# Don't understand where the prompt goes with ConversationalRetrievalChain

**URL:** <https://community.deeplearning.ai/t/dont-understand-where-the-prompt-goes-with-conversationalretrievalchain/376776>\
**Category:** LangChain: Chat with Your Data\
**Created:** [July 7, 2023, 2:14am UTC](https://community.deeplearning.ai/t/dont-understand-where-the-prompt-goes-with-conversationalretrievalchain/376776 "2023-07-07T02:14:33Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![gms7](https://avatars.discourse-cdn.com/v4/letter/g/b5ac83/32.png) [@gms7](https://community.deeplearning.ai/u/gms7)\
**Post date:** [July 7, 2023, 2:14am UTC](https://community.deeplearning.ai/t/dont-understand-where-the-prompt-goes-with-conversationalretrievalchain/376776/1 "2023-07-07T02:14:33Z")

</div>

In section 06\_Chat, for the Conversation Chain we have:

```auto
from langchain.chains import ConversationalRetrievalChain
retriever=vectordb.as_retriever()
qa = ConversationalRetrievalChain.from_llm(
    llm,
    retriever=retriever,
    memory=memory
)

```

And as such have lost the prompt. What if we still want the prompt to help guide the solution. Does it somehow get stuffed into the Memory?

Also, “chat\_history” isn’t specified on the result request, should it be:

`result = qa({"question": question, "chat_history": chat_history})`

Great, efficient course BTW.