not starting

chatbot.py

@@ -310,12 +310,6 @@ Response:"""
         )
         
         # Create the conversation chain
-        # LLMChain combines the language model, prompt template, and memory
-        # This creates a conversational agent that can:
-        # - Generate responses using the LLM
-        # - Use the prompt template for structured input
-        # - Maintain conversation history in memory
-        # - verbose=False: Disables detailed logging of chain operations
         self.conversation = LLMChain(
             llm=self.llm,
             prompt=self.prompt_template,
@@ -324,16 +318,12 @@ Response:"""
         )
         
         # Setup embeddings for vector search
-        # HuggingFaceEmbeddings converts text to numerical vectors for similarity search
-        # all-MiniLM-L6-v2 is a lightweight but effective sentence embedding model
-        # These embeddings enable semantic search of past conversations and guidelines
         self.embeddings = HuggingFaceEmbeddings(
             model_name="sentence-transformers/all-MiniLM-L6-v2"
         )
         
         # Setup vector database for retrieving relevant past conversations
-        # The vector database stores embeddings of therapy guidelines and past conversations
-        # This enables semantic search to find relevant context for each response
+        
         if therapy_guidelines_path and os.path.exists(therapy_guidelines_path):
             self.setup_vector_db(therapy_guidelines_path)
         else:
@@ -446,9 +436,6 @@ Response:"""
             )
             
             # Create LangChain wrapper
-            # HuggingFacePipeline wraps the HuggingFace pipeline for use with LangChain
-            # This enables the pipeline to work seamlessly with LangChain components
-            # like chains, memory, and prompts
             llm = HuggingFacePipeline(pipeline=text_generator)
             
             return model, tokenizer, llm