Arthur
Arthur
Any update on this?
Hi @njalan I implemented a user-level cache using the existing MemoryCache class to store the latest N Q/A pairs per user. This cache is then appended to the prompt before...
+1. Please allow us to modify the parameters for default middlewares like SummarizationMiddleware.
We ran into this exact issue in production. Since there's no way to customize SummarizationMiddleware parameters, we ended up building our own middleware with the following features: - Configurable thresholds...