Option A is correct. Cortex Analyst can leverage Cortex Search Services to improve literal search by including a configuration block within a dimension's definition in the semantic model YAML. This block specifies the service name and an optional 'literal_column'. Option B is correct. Snowflake recommends splitting text in your search column into chunks of no more than 512 tokens for best search results with Cortex Search, even when using models with larger context windows like 'snowflake-arctic-embed-l-v2.0-8k' This practice typically leads to higher retrieval and downstream LLM response quality in RAG scenarios. Option C is incorrect. The 'VECTOR data type is allowed in hybrid tables but is explicitly not supported as a primary key, secondary index key, or clustering key in Snowflake. Option D is incorrect. For EMBED_TEXT functions, which are used to generate embeddings for Cortex Search, only 'input tokens' are counted towards the billable total, not output tokens. The Cortex Search service itself is billed per GBImonth of indexed data. Option E is incorrect. Snowflake Cortex functions, including Cortex Search, do not support dynamic tables.