Maintain context in case of RAG (semantic search) when user query referes back to the previous conversation - for example: "How much does the second option cost?"

[SomebodySysop]

There are two ways to do this. Number one is, as @Macha suggests, sending the chat history with every request. The second is one I’ve used for some time now, and that is generating a Standalone question to send as your prompt: How to construct the prompt for a standalone question?

And, of course, using both methods together.

@banaiviktor

But in real life conversations you can face questions when they just refer back to an object in a previous conversation. For example : “How much does it cost?”, or "Can you recommend a similar solution?, "Is the third option the best one?"etc.

This is the classic use case for sending the Chat History with your requests.

@banaiviktor

The query first should be reformulated in order to get the relevant parts in the source file.

That would be the Standalone question. That is, a question which contains the context of the conversation but can stand on it’s own. Combine that with the actual Chat History, and that should solve your problem.