Power Up Your Study Prep: Black Friday 75% Discount! Use coupon code below to save! - Ends in 0d 00h 00m 00s - Coupon code: big75certs

Free and Premium Snowflake GES-C02 Dumps Questions Answers

Page: 1 / 6
Total 85 questions

SnowPro Specialty: Gen AI Exam Questions and Answers

Question 1

Which components are necessary to deploy and run a container with Snowpark Container Services? (Choose two)

Options:

A.

A compute pool to run the container

B.

An external stage linked to Amazon S3

C.

A schedule task assigned to a virtual warehouse

D.

A file format registered for JSON or CSV data ingestion

E.

A service specification that defines the container behavior

Buy Now
Question 2

A Gen AI Specialist must prepare long documents for LLM ingestion. Which Snowflake Cortex function supports this requirement by returning an array of text chunks?

Options:

A.

EMBED_TEXT_768

B.

FINETUNE

C.

PARSE_DOCUMENT

D.

SPLIT_TEXT_RECURSIVE_CHARACTER

Question 3

Which commands can be used to display the Snowflake Cortex LLM models that are available? (Choose two)

Options:

A.

SHOW MODELS;

B.

LS @SNOWFLAKE.CORTEX.LLM;

C.

SHOW MODELS IN SNOWFLAKE.MODELS;

D.

SHOW VERSIONS LIKE 'CORTEX' IN MODEL LLM;

E.

CALL SNOWFLAKE.MODELS.CORTEX_BASE_MODELS_REFRESH();

Question 4

Which authentication methods are supported for accessing the Snowflake Cortex LLM REST API? (Choose two)

Options:

A.

SAML 2.0

B.

OAuth 2.0

C.

Single Sign-On (SSO)

D.

Key-pair authentication

E.

Multi-Factor Authentication (MFA)

Question 5

A table in a pipeline has a VARCHAR column that contains free-form text responses. A Gen AI Specialist must generate three new columns from those text responses.

How should this requirement be fulfilled? (Choose two)

Options:

A.

Use the SNOWFLAKE.CORTEX.COMPLETE function specifying a RESPONSE_FORMAT in the options argument, and use dot notation to extract the data to put into the three new columns.

B.

Use the SNOWFLAKE.CORTEX.COMPLETE function specifying a TOP_P in the options argument, and parse the value of the CHOICES response key.

C.

Use the SNOWFLAKE.CORTEX.ENTITY_SENTIMENT function in a SELECT statement once for each of the three new columns.

D.

Call the SNOWFLAKE.CORTEX.EXTRACT_ANSWER function in a SELECT statement, and use dot notation to extract data to put into the three new columns.

E.

Call the SNOWFLAKE.CORTEX.EXTRACT_ANSWER function in a SELECT statement once for each of the three new columns.

Question 6

Which authentication methods are supported when accessing the Snowflake Cortex LLM REST API? (Choose two)

Options:

A.

SAML 2.0

B.

OAuth 2.0

C.

Single Sign-On (SSO)

D.

Key-pair authentication

E.

Multi-Factor Authentication (MFA)

Question 7

A Gen AI Specialist is creating metadata for Snowflake Cortex Analyst by creating a semantic model. The relationship between the PRODUCTS and PRODUCT_SALES tables is defined as:

```yaml

relationships:

- name: sales_to_products

join_type: left_outer

relationship_type: many_to_one

left_table: PRODUCT_SALES

relationship_columns:

- left_column: PRODUCT_ID

right_column: ID

right_table: PRODUCTS

```

Which join will Cortex Analyst generate in a query that uses this model?

```sql

Options:

A.

SELECT...

FROM PRODUCT_SALES AS S

LEFT OUTER JOIN PRODUCTS AS P

ON S.PRODUCT_ID = P.ID;

B.

SELECT...

FROM PRODUCT AS P

LEFT OUTER JOIN PRODUCT_SALES AS PS

ON PS.PRODUCT_SALES = P.PRODUCTS;

C.

SELECT...

FROM PRODUCT_SALES AS S

FULL OUTER JOIN PRODUCT AS P

ON S.PRODUCT_ID = P.ID;

D.

SELECT...

FROM PRODUCT_SALES AS S

FULL OUTER JOIN PRODUCT AS P

WHERE P.ID = S.PRODUCT_ID;

```

Question 8

How can costs that are directly associated with invoking the Snowflake Cortex COMPLETE function be minimized? (Choose two)

Options:

A.

Set max_tokens to limit the number of input tokens.

B.

