Activedumpsnet Logo
What is the PRIMARY purpose of the use of the PARSE_DOCUMENT function in Snowflake?
To identify any Personally Identifiable Information (PII) in text
To identify data that will benefit from the use of a directory table
To extract text from PDF files
To parse JSON data
The PARSE_DOCUMENT function is part of Snowflake Cortex AI and is designed specifically to extract text, layout information, and structured elements from unstructured documents, especially PDFs. It supports OCR-based extraction for scanned files and layout-aware extraction to preserve tables, headings, and format structure.
Its purpose is not PII detection; Snowflake does not provide built-in automatic PII identification via PARSE_DOCUMENT. It does not identify candidate data for directory tables and is unrelated to JSON parsing—Snowflake uses PARSE_JSON for JSON data.
PARSE_DOCUMENT is primarily used for workflows such as contract analysis, invoice extraction, document classification, compliance automation, and downstream AI enrichment.
==================
Which Snowflake Cortex LLM function allows a user to specify which model will be used?
COMPLETE
SENTIMENT
SUMMARIZE
TRANSLATE
TheCOMPLETEfunction is the only Cortex LLM function where the user can explicitly specify the model name (e.g., Mistral, Snowflake Arctic, Meta Llama models).
SUMMARIZE, SENTIMENT, and TRANSLATE are task-specific functions that use built-in, preselected models anddo not allowmodel selection.
What is the primary responsibility of Role Hierarchy in Snowflake's access control model?
To allow roles to inherit privileges from parent roles
To define the order of SQL command execution
To categorize different types of users
To specify the size of virtual warehouses
Role hierarchy enables a parent role to inherit privileges assigned to child roles. This simplifies RBAC administration, reduces redundant grants, and ensures scalable security management. It has no relation to SQL sequencing, user categorization, or compute sizing.
What parameter is used to define how long Time Travel can be used to access a table?
DATE_OUTPUT_FORMAT
DATA_RETENTION_TIME_IN_DAYS
TIMEZONE
USE_CACHED_RESULT
The DATA_RETENTION_TIME_IN_DAYS parameter controls the Time Travel retention period for Snowflake objects such as tables, schemas, and databases. It specifies the number of days that historical data (prior versions of rows or dropped objects) is retained and accessible via Time Travel. Within this retention window, users can query data “as of” a previous time, restore dropped objects, or clone objects at a historical point.
DATE_OUTPUT_FORMAT determines the display format for date values and is unrelated to historical retention. TIMEZONE affects how timestamps are interpreted and displayed, not how long data history is preserved. USE_CACHED_RESULT governs whether Snowflake may return cached query results, not Time Travel behavior.
==================
How is the initial activation of the Snowflake Data Exchange feature, which is necessary for establishing private exchanges, typically accomplished?
Any Snowflake account administrator can enable Data Exchange through the web interface with a single click.
Activation of the Data Exchange feature generally requires a request to Snowflake Support, who then enable it for the specific account.
Data Exchange is automatically enabled for all Snowflake accounts upon creation.
Activation of the Data Exchange feature requires a specific SQL command to be executed by the ACCOUNTADMIN role.
The Data Exchange feature is not automatically enabled for all Snowflake accounts. Instead, enabling this capability—particularly for private exchanges—typically requires submitting a request toSnowflake Support. Snowflake evaluates account type, region, and compliance requirements before enabling the Data Exchange functionality. Snowflake administrators cannot independently enable this through Snowsight, nor is there a SQL command available to turn it on. Once activated, account administrators can create private exchanges, manage listings, and define which Snowflake accounts can participate. This activation step ensures secure, intentional use of data-sharing capabilities at an account level.
=======================================
What is the name for a Snowflake account holder who shares data with other Snowflake accounts?
A data provider
A data consumer
A data reader
A data administrator
In Snowflake’s Secure Data Sharing model, the accountsharingdata is known as thedata provider. Providers create shares that include selected objects (tables, views, secure views, etc.) and grant access to consumer accounts.
Adata consumerreceives the shared data.Data readeranddata administratorare not defined terms in Snowflake’s sharing architecture.
==================
What is the typical syntax for using the LIMIT clause to retrieve the first 10 rows of a table named employees?
SELECT * FROM employees LIMIT 10;
SELECT LIMIT 10 * FROM employees;
LIMIT 10 SELECT * FROM employees;
SELECT * FROM employees WHERE LIMIT 10;
TheLIMITclause is used to restrict the number of rows returned by a query. The correct syntax in Snowflake is:
SELECT * FROM employees LIMIT 10;
This retrieves the first 10 rows of the result set. LIMIT appears at the end of the SELECT statement. Snowflake follows a SQL syntax similar to MySQL/PostgreSQL regarding LIMIT usage.
Incorrect forms include:
Using LIMIT before SELECT
Embedding LIMIT inside WHERE
Reversing the order of SELECT and LIMIT
LIMIT is frequently used for sampling, record previewing, debugging, and exploratory analysis.
