Free Practice Questions for Snowflake GES-C02 Certification

● Snowflake Cortex ○ Cortex Models and Functions ○ Cortex Fine-tuning (Public Preview) ○ Cortex Search ■ RAG use cases ■ Unstructured data use cases ○ Cortex Analyst ■ Text-to-SQL use cases ○ Cortex Agents ● Snowflake Cortex Code ● Cortex Code in Snowsight UI ○ Cortex Code Command Line (CLI) ● Snowflake Copilot Inline (Public Preview) ○ Cortex Models and Functions ○ Cortex Fine-tuning (Public Preview) ○ Cortex Search ■ RAG use cases ● Snowflake Intelligence ● Different interfaces ○ AI Studio ○ SQL ○ REST API ● Bringing your own models into Snowflake ○ Snowflake Model Registry (custom model) ○ Snowpark Container Services

● Prompting ● Cortex AI functions ○ Vector-embedding ○ Context Windows ● Cortex Search ○ Multi-index queries ○ Access control requirements ○ Different ways to use Cortex Search ● Cortex Analyst ○ Semantic Views ○ Semantic Views Autopilot ○ YAML Specification for Semantic Views ○ Verified Query ○ Custom Instructions ● Cortex Agents ● Snowflake Intelligence ● Cross-region inference ○ CORTEX_ENABLED_CROSS_REGION parameter ○ Considerations (e.g., latency, availability) ● REST APIs ● Model Context Protocol (MCP) ● Snowflake Cortex Code ○ Cortex Code CLI commands ● Cortex Knowledge Extensions (CKE)

● Snowflake Cortex AI functions ○ General ■ AI_COMPLETE ■ COMPLETE Structured Outputs ○ Task-specific functions ■ AI_CLASSIFY ■ AI_EXTRACT ■ AI_PARSE_DOCUMENT ■ AI_SENTIMENT ■ SUMMARIZE ■ AI_SUMMARIZE_AGG ■ AI_TRANSLATE ■ AI_EMBED ■ AI_FILTER ■ AI_AGG ■ AI_SIMILARITY ■ AI_TRANSCRIBE ■ AI_REDACT ○ Vector functions ■ VECTOR_INNER_PRODUCT ■ VECTOR_L1_DISTANCE ■ VECTOR_L2_DISTANCE ■ VECTOR_COSINE_SIMILARITY ■ VECTOR_TRUNCATE ■ VECTOR_NORMALIZE ■ VECTOR_SUM ■ VECTOR_MIN ■ VECTOR_MAX ■ VECTOR_AVG ○ Helper functions ■ AI_COUNT_TOKENS ■ TRY_COMPLETE ■ SPLIT_TEXT_RECURSIVE_CHARACTER ■ SPLIT_TEXT_MARKDOWN_HEADER ■ TO_FILE ■ PROMPT

● Use fully-managed LLMs, RAG, and text-to-SQL services ○ Unstructured data ■ Functions ● AI_PARSE_DOCUMENT ● AI_EXTRACT ● AI_SIMILARITY ● AI_COMPLETE ■ Cortex Search ● Recursive split text markdown ● Chunk sizing ● Embedding models ● Semantic reranking ■ Multi-modal Analytics ● Audio and Image Processing ○ Structured data ■ Functions ● AI_COMPLETE ■ Cortex Analyst ● Cortex Analyst Verified Query Repository (VQR) ● Integration with Cortex Search ● Suggested Questions ● CUSTOM_INSTRUCTIONS ● Performance considerations ○ Choosing a model ○ Latency (e.g., model size) ○ Accuracy (e.g., fine-tuning, reducing hallucinations) ○ Model capability ○ Provisioned Throughput

● Set up the Snowflake environment ○ Required privileges ● Invoke Cortex functions within the application code (e.g., Streamlit in Snowflake) ○ Chat conversations ■ Multi-turn architecture ■ Update parameters (i.e., messages array for conversation history) ● Snowflake Intelligence

● Snowflake Cortex ● SQL interface ● Data extraction ● Data enrichment ● Data augmentation ● Data transformations

● Using Snowpark Container Services ○ Environment setup ○ Docker images ○ Specification files ○ Create compute pool ○ Create image repository ● Using Snowflake Model Registry ○ Logging the model ○ Calling the model

● Limits on which models can be used ○ Restrict access to specific models ● Application roles ■ Control model access ● Role-Based Access Control (RBAC) ● Account-level allowlist parameter ● Data safety and security considerations ○ Cross region inference ○ Guardrails ○ Sensitive data management (e.g., AI_REDACT) ○ Methods to reduce model hallucinations and bias ● REST API authentication methods

● Individual privileges ○ Specific requirements for Analyst, Search, Agents, and Snowflake Intelligence ● Roles ○ CORTEX_USER ○ CORTEX_ANALYST_USER ○ CORTEX_AGENT_USER ○ CORTEX_EMBED_USER

● Cortex Agents ○ Limit token usage ● Cortex Search ○ Different types of costs (e.g., virtual warehouse, EMBED_TEXT, serving, indexing) ● Cortex Analyst ● Cortex AI functions ○ Minimize tokens ○ Token cost implications ● Tracking costs of Snowpark Container Services ○ Compute pools ● Tracking model usage and consumption ○ Usage quotas ○ CORTEX_ANALYST_USAGE_HISTORY ○ CORTEX_AISQL_USAGE_HISTORY ○ CORTEX_SEARCH_DAILY_USAGE_HISTORY ○ CORTEX_REST_API_USAGE_HISTORY ○ CORTEX_PROVISIONED_THROUGHPUT_USAGE_HISTORY ○ METERING_DAILY_HISTORY ○ METERING_HISTORY ● Object tagging to monitor AI services costs

● Snowflake AI observability features ○ Evaluation metrics ○ Comparisons ○ Tracing ○ Logging ○ Event tables ● Implementation methods ○ Trulens SDK

● AI_PARSE_DOCUMENT ○ OCR mode ○ LAYOUT mode ○ page_split ○ page_limit ● AI_EXTRACT ○ Response format ○ How to prompt/Prompt engineering

● Upload documents ● Requirements (e.g., formats, size limits)

● Orchestration of Snowflake tooling ○ Streams ○ Tasks

● Extracting query errors ○ GET_PRESIGNED_URL function ● Requirements and privileges ● Cost and best practice considerations ● Fine-tuning arctic-extract models