The Grounded Generation (GG) stack is becoming increasingly popular for building GenAI applications, with use-cases like question-answering and chatbots relying on a strong retrieval engine that combines the strength of pre-trained large language models (LLMs) with contextual text. A reference architecture for GG has been proposed, highlighting two distinct flows: data-ingestion and query-response. The data-ingestion flow involves processing and preparing data for querying, while the query-response flow involves encoding user queries, retrieving relevant chunks of text, constructing a comprehensive prompt, and generating responses using generative LLMs. However, building a GG application from scratch can be complex and requires specialized expertise in retrieval engines, embedding models, and vector databases. GenAI platforms like Vectara provide a powerful yet easy-to-use set of APIs that allow developers to focus on building their application, instead of having to specialize in the increasingly complex and constantly evolving set of skills required to build such applications on their own. These platforms encapsulate a lot of the functionality of the GG stack into a single platform, handling tasks like data processing, vector and text storage, query flow, response generation, security, and privacy.