What task can be performed on the Snowsight Schema Details page?
Change the schema name.
Share a schema with a different account.
Truncate the schema data.
Edit the schema metrics.
On the Snowsight Schema Details page, one of the supported operations is renaming the schema. The UI exposes controls that allow users with appropriate privileges to change the schema name, which can help maintain consistent naming conventions or reflect project reorganizations.
Sharing data with other accounts is typically done using secure shares at the database or object level, not from a simple “Share this schema” function on the Schema Details page. Truncation is a table-level operation (e.g., TRUNCATE TABLE), not something that applies at the schema level. Metrics visible on the Schema Details page (such as object counts or storage usage) are informational and not directly editable; they are derived from system metadata.
==================
What a Database in Snowflake cant contain?
Views
Tables
Role
Database Role
A Snowflake database is a top-level container that can include schemas, and within those schemas it can contain objects such astables,views,stages,functions,procedures, anddatabase roles. However,global account-level roles(such as SYSADMIN, SECURITYADMIN, PUBLIC, or custom account roles) do not reside inside a database. These roles are created and managed at the Snowflake account level, not within any specific database. In contrast,database rolesare scoped within a specific database and can exist inside it. Views and tables are standard database objects. Therefore, the only option that a Snowflake database cannot contain is an account-levelRole.
=======================================
What type of mode available in PARSE_DOCUMENT function? (choose two)
OCR
OMR
CONTENT
LAYOUT
PARSE_DOCUMENT supports two processing modes:OCRandLAYOUT. OCR mode performs Optical Character Recognition, extracting raw text from scanned documents, images within PDFs, or low-quality text-based documents. It is ideal for scenarios like contract ingestion, receipt processing, or older scanned documents. LAYOUT mode extracts structured layout elements—tables, paragraphs, lines, bounding boxes—preserving the original document’s spatial organization. This enables downstream analytical tasks such as table reconstruction or semantic segmentation of document content. OMR (Optical Mark Recognition) is not a supported feature, and “CONTENT” is not a valid mode. By supporting OCR and LAYOUT modes, Snowflake Cortex provides robust document intelligence capabilities directly within the Snowflake environment.
Which package is needed for Python worksheet?
NumPy
Snowpark
Matplotlib
Pandas
Snowflake’s Python Worksheets require theSnowpark for Pythonpackage. Snowpark integrates deeply with Snowflake’s compute engine, enabling DataFrame operations, UDF creation, ML workflows, and direct execution of Python logic inside Snowflake compute.
While additional libraries like Pandas, NumPy, and Matplotlib may be available in worksheets, they arenot requiredto enable the Python execution environment. Snowpark is the core computational interface that connects Python to Snowflake’s data and compute layers.
It enables:
Distributed data processing
Transformations expressed in Python but executed inside Snowflake
Access to Snowflake tables as DataFrames
Integration with Snowpark ML and Cortex functions
Thus, Snowpark is the essential package for Python worksheet support.
====================================================
What is the SHOW GRANTS SQL command primarily used for?
To view the history of data loads.
To display all privileges granted to a role or user.
To list all active users in the account.
To show current warehouse credit usage.
SHOW GRANTS lists privileges assigned to roles, users, objects, or shares. It is essential for permissions auditing and RBAC management.
SHOW USERS lists users, not privileges.
Warehouse usage is in ACCOUNT_USAGE views.
Load history is retrieved via COPY_HISTORY or LOAD_HISTORY.
====================================================
What does Snowflake UI called?
Snowsite
SnowGUI
SnowView
Snowsight
The official Snowflake web interface is calledSnowsight. Snowsight is the modern, browser-based UI that enables SQL development, Python worksheets, dashboarding, visual exploration, and account monitoring. It replaces the classic UI and is now the default interface. Snowsight provides integrated capabilities such as notebooks, data loading interfaces, dashboards, role and warehouse management, and visual query history. Other options like Snowsite, SnowGUI, and SnowView are not valid Snowflake product names.
=======================================
Given a table named MY_TABLE, which SQL statement would create a clone named MY_TABLE_CLONE?
COPY TABLE MY_TABLE TO MY_TABLE_CLONE;
CREATE TABLE MY_TABLE_CLONE CLONE MY_TABLE;
BACKUP TABLE MY_TABLE TO MY_TABLE_CLONE;
RESTORE TABLE MY_TABLE TO MY_TABLE_CLONE;
The correct SQL syntax to create a zero-copy clone of an existing table is:
CREATE TABLE MY_TABLE_CLONE CLONE MY_TABLE;
This command instantly creates a new table that references the same underlying micro-partitions as the original. Because of Snowflake’smetadata-only cloning, no storage is consumed at the time of creation. Storage only increases when either the original or the clone diverges through DML operations, following acopy-on-writemodel.
Cloning is available for multiple object types—tables, schemas, databases, stages, streams, tasks, and more. This capability enables rapid creation of development sandboxes, QA environments, rollback copies, or controlled experimentation without duplicating data.
