Option A is correct. Cortex Search provides low-latency, high-quality 'fuzzy' search and handles embedding, infrastructure maintenance, search quality parameter tuning, and ongoing index refreshes. Its primary use cases are as a RAG engine for LLM chatbots and as a backend for enterprise search. Option B is incorrect. Cortex Search Services incur costs based on the amount of indexed data (6.3 Credits per GB/mo of indexed data), not solely on the number of queries executed. Option C is incorrect. Cortex Search offers multilingual embedding models like 'snowflake-arctic-embed-l-v2.ff and 'voyage-multilingual-2 , supporting multilingual AI workflows. Option D is correct. Snowflake recommends splitting text into chunks of no more than 512 tokens for optimal search results, as smaller chunks can lead to more precise retrieval and higher-quality LLM responses in RAG scenarios, even with models that support longer context windows. Option E is correct. A virtual warehouse is required for Cortex Search Service to refresh the service, which includes running queries against base objects, orchestrating text embedding jobs, and building the search index.