Update model_pipelineV2.py

model_pipelineV2.py

@@ -55,13 +55,20 @@ class ModelPipeLine:
         return document_separator.join(doc_strings)
        
     def create_final_chain(self):
-
         answer_prompt, condense_question_prompt = self.get_prompts()
-        # This adds a "memory" key to the input object
+        
+        # Debugging outputs
+        print("Condense Question Prompt:", condense_question_prompt)
+        print("LLM:", self.llm)
+    
         loaded_memory = RunnablePassthrough.assign(
             chat_history=RunnableLambda(self.memory.load_memory_variables) | itemgetter("history"),
         )
-        # Now we calculate the standalone question
+    
+        # Check if loaded_memory is valid
+        if loaded_memory is None:
+            raise ValueError("Loaded memory is None")
+    
         standalone_question = {
             "standalone_question": {
                 "question": lambda x: x["question"],
@@ -70,25 +77,30 @@ class ModelPipeLine:
             | condense_question_prompt
             | self.llm,
         }
-        # Now we retrieve the documents
+    
+        # Ensure standalone_question is valid
+        if standalone_question is None:
+            raise ValueError("Standalone question is None")
+    
         retrieved_documents = {
             "docs": itemgetter("standalone_question") | self.retriever,
             "question": lambda x: x["standalone_question"],
         }
-        # Now we construct the inputs for the final prompt
+    
         final_inputs = {
             "context": lambda x: self._combine_documents(x["docs"]),
             "question": itemgetter("question"),
         }
-        # And finally, we do the part that returns the answers
+    
         answer = {
             "answer": final_inputs | answer_prompt | self.llm,
             "docs": itemgetter("docs"),
         }
-        # And now we put it all together!
+    
         final_chain = loaded_memory | standalone_question | retrieved_documents | answer
-
+    
         return final_chain
+
     
 
     def call_conversational_rag(self,question, chain):