This is the code shown below for getting response from RAG LLM.

def get_res(prompt, text1, text2, int1, int2):
   if len(text1)>1:
       prompt = prompt + "n text1: " + text1
   if len(text2) > 1:
       prompt = prompt + "n text2: " + text2
   docs = retriever.get_relevant_documents(prompt)


   qa_chain = RetrievalQA.from_chain_type(llm=llm,chain_type = "stuff",retriever = 
  retriever,return_source_documents = True)

   llm_response = qa_chain(prompt)

   return{'response':llm_response['result'],'int1':int1,'int2':int2}

I want to capture the following information from this process – prompt, response, and context-data for every call made to the retrieval end-point.

Please share an approach (with an example) on how I can achieve to pull out these data values.