No matter you are a fresh man or experienced IT talents, here, you may hear that GES-C02 certifications are designed to take advantage of specific skills and enhance your expertise. While, if you want to be outstanding in the crowd, it is better to get the GES-C02 certification. While, where to find the latest GES-C02 Study Material for preparation is another question. Snowflake GES-C02 exam training will guide you and help you to get the GES-C02 certification. Hurry up, download GES-C02 test practice torrent for free, and start your study at once.
| Section | Weight | Objectives |
|---|---|---|
| Topic 1: Snowflake Cortex AI and LLM Functions | 38% | - Building generative AI applications
|
| Topic 2: Snowflake for Gen AI Overview | 24% | - Generative AI and large language model fundamentals
|
| Topic 3: Snowpark Container Services for Gen AI | 10% | - Custom AI application operations
|
| Topic 4: Document Processing | 10% | - Document ingestion and preparation
|
| Topic 5: Snowflake Gen AI Governance | 18% | - Access control and security
|
Do you feel aimless and helpless when the GES-C02 exam is coming soon? If your answer is absolutely yes, then we would like to suggest you to try our GES-C02 training materials, which are high quality and efficiency test tools. Your success is 100% ensured to pass the GES-C02 Exam and acquire the dreaming certification which will enable you to reach for more opportunities to higher incomes or better enterprises.
NEW QUESTION # 35
Which commands can be used to display the available Snowflake Cortex LLM models? (Choose two)
Answer: C,E
Explanation:
In Snowflake, base foundation models available for Cortex functions are exposed as registered model entities within the shared system schema SNOWFLAKE.MODELS.
To inspect and display the catalog of available models:
* SHOW MODELS IN SNOWFLAKE.MODELS;: Explicitly queries the shared system schema housing foundation model definitions, listing their names, default versions, and operational metadata.
* SHOW MODELS;: Executes the broader model listing command across the currently active database and schema context or visible schemas permitted by the role's privileges.
Regarding the incorrect choices:
* LS @... lists files stored in stages, not registered model objects.
* SHOW VERSIONS LIKE ... inspects versions within a single, specific model instance rather than listing all available system models.
* CALL SNOWFLAKE.MODELS.CORTEX_BASE_MODELS_REFRESH() is a system procedure used internally to refresh the base model catalog metadata; it does not return a tabular display of models.
References & Study Guide Topics:
* Snowflake Gen AI Functions: Model Discovery and Metadata Management
* Snowflake Model Registry: Exploring System Models via SHOW MODELS
NEW QUESTION # 36
Which APIs or functions can be used to query the Snowflake Cortex Search Service? (Choose three)
Answer: A,B,F
Explanation:
Snowflake Cortex Search provides dedicated programmatic and SQL interfaces to query the hybrid search index and retrieve the top-k relevant context chunks for RAG architectures:
1. **Snowflake Python APIs:** Using the Snowflake Python SDK or Snowpark client (`snowflake.core.
cortex.search_service`), developers can execute search queries directly from Python applications, notebooks, or Streamlit interfaces.
2. **Snowflake REST APIs:** External applications, microservices, and web clients can retrieve search chunks over standard HTTPS endpoints by making authenticated REST calls to the Cortex Search service endpoint.
3. **The SEARCH_PREVIEW function:** In SQL worksheets and stored procedures, developers can test, query, and preview retrieval results directly using the built-in system function `SNOWFLAKE.CORTEX.
SEARCH_PREVIEW(...)`.
In contrast, `CORTEX.COMPLETE` executes text generation rather than searching an index;
`EMBED_TEXT_768` computes vector embeddings from input strings; and `CORTEX.SUMMARIZE` produces a condensed textual synopsis. None of these functions query a Cortex Search Service.
References & Study Guide Topics:
* Snowflake Gen AI Functions: Cortex Search Service Retrieval Protocols
* Application Development: Querying Indexes via Python, REST, and `SEARCH_PREVIEW`
NEW QUESTION # 37
A Gen AI Specialist wants to use a Snowflake Cortex LLM function to classify customer questions into two categories: support and food.
The Specialist created a table named QUERIES containing the following values:
| ID | QUERY_TEXT |
| :--- | :--- |
| 1 | How do I reset my account password? |
| 2 | Where's the best sushi place in town? |
| 3 | I need help with a billing issue. |
Which command should be used?
```sql
Answer: A
Explanation:
The `SNOWFLAKE.CORTEX.CLASSIFY_TEXT` function assigns unstructured text to one or more predefined taxonomy categories without requiring manual prompt engineering.
