The community member is asking for the best "Chat Modes" to use with a RAG query engine when they need to refine answers based on chat history and new user questions. The three options presented are:
condense_question - Rewrite the user message as a query for the index and return the response.
context - Retrieve nodes from the index using each user message and insert the text into the system prompt.
condense_plus_context - A combination of condense_question and context.
A community member recommends using condense_plus_context, stating that it "feels the most natural and accurate".
Hello, What is best Chat Modes recommended to use with RAG query engine, when I need to refine answer base on chat history and new user questions ?
-condense_question - Look at the chat history and re-write the user message to be a query for the index. Return the response after reading the response from the query engine. -context - Retrieve nodes from the index using every user message. The retrieved text is inserted into the system prompt, so that the chat engine can either respond naturally or use the context from the query engine. -condense_plus_context - A combination of condense_question and context. Look at the chat history and re-write the user message to be a retrieval query for the index. The retrieved text is inserted into the system prompt, so that the chat engine can either respond naturally or use the context from the query engine.