Incorrect options:
“COPY TABLE” is not a valid Snowflake command.
BACKUP/RESTORE are not Snowflake SQL commands.
RESTORE applies only to Time Travel or Fail-safe, not to cloning.
Thus, the CLONE keyword is the only correct method for zero-copy duplication.
====================================================
Which of the following system-defined roles exist in Snowflake? (Choose any 3 options)
SECURITYADMIN
DATABASEADMIN
ACCOUNTADMIN
SYSADMIN
Snowflake provides a predefined set ofsystem-defined rolesthat enforce Role-Based Access Control (RBAC). These roles ensure structured governance and centralized privilege management across accounts. The primary system-defined roles include:
ACCOUNTADMIN, the highest-privileged role, responsible for global account-level activities such as billing, governance, replication, and cross-region/cloud configuration. It has implicit ownership of all objects.
SECURITYADMINmanages users, roles, MFA, and all privilege grants. This role ensures operational control over user lifecycle management while supporting separation of duties from ACCOUNTADMIN.
SYSADMINmanages objects such as databases, schemas, tables, warehouses, and other compute objects. It is the default role for data engineering and data platform teams needing full control of object creation and maintenance.
DATABASEADMINdoes not exist as a system-defined role—it is typically user-created for customization. System roles form a foundational security model for controlled privilege escalation and governance.
====================================================
What is the purpose of assigning roles to users in Snowflake?
To manage and enforce permissions on objects
To define user tasks
To optimize query execution plans
To control which data types users can query
Snowflake uses a Role-Based Access Control (RBAC) model, whererolesare the containers of privileges. Assigning roles to users ensures that permissions on database objects (such as tables, schemas, warehouses, and functions) are enforced consistently and securely. Users do not receive privileges directly; instead, privileges are granted to roles, and roles are assigned to users.
This enables scalable, auditable, and manageable access control.
Roles do not determine tasks, do not affect query optimization, and do not govern which data types a user may query—permissions are object-based, not datatype-based.
==================
Which of the following are examples of semi-structured data formats? (Choose any 3 options)
JSON
CSV
Parquet
XML
Semi-structured data refers to formats that do not follow a rigid relational schema but still contain structural tags or hierarchies, allowing flexible representation of nested or irregular data. In Snowflake,JSON,Parquet, andXMLare all considered semi-structured because they incorporate metadata, hierarchical fields, or tagged data that can vary across records. JSON offers key–value pairs and nested arrays, making it ideal for logs and API responses. Parquet, being a columnar file format containing both schema definitions and metadata, is optimized for analytics while still supporting semi-structured capabilities such as variable field nesting. XML uses tags and attributes to represent hierarchical content, making it semi-structured as well. On the other hand, CSV represents strictly structured, row/column-based data without inherent metadata or hierarchy, so it is not considered semi-structured. Snowflake treats semi-structured formats by loading them into the VARIANT data type, enabling powerful SQL-based exploration using path notation.
=======================================
What is a benefit of using an external stage to load data into Snowflake?
External stages reduce data storage costs because data is stored outside Snowflake.
External stages provide automatic data purging after successful loads.
External stages are more secure than internal stages for sensitive data.
External stages reduce the number of objects in a database.
External stages point to files in external cloud storage (S3, Azure Blob, GCS). Because the data is not stored inside Snowflake, the user avoids Snowflake storage charges, which can significantly reduce cost for large staging datasets.
External stages do not automatically delete files, are not inherently more secure than internal stages, and still count as database objects even though they reference external storage.
==================
Which function in Snowflake Cortex LLM are Task Specific Function? (Select two)
TRANSLATE
CLASSIFY_TEXT / AI_CLASSIFY
COUNT_TOKENS
PARSE_DOCUMENT
Snowflake’s Cortex LLM includestask-specific functions, meaning each performs a well-defined AI operation with predictable outputs. Examples include:
TRANSLATE– Converts text between languages; deterministic and domain-independent.
CLASSIFY_TEXT / AI_CLASSIFY– Assigns text to predefined categories, ideal for sentiment, topics, or routing tasks.
PARSE_DOCUMENT– Extracts structured information from documents (PDFs, invoices, receipts, contracts) including layout-aware content.
These functions are optimized for reliability, reproducibility, and governance, making them suitable for production pipelines.
COUNT_TOKENSis not task-specific—it’s a utility function used to estimate LLM token usage rather than perform a primary AI task.
Thus, TRANSLATE, CLASSIFY_TEXT, and PARSE_DOCUMENT are the correct task-specific functions.
====================================================
To exclude certain columns from a SELECT query, you should:
Explicitly list the columns you want to include
Use the EXCLUDE keyword
Use a REMOVE function on the table
Use the OMIT clause
Snowflake supports theEXCLUDEkeyword to simplify queries when excluding certain columns from a SELECT * operation. SELECT * EXCLUDE (column1, column2) reduces verbosity and enhances maintainability, especially when table schemas evolve. Explicitly listing all columns is possible but inefficient. Snowflake does not support REMOVE functions for columns nor an OMIT clause. EXCLUDE is the correct and official mechanism.
=======================================
When loading CSV data, what FILE FORMAT option allows you to skip the header row?
SKIP_FILE_HEADER = FALSE
IGNORE_HEADER = TRUE
HEADER_SKIP = 1
SKIP_HEADER = 1
Snowflake’s file format options allow granular control over CSV ingestion. The SKIP_HEADER = 1 parameter instructs Snowflake to ignore the first line of the file, typically containing column headers. This is the correct and official parameter within FILE FORMAT objects or inline COPY INTO options. Other options listed—such as SKIP_FILE_HEADER, IGNORE_HEADER, or HEADER_SKIP—are not valid Snowflake parameters. When SKIP_HEADER is applied, Snowflake begins reading data rows starting from line 2. This ensures proper alignment between file contents and table structure during ingestion. SKIP_HEADER can also be set to values greater than 1 if multiple header rows exist. This behavior is essential when loading structured data where the header row is not intended for table consumption.
=======================================
What is the primary purpose of the LIMIT clause in a Snowflake query?
To sort the result set
To filter the result set
To restrict the number of rows returned
To group the result set
The LIMIT clause limits the number of rows Snowflake returns from a query. It is commonly used to preview datasets, improve performance when exploring large tables, and paginate results. LIMIT may be combined with OFFSET to skip a number of rows. Sorting is performed with ORDER BY, filtering with WHERE, and grouping with GROUP BY—not with LIMIT. Therefore, restricting returned rows is the primary purpose of LIMIT.
=======================================
What are the benefits of using the Snowsight data loading interface? (Select TWO).
It creates permanent file formats that can be used to load data in the future.
It allows a user to insert the records of a supported file into a table.
It will try to detect data types.
It allows a user to optimize data loading into a table.
It lets a user merge file rows into the table records.
Snowsight’s file-loading interface:
•Automatically detects data typesby inspecting column values.
•Loads (inserts) file contents directly into a table, either a new table or an existing one.
Snowsight does not automatically create permanent file formats, does not merge rows, and does not optimize warehouse-level performance.
==================
What is the Snowsight Query Profile used for?
To execute SQL queries
To create new database objects
To manage data loading processes
To visualize and analyze query performance
The Snowsight Query Profile is a powerful diagnostic tool that provides a visual breakdown of how Snowflake executed a query. Its primary purpose is to help users visualize and analyze query performance. It displays execution steps, including scan operations, join strategies, pruning results, aggregation methods, and data movement between processing nodes.
The profile shows metrics such as execution time per step, partition pruning effectiveness, bytes scanned, and operator relationships. This allows developers, analysts, and DBAs to identify bottlenecks—such as unnecessary full-table scans, non-selective filters, or inefficient joins—and tune SQL accordingly.
Query Profile does not execute queries; execution happens in worksheets or programmatic interfaces. It does not create objects or manage data loading; those tasks involve separate SQL commands and UI interfaces.
Overall, Query Profile is essential for performance tuning, helping teams reduce compute costs, optimize warehouse sizing, and improve query efficiency.
==================
Which cloud platforms does Snowflake support?
Amazon Web Services (AWS)
Google Cloud Platform (GCP)
Microsoft Azure
All of the options
Snowflake is a fully cloud-native platform that supports deployment across all three major cloud providers:AWS, GCP, and Azure. Snowflake delivers consistent functionality across each provider, allowing organizations to choose the cloud best suited for regulatory, architectural, and business requirements. Although small feature differences may exist between cloud providers, Snowflake’s core capabilities—virtual warehouses, storage layers, security, data sharing, and governance—operate uniformly across all three platforms. This multi-cloud support gives Snowflake strong flexibility for hybrid, multi-region, and multi-cloud deployments.
=======================================
What does the SELECT * statement do in a Snowflake query?
Retrieves all columns from a specified table or view
Retrieves only distinct values
Retrieves only the primary key column
Retrieves a limited number of rows
The SELECT * statement instructs Snowflake to returnall columnsfrom the referenced table or view. This is commonly used during data exploration, debugging, initial data profiling, and validation steps. It allows users to quickly view the complete dataset structure without manually specifying each column name.
However, while SELECT * retrieves all columns, it does not limit the number of rows. To restrict rows, developers must include aLIMITclause (e.g., SELECT * FROM table LIMIT 10;).
The query does not automatically apply DISTINCT or primary key filtering—Snowflake returns all rows exactly as stored unless additional filtering, WHERE conditions, or ordering are provided.
Though SELECT * is convenient, Snowflake best practices recommend explicitly selecting columns in production workloads to optimize performance and avoid unnecessary scanning of unused fields.
How does Snowflake's compute layer handle query execution?
