hotel_data = load_data_from_directory()
 
 def handle_query(query):
-    chat_text_qa_msgs = [
-        (
-            "user",
-            """
-            You are the Hotel voice chatbot and your name is hotel helper. Your goal is to provide accurate, professional, and helpful answers to user queries based on the hotel's data. Always ensure your responses are clear and concise. Give response within 10-15 words only. You need to give an answer in the same language used by the user.       
-            {context_str}
-            Question:
-            {query_str}
-            """
-        )
-    ]
-    text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
-
-    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
-    index = load_index_from_storage(storage_context)
-    context_str = ""
-    for past_query, response in reversed(current_chat_history):
-        if past_query.strip():
-            context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"
-
-    query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)
-    print(query)
-
-    # Use Gemini for generating the response
+    """Handle user queries and generate responses using Gemini."""
+    # Prepare the prompt with context and query
     prompt = f"""
-    Context: {context_str}
+    Context: {hotel_data}
     Question: {query}
+    Answer the question based on the context above. If the answer is not found, say "I'm sorry, I couldn't find an answer."
     """
+    # Generate response using Gemini
     gemini_response = gemini_model.generate_content(prompt)
-    response = gemini_response.text
-
-    current_chat_history.append((query, response))
+    response = gemini_response.text.strip()
     return response
 
 app = Flask(__name__)
 
-# Data ingestion
-data_ingestion_from_directory()
-
 # Generate Response
 def generate_response(query, language):
     try: