I have been building a RAG chat application using Azure Open AI model (gpt-35-turbo) and azure embeddings (ada-embedding-002). Here I am providing the prompt templates and the RAG chain.

from langchain.chains import create_history_aware_retriever
from langchain_core.prompts import MessagesPlaceholder

contextualize_q_system_prompt = (
    "Given a chat history and the latest user question "
    "which might reference context in the chat history, "
    "formulate a standalone question which can be understood "
    "without the chat history. Do NOT answer the question, "
    "just reformulate it if needed and otherwise return it as is."
)

contextualize_q_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", contextualize_q_system_prompt),
        MessagesPlaceholder("chat_history"),
        ("human", "{input}"),
    ]
)

history_aware_retriever = create_history_aware_retriever(
    llm, retriever, contextualize_q_prompt
)

from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain

system_prompt = (
    "You are an assistant for question-answering tasks. "
    "Use the following pieces of retrieved context to answer "
    "the question. If you don't know the answer, say that you "
    "don't know. Don't use any other data sources except the provided pdf."
    "Use six sentences maximum and keep the "
    "answer concise."
    "nn"
    "{context}"
)

qa_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system_prompt),
        MessagesPlaceholder("chat_history"),
        ("human", "{input}"),
    ]
)

question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)

rag_chain = create_retrieval_chain(history_aware_retriever, question_answer_chain)

from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.chat_history import BaseChatMessageHistory
from langchain_core.runnables.history import RunnableWithMessageHistory

store = {}


def get_session_history(session_id: str) -> BaseChatMessageHistory:
    if session_id not in store:
        store[session_id] = ChatMessageHistory()
    return store[session_id]

conversational_rag_chain = RunnableWithMessageHistory(
    rag_chain,
    get_session_history,
    input_messages_key="input",
    history_messages_key="chat_history",
    output_messages_key="answer",
)

conversational_rag_chain.invoke(
    {"input": "Hi, can you tell me about apple ?"},
    config={
        "configurable": {"session_id": "abc123"}
    },  # constructs a key "abc123" in `store`.
)["answer"]

When I use openai models and embeddings it’s working perfectly and doesn’t provide information outside the pdf, but when I use azure open ai model and azure embeddings, it’s providing answers from it’s knowledge base also. What is the reason ?