By optimizing data in cloud storage
With shared-disk architecture
Using MPP (massively parallel processing) compute
Using single-threaded processing
Snowflake’scompute layerusesMassively Parallel Processing (MPP), meaning queries are divided into smaller tasks distributed across multiple compute nodes in the Virtual Warehouse. Each node processes a portion of the data simultaneously, maximizing parallelism and drastically reducing query times.
Although Snowflake uses a central storage layer (shared-disk model), the compute engine behaves like ashared-nothing MPP system, where each node handles local processing independently, minimizing contention.
Incorrect options:
Snowflake does not rely on single-thread execution.
Storage optimization occurs at the Storage Layer, not compute.
Snowflake does not use traditional shared-disk execution; compute nodes work in parallel independently.
This architecture enables high performance for large analytical workloads.
====================================================
What are Snowflake notebooks primarily used for?
Storing raw data
User authentication
Writing and executing SQL queries, Python commands, building visualizations, and documenting analysis
Managing cloud storage
Snowflake Notebooks provide an interactive environment where developers and analysts can combineSQL,Python, visualization libraries, and documentation. Use cases include exploratory analysis, ETL prototyping, data engineering workflows, machine learning model development, and dashboard creation using Streamlit components.
Notebooks allow mixing of SQL and Python cells with shared session state, enabling smooth transitions between Snowpark DataFrames, SQL queries, visual charts, and markdown explanations. They enhance reproducibility and collaboration, supporting versioning, parameterization, and seamless Snowflake compute integration.
Incorrect options:
Raw data is stored in Snowflake tables, not in notebooks.
User authentication is handled by the Cloud Services Layer.
Managing cloud storage is automatic and not a notebook responsibility.
Thus, Snowflake notebooks are an end-to-end development and analytics interface.
====================================================
Which of the following are date and time data types in Snowflake? (Choose any 3 options)
TIMEDATE
TIMESTAMP
DATE
DATETIME
Snowflake provides multipledate and time data typesto handle various temporal workloads. TheDATEtype stores only the calendar date (year, month, day), suitable for dimensional modeling, slowly changing dimensions, and calendar-related analytics.
TIMESTAMPrepresents a point in time and includes sub-second precision. Snowflake supports multiple variants:
TIMESTAMP_NTZ(no time zone)
TIMESTAMP_LTZ(local time zone)
TIMESTAMP_TZ(explicit time zone)
These options allow flexibility for global operations, event logs, and time-series analytics.
DATETIMEis an alias forTIMESTAMP_NTZ, meaning it stores both date and time but without time-zone awareness. It is commonly used in ETL, application logs, and system-generated events.
TIMEDATEis not a valid Snowflake data type and does not exist in Snowflake’s type system.
These temporal types support extensive built-in datetime functions, automatic casting, and integration with semi-structured data through VARIANT.
====================================================
Which are the type of Views we have in Snowflake? (Choose any 3 options)
Materialized
Non-Materialized
UnMaterialized
Secure
Snowflake supportsNon-Materialized Views(standard views),Materialized Views, andSecure Views. Non-materialized views compute results dynamically at query time. Materialized views store precomputed results, improving performance for repeated analytical queries. Secure views protect underlying query logic and metadata from being exposed, ensuring privacy when sharing datasets. The option “UnMaterialized” is not a Snowflake concept and does not exist as a view type.
What is the purpose of auto-resume on a virtual warehouse?
To restart the warehouse manually after suspension.
To automatically start the warehouse when a query is submitted to it.
To automatically scale up the warehouse size.
To prevent the warehouse from suspending.
When auto-resume is enabled, Snowflake automatically starts a suspended warehouse when a query or task is submitted. This ensures smooth operations without manual intervention.
It does not scale the warehouse, prevent suspension, or require manual restarting.
====================================================
What Snowflake parameter is configured in the Query Processing layer?
The minimum and maximum serverless compute limits
The types of tables available in an account
The sizing of virtual warehouses
The minimum and maximum micro-partition limits
The Query Processing layer of Snowflake is wherevirtual warehouses operate, so warehouse sizing parameters (X-Small to 6X-Large) fall under this layer. Warehouse size determines compute power, concurrency, and performance behavior for SQL workloads. Administrators configure warehouse size based on workload intensity, response time requirements, and cost considerations.
Serverless compute limits and micro-partition limits belong to storage and services layers. Table types (permanent, transient, temporary) are storage-level configurations, not part of Query Processing.
Thus, warehouse sizing is the correct parameter configured at the Query Processing layer.
==================
Which SQL command is used to view the definition of a Table?
SHOW TABLE
SELECT GET_DDL('TABLE','
SELECT * FROM INFORMATION_SCHEMA.ABLES
DESCRIBE TABLE
TheGET_DDLfunction retrieves the Data Definition Language (DDL) script that was used to create a given object. Executing:
SELECT GET_DDL('TABLE', 'MY_TABLE');
returns the full DDL including column definitions, comments, clustering keys, constraints, masking policies, and other metadata. This makes it essential for schema migration, replication, compliance audits, and environment synchronization.