Set max_tokens to limit the number of output tokens in the response.

C.

Reduce the size of the virtual warehouse used to run the function.

D.

Use an LLM that has more parameters than the current LLM being used.

E.

Use an LLM that has fewer parameters than the current LLM being used.

Question 9

A user opened the Snowflake Cortex LLM Playground in the AI & ML Studio within Snowsight, selected gemma-7b from the Standard models drop-down list, and typed "What is Gen AI?" into the dialog box.

Which SQL statement will achieve the same result?

Options:

A.

SELECT SNOWFLAKE.CORTEX.CLASSIFY_TEXT('gemma-7b', 'What is Gen AI?');

B.

SELECT SNOWFLAKE.CORTEX.COMPLETE('gemma-7b', 'What is Gen AI?');

C.

SELECT SNOWFLAKE.CORTEX.EXTRACT_ANSWER('gemma-7b', 'What is Gen AI?');

D.

SELECT SNOWFLAKE.CORTEX.SUMMARIZE('gemma-7b', 'What is Gen AI?');

Question 10

To submit a request to the Snowflake Cortex Analyst REST API endpoint, which fields are required in the body of the API request? (Choose three)

Options:

A.

Stream

B.

Content

C.

Request ID

D.

Suggestions

E.

Role of the speaker

F.

Path to the semantic model YAML file

Question 11

Which view in the ACCOUNT_USAGE schema can query token costs for Snowflake Cortex LLMs aggregated in one-hour increments?

Options:

A.

CORTEX_DOCUMENT_PROCESSING_USAGE_HISTORY

B.

CORTEX_FUNCTIONS_QUERY_USAGE_HISTORY

C.

CORTEX_FUNCTIONS_USAGE_HISTORY

D.

CORTEX_SEARCH_SERVING_USAGE_HISTORY

Question 12

Which key considerations apply when using the Snowflake Model Registry to manage models? (Choose two)

Options:

A.

Once a model is registered, it cannot be updated or deleted.

B.

Models need to be exported to external storage before they are registered.

C.

Models can be deployed and invoked directly using SQL commands in Snowflake.

D.

Models registered in the Model Registry can only be used with Snowpark for Python.

E.

The Model Registry supports versioning so that multiple versions of a model can be tracked.

Question 13

Which strategy should be used to reduce latency when using the SNOWFLAKE.CORTEX.COMPLETE function?

Options:

A.

Use the REST API when invoking inferences

B.

Use the SQL API when using a Snowpark session object

C.

Set the temperature parameter close to 1.

D.

Pass a JSON schema to the response_format parameter

Question 14

The following error is received while attempting to extract details from a document with Snowflake Document AI:

`Request failed for external function DOCUMENT_EXTRACT_FEATURES$V1 with remote service error: 422`

How should this error be resolved?

Options:

A.

Publish the model build.

B.

Reduce the number of documents in the query or extend the query expiration time.

C.

Recreate the internal stage specifying the SNOWFLAKE_SSE encryption type.

D.

Grant the CREATE SNOWFLAKE.ML.DOCUMENT_INTELLIGENCE privilege to the role running the extraction query.

Question 15

A Gen AI Specialist has deployed a base model as an LLM in a production environment for a proof of concept. The model is larger and more expensive than other base models.

How can the Specialist lower production costs without affecting performance for the limited tasks needed to support the proof of concept?

Options:

A.

Use Snowflake Cortex Search to limit the number of context documents.

B.

Use Snowflake Cortex Agents to ensure the base model is concise

C.

Use Snowflake Cortex Fine-tuning on a different base model

D.

Provide a semantic model to ensure the LLM is able to interpret the prompts

Question 16

Which SQL functions are designed and optimized to carry out and automate specific routine tasks within Snowflake Cortex? (Choose two)

Options:

A.

ANOMALY_DETECTION

B.

CLASSIFICATION

C.

FORECAST

D.

PARSE_DOCUMENT

E.

SENTIMENT

Question 17

How does Snowflake Cortex Analyst generate suggested questions? (Choose two)

Options:

A.

Cortex Analyst only returns questions that are guaranteed to return results.

B.

Onboarding questions flagged in the Verified Query Repository (VQR) are only shown if the user provides no input.

C.

When no Verified Query Repository (VQR) is present, Cortex Analyst uses the underlying LLMs to generate up to three suggested questions.

D.

When a Verified Query Repository (VQR) is defined, Cortex Analyst suggests up to five questions based on semantic similarity to the user's input.

E.

