Is it possible to customize VAPI's RAG implementation?
Is it possible to customize VAPI's RAG implementation without using make.com, to avoid high latency? Specifically, can we integrate our own vector database for semantic and keyword search, use Unstructured for document processing, and implement reranking with Cohere, while maintaining low latency?