DESCRIBE TABLEshows only column-level metadata—names, types, nullability—but does not return the full DDL.
SHOW TABLEis not a valid Snowflake command; tables are listed using SHOW TABLES.
INFORMATION_SCHEMA.TABLES lists table metadata, but the provided option “ABLES” is invalid and still would not provide DDL even if corrected.
Thus,GET_DDL()is the only method that returns the complete table definition directly.
====================================================
What is a key feature of Snowflake notebooks?
Command-line interface only
Text-only data display
Integrated environment for writing queries and visualizing results
Manual hardware configuration
Snowflake Notebooks provide an integrated, interactive development environment that enables users to write SQL and Python code, visualize results, and document analysis—all in the same workspace. They support data visualizations, charts, tables, and Streamlit-based interactions. Notebooks run entirely within Snowsight and require no manual hardware configuration. They are not CLI-based and support much richer displays than plain text. This integration streamlines the entire data exploration, transformation, and modeling workflow.
=======================================
What is a key characteristic of a Snowflake virtual warehouse?
It provides compute resources.
It manages account roles.
It permanently stores data.
It encrypts data.
A virtual warehouse is the compute engine of Snowflake. It provides CPU, memory, and temporary storage needed to execute SQL queries, data loading operations, and DML actions. Warehouses can be sized dynamically and suspended or resumed to optimize cost.
Warehouses donotstore data; Snowflake’s storage is independent and centralized. Warehouses do not manage roles—access control is handled through Snowflake’s RBAC system. Encryption is performed automatically by Snowflake’s storage and cloud services, not by warehouses.
Thus, the correct characteristic is that virtual warehouses supply compute.
==================
If you'd like, I can provideQuestions 42–55 next, with the same 150–200-word explanations.
You said:
Questions 42–55 next, with the same 150–200-word explanations
ChatGPT said:
Below areQuestions 42–55, all formatted exactly per your requirements, with150–200-word explanationsandevery original option preserved exactly.
What are the steps to create a new stage in Snowsight?
Data >> Create Schema
Data >> add data >> Create Schema
Data Product >> Create Schema
Data >> Database >> Schema >> Create Stage
To create a new stage in Snowsight, users navigate through:Data → Database → Schema → Create Stage. Within the schema, selecting the "+" icon opens the option to create a stage. Users may configure internal or external stages, encryption settings, and directory table options. Other paths listed reference creating schemas rather than creating stages and are therefore incorrect.
=======================================
What is the impact of enabling auto-suspend on a Snowflake virtual warehouse?
The size of the warehouse will adjust automatically, improving query performance.
The warehouse will be dropped after a specified period of inactivity.
The warehouse will be stopped after a specified period of inactivity, reducing costs.
The warehouse costs will stabilize from month-to-month.
When auto-suspend is enabled on a virtual warehouse, Snowflake automatically suspends (stops) the warehouse after it has been idle for the configured period of time. Once suspended, the warehouse stops consuming compute credits, thereby reducing costs, since Snowflake bills only for active compute usage. When new queries arrive, auto-resume (if enabled) restarts the warehouse automatically.
Auto-suspend does not change the warehouse size; scaling up or down is a separate configuration. The warehouse is not dropped—its metadata and settings remain intact. Costs may be reduced and made more efficient but are not guaranteed to “stabilize month-to-month,” as the bill still depends on actual usage and workload patterns.
==================
What will be returned when a user runs this command?
SELECT count FROM my_table LIMIT 10;
A non-deterministic set of 10 values in the count column.
The highest 10 values in the count column.
All values in the count column that are less than or equal to 10.
The lowest 10 values in the count column.
When a LIMIT clause is applied without an ORDER BY, Snowflake does not guarantee which rows will be returned. This means the result of:
SELECT count FROM my_table LIMIT 10;
is anon-deterministic set of 10 rows. Because Snowflake stores data in micro-partitions and distributes processing across compute resources, the natural order of rows is undefined unless explicitly controlled.
To retrieve the lowest or highest values, users must specify ORDER BY count ASC or ORDER BY count DESC respectively. Without ordering, Snowflake simply returnsany10 qualifying rows.
• Option B (highest values) requires ORDER BY count DESC.
• Option D (lowest values) requires ORDER BY count ASC.
• Option C (values ≤ 10) requires a WHERE clause (WHERE count <= 10).
Therefore, the query returns a non-predictable sample of 10 rows from the column, making option A correct.
==================
When should AUTO_SUSPEND be enabled for a virtual warehouse?
To ensure the warehouse is always active for immediate queries.
To save credits during periods of inactivity.
When the warehouse is expected to run continuously.
To increase the warehouse's performance.
AUTO_SUSPEND minimizes cost by suspending compute after a specified idle period.
It prevents unnecessary credit consumption while ensuring compute resumes automatically when needed.
Performance improvements depend on warehouse size, not suspension settings.