Cortex Analyst prioritizes queries in the Verified Query Repository (VQR) as suggestions based on the queries that reference the most-frequently used logical columns.

Question 18

This use case retrieves auto-part details from two data systems:

Datasource A:

Table Name - Parts_A

Columns Name - Parts_description, part_id

Datasource B:

Table Name - Parts_B

Columns Name - Parts_description, part_id

Code snippet

Which query compares the part descriptions across the two data sources?

```sql

Options:

A.

SELECT

B.

*,

VECTOR_INNER_PRODUCT(a.parts_description, b.parts_description) AS score

FROM Parts_A a, Parts_B b

WHERE a.part_id = b.part_id;

C.

SELECT

D.

*,

VECTOR_L1_DISTANCE(a.parts_description, b.parts_description) AS score

FROM Parts_A a, Parts_B b

WHERE a.part_id = b.part_id;

E.

SELECT

F.

*,

VECTOR_COSINE_SIMILARITY(a.parts_description, b.parts_description) AS score

FROM Parts_A a, Parts_B b

WHERE a.part_id = b.part_id;

G.

SELECT

Question 19

When creating a Snowflake Document AI model, which object must have the CREATE SNOWFLAKE.ML.DOCUMENT_INTELLIGENCE privilege?

Options:

A.

Virtual warehouse

B.

Database

C.

Schema

D.

Stage

Question 20

A Gen AI Specialist is writing a Python script that leverages Snowflake Cortex to answer users' questions. The script contains this code:

Python

from snowflake.cortex import CompleteOptions, complete

user_question = < 'Prompt that could generate an unsafe response' >

Regardless of the content of the prompt (user_question) that is passed to snowflake.cortex.complete, the Specialist must ensure that the function filters potentially unsafe or harmful response language.

Which code will accomplish this?

Python

Options:

A.

response = complete(

'llama3.1-70b',

[dict(role='user', content=user_question)],

options=CompleteOptions(temperature=1),

)

B.

response = complete(

'llama3.1-70b',

[dict(role='user', content=user_question)],

stream=False,

)

C.

response = complete(

'llama3.1-70b',

[dict(role='user', content=user_question)],

options=CompleteOptions(guardrails=True),

)

D.

response = complete(

'llama3.1-70b',

[dict(role='user', content=user_question)],

options=CompleteOptions(response_format='safe'),

)

Question 21

Which governance principles does Snowflake guarantee when its Gen AI features and the underlying models are used? (Choose two)

Options:

A.

Snowflake customer data is never made available to other customers or model developers.

B.

Snowflake enforces Role-Based Access Control (RBAC) to ensure appropriate model access.

C.

Snowflake allows customers to create fine-tuned models that can be shared with other customers.

D.

Snowflake only allows third-party models to access Snowflake accounts using the Snowflake Model Registry.

E.

Snowflake mandates the use of Cortex Guard in the Cortex COMPLETE function to filter unsafe responses from a model.

Question 22

Which Snowflake feature enables application integration to answer questions using structured data in Snowflake?

Options:

A.

Document AI

B.

Copilot

C.

Cortex Search

D.

Cortex Analyst

Question 23

A Gen AI Specialist needs to determine whether feedback from a recent survey was generally positive, negative, or neutral. The Specialist wants the assessment reported as either a floating-point number from –1 to +1 (inclusive) or an object with a categories field.

Which statements will produce the desired results? (Choose two)

Options:

A.

SNOWFLAKE.CORTEX.CLASSIFY_TEXT (SURVEY_TEXT)

B.

SNOWFLAKE.CORTEX.COMPLETE (SURVEY_TEXT)

C.

SNOWFLAKE.CORTEX.ENTITY_SENTIMENT (SURVEY_TEXT, [‘positive’, ‘negative’, ‘neutral'])

D.

SNOWFLAKE.CORTEX.FINETUNE (SURVEY_TEXT);

E.

SNOWFLAKE.CORTEX.SENTIMENT (SURVEY_TEXT)

Question 24

Which parameters in a SNOWFLAKE.CORTEX.COMPLETE function call can be adjusted to control the randomness and diversity of an LLM response? (Choose two)

Options:

A.

guardrails

B.

max_tokens

C.

response_format

D.

temperature

E.

top_p

Question 25

A Gen AI Specialist has one document on which they want to perform completions. The document is too large for the context window of SNOWFLAKE.CORTEX.COMPLETE.

In what order should the functions be applied to resolve the issue?

Options:

Page: 1 / 6
Total 85 questions