Hello guys, I'll feed my index with documents from my chat logs and my FAQ data, is that possible to set a priority for them on the save OR on the retrieve, like, obviously the FAQ information should be used PRIOR the chat logs, because it will always be more precise.
If they're in the same index wouldn't the most relevant answer surface anyways? By default it will retrieve the snippet that most matches your question. I guess you could include in the metadata for each node that whether it's FAQ or chat logs. But maybe it could also make sense to have separate indices and use multiple query engines?
The FAQ/Chat logs was just a sample, I'll fetch data from multiple sources over our company, like internal chat logs, chat logs, faq, e-mail conversations, etc. But for internal reasons, even when the "question" is the same, like "What is the color of xxx equipment" the answer can be found on all those sources, but I want to use the response for the FAQ source if possible..