====================================================
What is the primary purpose of the CLASSIFY_TEXT function in Cortex?
Translating text to different languages
Generating text completions based on a given prompt
Extracting data from documents
Classifying text into predefined categories
TheCLASSIFY_TEXTfunction performscategory assignmentfor free-form text. Users provide a list of predefined labels, and the function predicts the most appropriate category using a Snowflake-optimized LLM. It is ideal for automatically tagging customer feedback, routing support tickets, labeling product reviews, classifying email content, and segmenting operational logs.
The function outputs both the predicted label and an associated confidence score, enabling downstream filtering, dashboarding, and automated processing.
Other options belong to different Cortex functions:
TRANSLATEhandles multilingual translation.
COMPLETEgenerates natural language completions.
PARSE_DOCUMENTextracts structured information from documents.
Thus, CLASSIFY_TEXT is task-specific and optimized specifically for classification workloads.
====================================================
What are the key benefits of using Snowflake? (Select TWO).
Independent scaling of compute and storage
Vendor lock-in
Manual infrastructure management
Near-unlimited concurrency
On-premises deployment
Snowflake’s multi-cluster shared data architecture enablesindependent scaling of compute and storage, meaning workloads can be sized differently without affecting stored data.
It also providesnear-unlimited concurrency, because Snowflake can automatically add compute clusters during peak loads.
Snowflake does not require manual infrastructure management and runs fully in the cloud—not on-premises. Multi-cloud support reduces vendor lock-in, not increases it.
==================
What is the default Time Travel retention period for standard tables in Snowflake?
0 days
1 day
7 days
14 days
Standard permanent tables in Snowflake have a default1-day Time Travel retention period. During this period, users may query historical data, restore dropped tables, or clone past states. Higher editions allow extending this period up to 90 days. Temporary and transient tables have 0-day retention by default.
====================================================
What filter can be used when searching for data products on the Snowflake Marketplace?
Size
Compatibility
Price
Performance
On the Snowflake Marketplace, users can apply a Price filter when searching for data products. This filter helps distinguish between free offerings and paid listings, making it easier to align data acquisition with budget and commercial terms. Marketplace metadata includes pricing information that this filter uses to refine search results.
Dataset “Size” is not exposed as a primary Marketplace search filter. “Compatibility” is implied, as all Marketplace products are consumable within Snowflake. “Performance” is not a filterable attribute, because performance is influenced mainly by the consumer’s compute configuration and query design, rather than a fixed property of the Marketplace listing.
==================
In the Query Profile, what does the Pruning section provide?
Information on how Snowflake removed rows from the query results.
Information on how Snowflake removed columns from the query results.
Information on how Snowflake removed objects from the query plan.
Information on how Snowflake removed micro-partitions from the query scan.
The Pruning section of the Snowsight Query Profile showshow Snowflake eliminated unnecessary micro-partitions from the scan phaseof the query. Snowflake stores data in micro-partitions and maintains metadata such as min/max values for each column within each partition. When a query includes filters (e.g., WHERE clauses), Snowflake evaluates this metadata to determine which micro-partitions cannot possibly satisfy the predicate. These partitions are skipped, meaning they are never scanned or read from storage.
This process drastically improves performance because Snowflake minimizes I/O, reduces compute usage, and shortens execution time. Partition pruning is especially impactful on large tables because only a fraction of the stored micro-partitions typically need to be accessed.
The Pruning section does not show removedrows—that happens during the filter step. It does not show removedcolumns—column pruning is handled separately by the optimizer. It also does not show removedobjectsfrom the plan. Its sole purpose is to document micro-partition elimination and scan reduction.
==================
What Snowflake object is used to organize database objects into logical groupings?
Schemas
Roles
Tables
Stages
Schemas serve as logical containers within a database, grouping tables, views, file formats, functions, and other objects.
Roles control access, not organization.
Tables store data but do not group objects.
Stages store files or point to external storage; they are not organizational containers.
==================
What is a key benefit of using Snowsight for loading data into Snowflake?
Requires external tools for data loading
Manual data storage configuration
Simplified and intuitive data loading process
Limited to specific file formats
Snowsight provides an intuitive UI-based workflow for loading data, enabling drag-and-drop file upload, schema inference, previewing records, automatic table creation, and loading into existing tables. Users can load CSV, JSON, Parquet, AVRO, ORC, and other supported formats without writing COPY INTO commands manually.
Snowsight also generates the equivalent SQL code, helping users understand and reuse ingestion scripts in pipelines. It eliminates the need for external tools such as SnowSQL CLI or custom ETL scripts.
Incorrect statements:
External tools are not required.
Manual storage configuration is unnecessary; Snowflake abstracts all storage.
Snowsight supports a wide variety of formats, not limited ones.
Thus, the key advantage is asimple, guided data-loading workflow, especially useful for new Snowflake users.
====================================================
What is the main advantage of using Materialized Views in Snowflake?
They always contain the latest data in real-time.
They can be directly updated by DML statements.
