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")
 
@@ -46,73 +49,77 @@ 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)  
 
-# Function to handle the query and provide a response
-def handle_query(query, selected_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 response template based on selected language
-    if selected_language == 'telugu':
-        language_prompt = "మీరు తాజ్ హోటల్ చాట్‌బాట్, తాజ్ హోటల్ సహాయకుడు."
-    elif selected_language == 'hindi':
-        language_prompt = "आप ताज होटल चैटबोट हैं, ताज होटल सहायक।"
-    else:
-        language_prompt = "You are the Taj Hotel chatbot, Taj Hotel Helper."
     
     chat_text_qa_msgs = [
         (
             "user",
-            f"""
-            {language_prompt}
+            """You are the Taj Hotel chatbot, Taj Hotel Helper.
     
-            **Your Role:**
+            *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:**  
+            *Instructions:*
+            - *Context:*  
               {context_str}
-            - **User's Question:**  
-              {query}
+            - *User's Question:*  
+              {query_str}
             
-            **Response Guidelines:**
-            1. **Language Adaptation:** Respond in the language of the question (English, Telugu, or Hindi).
-            2. **Tone:** Maintain politeness, professionalism, and the luxury branding of the Taj Hotel.
-            3. **Clarity:** Limit responses to 10-15 words for direct and clear communication.
-            4. **Knowledge Boundaries:** If unsure of an answer, respond with:
-               _"I’m not sure. Please contact our staff for accurate information."_
-            5. **Actionable Help:** Offer suggestions or alternative steps to guide the user where applicable.
+            *Response Guidelines:*
+            1. *Language Adaptation:* Respond in the language of the question (English, Telugu, or Hindi).
+            2. *Tone:* Maintain politeness, professionalism, and the luxury branding of the Taj Hotel.
+            3. *Clarity:* Limit responses to 10-15 words for direct and clear communication.
+            4. *Knowledge Boundaries:* If unsure of an answer, respond with:
+               "I’m not sure. Please contact our staff for accurate information."
+            5. *Actionable Help:* Offer suggestions or alternative steps to guide the user where applicable.
     
-            **Response:** [Your concise response here]
-            """
+            *Response:* [Your concise response here]
+            """.format(context_str=context_str, query_str=query)
         )
     ]
 
-    text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
+
+    
+    text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)  
     
-    # Load the index for querying
     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_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)  
     print(f"Querying: {query}")  
     answer = query_engine.query(query)  
 
-    # Extracting the response
+    # Extracting the response  
     if hasattr(answer, 'response'):  
         response = answer.response  
     elif isinstance(answer, dict) and 'response' in answer:  
@@ -124,16 +131,16 @@ def handle_query(query, selected_language):
     current_chat_history.append((query, response))  
     return response
 
-app = Flask(__name__)  
+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)}"  
@@ -148,17 +155,13 @@ 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)
+if _name_ == '_main_':  
+    app.run(debug=True)