Its SQL signature requires two positional arguments:
1. `text`: The string column or literal containing the text to be evaluated (here, `query_text`).
2. `categories`: An `ARRAY` of strings defining the target classification categories (here, `['support', 'food']`).
Option B follows this syntax: `SNOWFLAKE.CORTEX.CLASSIFY_TEXT(query_text, ['support', 'food'])`.
The function evaluates each row in `QUERIES` and returns a JSON object containing the assigned category label.
Option A is invalid because it omits the mandatory category array. Option C reverses the argument order.
Option D uses invalid named-argument syntax and incorrectly passes a model parameter, as
`CLASSIFY_TEXT` uses an internal specialized model rather than exposing user-selected foundation models.
References & Study Guide Topics:
* Snowflake Gen AI Functions: `SNOWFLAKE.CORTEX.CLASSIFY_TEXT` Function Signatures
* Text Classification: Positional Arguments and Category Arrays
NEW QUESTION # 38
Which commands restrict access to Snowflake Cortex functions so that access is provided only to roles with explicitly granted privileges? (Choose two)
Answer: D,E
Explanation:
By default in Snowflake accounts, baseline privileges to access Cortex functions are broadly available because the shared database role SNOWFLAKE.CORTEX_USER is granted directly to the pseudo-role PUBLIC. Since every Snowflake user and custom role automatically inherits privileges assigned to PUBLIC, any user can invoke serverless Cortex LLM functions out of the box.
To eliminate this default public access and enforce a strict least-privilege security model, an administrator must execute:
* REVOKE DATABASE ROLE SNOWFLAKE.CORTEX_USER FROM ROLE PUBLIC; to remove direct access to the Cortex function wrappers.
* REVOKE IMPORTED PRIVILEGES ON DATABASE SNOWFLAKE FROM ROLE PUBLIC; to restrict inherited access to shared metadata, views, and system-defined database objects inside the shared SNOWFLAKE database.
Once these revocations take effect, serverless Cortex functions become inaccessible to general users until the ACCOUNTADMIN explicitly grants DATABASE ROLE SNOWFLAKE.CORTEX_USER to specific, authorized business roles. Options A and B are syntactically incorrect because CORTEX_USER is a database role, not an account-level role. Option D is invalid because Cortex is delivered via shared database roles, not via direct standard schema usage grants on SNOWFLAKE.CORTEX.
References & Study Guide Topics:
* Snowflake Gen AI Governance: Cortex Security Hardening and Least-Privilege Encampment
* Access Control Management: Database Roles vs. Account Roles in System Databases
NEW QUESTION # 39
Which privileges are needed to run a model fine-tuning job? (Choose two)
Answer: A,D
Explanation:
Executing fine-tuning jobs via SNOWFLAKE.CORTEX.FINETUNE requires specific privileges across the data source, processing compute, and target schema. Because the fine-tuning workflow queries existing tables or views containing training and validation data, the executing role must possess active container access, specifically USAGE on the parent database and schema housing those source datasets.
Furthermore, the output of a fine-tuning job is stored as a first-class model entity in the Snowflake Model Registry within a destination schema. Therefore, the executing role must hold either CREATE MODEL or OWNERSHIP on the destination schema where the fine-tuned model will be registered.
Option A is incorrect because serverless fine-tuning outputs to the Model Registry rather than requiring stage access for raw model weights. Option C is incorrect because OPERATE is an administrative warehouse privilege and does not apply to databases. Option D is incorrect because, while USAGE on the destination schema is required to navigate objects, the governing and authoritative model creation privilege is explicitly CREATE MODEL or OWNERSHIP.
References & Study Guide Topics:
* Snowflake Gen AI Governance: Serverless LLM Fine-Tuning Security Matrix
* Model Lifecycle Management: Schema Permissions for Model Registration (CREATE MODEL)
NEW QUESTION # 40
......
The Snowflake is committed to making the Snowflake GES-C02 certification exam journey simple, smart, and easiest. The mock SnowPro Specialty: Gen AI Certification Exam exams that will give you real-time environment for Snowflake GES-C02 exam preparation. To keep you updated with latest changes in the GES-C02 Test Questions, we offer one-year free updates in the form of new questions according to the requirement of GES-C02 real exam. Updated GES-C02 PDF dumps ensure the accuracy of learning materials and guarantee success of in your first attempt.
Reliable GES-C02 Test Testking: https://www.actualtestpdf.com/Snowflake/GES-C02-practice-exam-dumps.html