Update main.py

main.py

@@ -1,12 +1,13 @@
-from flask import Flask, render_template, request, jsonify
-import os
-import shutil
-from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate, Settings
-from llama_index.llms.huggingface import HuggingFaceInferenceAPI
-from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from huggingface_hub import InferenceClient
+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 llama_index.llms.huggingface import HuggingFaceInferenceAPI  
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding  
+from huggingface_hub import InferenceClient  
 from transformers import AutoTokenizer, AutoModel
 
+
 # Ensure HF_TOKEN is set  
 HF_TOKEN = os.getenv("HF_TOKEN")  
 if not HF_TOKEN:  
@@ -27,13 +28,15 @@ Settings.llm = HuggingFaceInferenceAPI(
     max_new_tokens=512,  
     generate_kwargs={"temperature": 0.1},  
 )  
-
-# Configure embedding model (XLM-RoBERTa model for multilingual support)
+# Settings.embed_model = HuggingFaceEmbedding(  
+#     model_name="BAAI/bge-small-en-v1.5"  
+# )  
+# Replace the embedding model with XLM-R
 Settings.embed_model = HuggingFaceEmbedding(
-    model_name="xlm-roberta-base"  # Multilingual support
+    model_name="xlm-roberta-base"  # XLM-RoBERTa model for multilingual support
 )
 
-# Configure tokenizer and model for multilingual responses
+# Configure tokenizer and model if required
 tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-base")
 model = AutoModel.from_pretrained("xlm-roberta-base")
 
@@ -46,80 +49,56 @@ os.makedirs(PERSIST_DIR, exist_ok=True)
 chat_history = []  
 current_chat_history = []  
 
-# Data ingestion function
 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 its contents  
+        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)  
+    
+    # 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)  
 
-def handle_query(query, user_language):  
+def handle_query(query):  
     context_str = ""  
-
+    
     # Build context from current chat history  
     for past_query, response in reversed(current_chat_history):  
         if past_query.strip():  
             context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"  
     
-    # Define the chat response template based on selected language
-    if user_language == 'te':  # Telugu
-        response_template = """
-            మీరు తాజ్ హోటల్ చాట్‌బాట్, తాజ్ హోటల్ సహాయకుడిగా పనిచేస్తున్నారు.
-            **మీరు చేసే పాత్ర:**
-            - వినియోగదారుడి ప్రాముఖ్యమైన భాష (ఆంగ్లం, తెలుగు, హిందీ) లో సమాధానాలు ఇవ్వండి.
-            - హోటల్ యొక్క సేవలు, సదుపాయాలు మరియు విధానాలపై సమాచారం ఇవ్వండి.
-            **సూచన:**
-            - **ప్రసంగం:**  
-              {context_str}
-            - **వినియోగదారు ప్రశ్న:**  
-              {query_str}
-            **సమాధానం:** [మీ సమాధానం తెలుగులో ఇక్కడ]
-        """
-    elif user_language == 'hi':  # Hindi
-        response_template = """
-            आप ताज होटल के चैटबोट, ताज होटल हेल्पर हैं।
-            **आपकी भूमिका:**
-            - उपयोगकर्ता द्वारा चुनी गई भाषा (अंग्रेजी, हिंदी, या तेलुगु) में उत्तर दें।
-            - होटल की सेवाओं, सुविधाओं और नीतियों के बारे में जानकारी प्रदान करें।
-            **निर्देश:**
-            - **संदर्भ:**  
-              {context_str}
-            - **उपयोगकर्ता का प्रश्न:**  
-              {query_str}
-            **उत्तर:** [आपका उत्तर हिंदी में यहाँ]
-        """
-    else:  # Default to English
-        response_template = """
-            You are the Taj Hotel chatbot, Taj Hotel Helper.
-            **Your Role:**
-            - Respond accurately and concisely in the user's preferred language (English, Telugu, or Hindi).
-            - Provide information about the hotel’s services, amenities, and policies.
-            **Instructions:**
-            - **Context:**  
-              {context_str}
-            - **User's Question:**  
-              {query_str}
-            **Response:** [Your concise response here]
-        """
-
-    # Create a list of chat messages with the user query and response template
     chat_text_qa_msgs = [
         (
             "user",
-            response_template.format(context_str=context_str, query_str=query)
+            """
+            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}
+            """
         )
     ]
 
-    # Use the defined chat template
-    text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)  
 
+    
+    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 = ""  
+    
+    # # Build context from current chat history  
+    # 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 the index and retrieve the answer
     query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)  
     print(f"Querying: {query}")  
     answer = query_engine.query(query)  
@@ -136,17 +115,16 @@ def handle_query(query, user_language):
     current_chat_history.append((query, response))  
     return response
 
-
 app = Flask(__name__)  
 
 # Data ingestion  
 data_ingestion_from_directory()  
 
 # Generate Response  
-def generate_response(query, language):  
+def generate_response(query):  
     try:  
         # Call the handle_query function to get the response  
-        bot_response = handle_query(query, language)  
+        bot_response = handle_query(query)  
         return bot_response  
     except Exception as e:  
         return f"Error fetching the response: {str(e)}"  
@@ -161,17 +139,13 @@ def index():
 def chat():  
     try:  
         user_message = request.json.get("message")  
-        selected_language = request.json.get("language")  # Get selected language from the request
         if not user_message:  
             return jsonify({"response": "Please say something!"})  
 
-        if selected_language not in ['english', 'telugu', 'hindi']:  
-            return jsonify({"response": "Invalid language selected."})  
-
-        bot_response = generate_response(user_message, selected_language)  
+        bot_response = generate_response(user_message)  
         return jsonify({"response": bot_response})  
     except Exception as e:  
         return jsonify({"response": f"An error occurred: {str(e)}"})  
 
 if __name__ == '__main__':  
-    app.run(debug=True)
+    app.run(debug=True)