...
We currently support all the LLMs from OpenAI, but only if they are deployed through Azure. We don't support proxying LLMs directly from OpenAI.
Does CogCache work well with a conversation use case?
Currently CogCache supports only single queries and is unable to provide a good answer based on conversation history. This feature is currently under development and will be available soon.
Does CogCache work well with a RAG use case?
Currently CogCache supports only simple queries and while it might still work with RAG queries, CogCache is not optimised for that use case. This feature is currently under development and will be available soon.