Update main.py

main.py

@@ -252,20 +252,16 @@ from flask import Flask, render_template, request, jsonify
 from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate, Settings
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from deep_translator import GoogleTranslator
-from vertexai.preview.generative_models import GenerativeModel
+import google.generativeai as genai
 
-# Ensure HF_TOKEN is set (optional if you're not using HuggingFace embeddings anymore)
-HF_TOKEN = os.getenv("HF_TOKEN")
-if not HF_TOKEN:
-    raise ValueError("HF_TOKEN environment variable not set.")
-
-# Configure Gemini API
+# Ensure GOOGLE_API_KEY is set
 GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
 if not GOOGLE_API_KEY:
     raise ValueError("GOOGLE_API_KEY environment variable not set.")
 
-# Initialize Gemini Flash 1.0
-gemini_flash_model = GenerativeModel("gemini-flash-1.0")
+# Configure Gemini model
+genai.configure(api_key=GOOGLE_API_KEY)
+gemini_model = genai.GenerativeModel('gemini-flash-1.0')
 
 # Configure Llama index settings
 Settings.embed_model = HuggingFaceEmbedding(
@@ -303,14 +299,13 @@ def handle_query(query):
         (
             "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.
+            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)
@@ -320,18 +315,17 @@ def handle_query(query):
         if past_query.strip():
             context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"
 
-    # Use Gemini Flash 1.0 to generate a response
+    query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)
+    print(query)
+
+    # Use Gemini for generating the response
     prompt = f"""
     Context: {context_str}
     Question: {query}
-    Answer:
     """
-    gemini_response = gemini_flash_model.generate(prompt=prompt, max_output_tokens=100, temperature=0.1)
-
-    # Extract the response
-    response = gemini_response.candidates[0].content.parts[0].text
+    gemini_response = gemini_model.generate_content(prompt)
+    response = gemini_response.text
 
-    # Append to chat history
     current_chat_history.append((query, response))
     return response