Update kadiApy_ragchain.py

kadiApy_ragchain.py

@@ -2,23 +2,21 @@ class KadiApyRagchain:
     
     def __init__(self, llm, vector_store):
         """
-        Initialize the RAGChain with an LLM instance, a vector store, and a conversation history.
+        Initialize the RAGChain with an LLM instance, a vector store
         """
         self.llm = llm
         self.vector_store = vector_store
-        self.conversation = []  
 
 
     def process_query(self, query, chat_history):
         """
         Process a user query, handle history, retrieve contexts, and generate a response.
         """
-        # Add the user query to the conversation history
-        self.add_to_conversation(user_query=query)
+
         
         # Rewrite query
         rewritten_query = self.rewrite_query(query)
-        print("RRRRRRRRRREEEEEEEEEEWRITEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEEE: ",rewritten_query)
+        print("Rewritten Query: ",rewritten_query)
         # Predict library usage
         print("Start prediction:")
         code_library_usage_prediction = self.predict_library_usage(query)
@@ -26,10 +24,10 @@ class KadiApyRagchain:
         # Retrieve contexts
         print("Start retrieving:")
         #doc_contexts = self.retrieve_contexts(query, k=2, filter={"dataset_category": "kadi_apy_docs"})
-        #code_contexts = self.retrieve_contexts(rewritten_query, k=3, filter={"usage": code_library_usage_prediction})
-        code_contexts = self.retrieve_contexts(query, k=2)
+        code_contexts = self.retrieve_contexts(rewritten_query, k=3, filter={"usage": code_library_usage_prediction})
+        #code_contexts = self.retrieve_contexts(query, k=2)
 
-        query_formulated_question= self.formulate_question(code_contexts)
+        #query_formulated_question= self.formulate_question(code_contexts)
         print("question:", query_formulated_question)
         doc_contexts = self.retrieve_contexts(query_formulated_question, k=2, filter={"dataset_category": "kadi_apy_docs"})
         
@@ -50,26 +48,9 @@ class KadiApyRagchain:
         print("Start generatin repsonsse:")
         response = self.generate_response(query, chat_history, formatted_doc_contexts, formatted_code_contexts)
         #response = self.generate_response(query, chat_history, formatted_contexts)
-        
-        # Add the response to the existing query in the conversation history
-        #self.add_to_conversation(llm_response=response)
-        
         return response
         
-    #not supported yet, need session handling in app.py
-    def add_to_conversation(self, user_query=None, llm_response=None):
-        """
-        Add either the user's query, the LLM's response, or both to the conversation history.
-        """
-        if user_query and llm_response:
-            # Add a full query-response pair
-            self.conversation.append({"query": user_query, "response": llm_response})
-        elif user_query:
-            # Add a query with no response yet
-            self.conversation.append({"query": user_query, "response": None})
-        elif llm_response and self.conversation:
-            # Add a response to the most recent query
-            self.conversation[-1]["response"] = llm_response
+
 
     def get_history(self):
         """