They physically store pre-computed results to improve query performance.
They are primarily used for data masking.
Snowflake Materialized Views physically store the results of a defined query. This pre-computation significantly improves performance for repetitive or complex queries, especially those based on aggregations and joins. Snowflake automatically maintains materialized views asynchronously. They do not update in real-time, cannot be changed through DML, and are not intended for masking—dynamic masking policies serve that purpose.
====================================================
Which of the following are valid components of Snowflake's core architecture? (Select THREE)
On-premises Data Centers
User Interface Layer
Third-Party ETL Tools
Database Storage Layer
Query Processing Layer
Cloud Services Layer
Snowflake’s architecture consists of:
• Database Storage Layer – Stores optimized columnar data.
• Query Processing Layer – Executes workloads via virtual warehouses.
• Cloud Services Layer – Handles metadata, optimization, access control.
ETL tools and UI are external integrations. Snowflake is cloud-native and has no on-premises components.
====================================================
What are the key benefits of the Snowflake multi-cluster shared data architecture? (Select TWO).
It provides enhanced data security features.
It optimizes data loading for unstructured data.
It allows for independent scaling of compute and storage.
It stores data in a columnar format to improve performance.
It offers near-unlimited concurrency and elasticity.
The Snowflake multi-cluster shared data architecture separates compute and storage, enablingindependent scaling of each. Compute resources (virtual warehouses) operate independently from the centralized storage layer, allowing users to increase compute power without impacting storage costs—or vice versa. This flexibility provides major advantages for cost optimization and workload performance tuning.
The architecture also supportsnear-unlimited concurrency and elasticity. When many users or workloads run simultaneously, Snowflake can automatically add additional clusters to a multi-cluster warehouse, ensuring that no queries experience queuing or performance degradation. This capability is crucial for BI dashboards, ETL pipelines, and large organizations with varied usage patterns.
Columnar storage (option D) is indeed a Snowflake feature but is not unique to the multi-cluster architecture. Enhanced security arrives via Snowflake’s platform-wide mechanisms, not specifically because of multi-cluster architecture. Unstructured data loading (option B) is also not governed by multi-cluster behavior.
==================
Which of the following data format supported to unload semi-structured data from Snowflake? (Choose any 2 options)
JSON
CSV
Parquet
XML
Snowflake supports unloading semi-structured data specifically intoJSONandParquetformats. JSON preserves semi-structured hierarchy and nested fields, making it ideal for interchange, backup, and integration with downstream systems. Parquet provides columnar, compressed, and metadata-rich storage well-suited for analytical reprocessing in data lakes or other systems. CSV is not semi-structured and cannot represent nested data accurately. XML, although a semi-structured format, is not supported by Snowflake as an unload format. When performing COPY INTO
=======================================
Which of the following are numeric data types supported by Snowflake? (Choose any 2 options)
INTEGER
BOOLEAN
VARCHAR
FLOAT
Snowflake supports several numeric data types, includingINTEGER(and its aliases INT, BIGINT, SMALLINT, TINYINT) andFLOAT(a floating-point type). INTEGER represents exact whole numbers, and FLOAT supports approximate numerical values with fractional components. BOOLEAN is a logical data type used for TRUE/FALSE values, not numeric. VARCHAR is a string data type, also not numeric. Thus, INTEGER and FLOAT are the correct numeric data types supported by Snowflake.
=======================================
Which of the following is true about Snowflake clones?
Clones can only be created from databases, not tables or schemas.
Clones initially consume minimal/no storage, with storage only being used for changes made to the clone or the original.
Clones consume the same storage as the original object.
Clones are automatically synchronized with the original object.
Snowflake cloning is a metadata-only operation at creation. Both the clone and source share micro-partitions until changes occur (copy-on-write).
They are independent and do not auto-sync.
They can be made at the database, schema, or table level.
====================================================
Where do tables reside in Snowflake?
Stages
Virtual warehouses
Schemas
File formats
In Snowflake’s logical hierarchy, tables reside within schemas, and schemas reside within databases. This structured arrangement allows clear organization, access management, and separation of workloads or business domains. A schema functions as a container that holds tables, views, functions, sequences, stages, and file formats. When users reference a table, they typically qualify it using the full three-part name: database.schema.table.
Stages are used to store or reference files, not to hold structured database tables. Virtual warehouses provide compute power for executing queries and performing DML operations but do not store data. File formats define how staged files should be interpreted (CSV, JSON, Parquet, etc.) and are unrelated to where tables physically reside.
Snowflake separates compute and storage, so while compute happens in virtual warehouses, all persistent data—including tables—is managed in Snowflake’s centralized storage layer, organized through schemas and databases. This organization ensures consistency, ease of management, and predictable access control.
==================
How can you load JSON data into a Snowflake table from stage?
Use the INSERT INTO command
Use the COPY INTO command
Use the LOAD DATA command
Use the UPLOAD JSON command
Snowflake uses the COPY INTO