Black Friday VIP Hour Limited Time 75% Discount Offer - Ends in 0d 00h 00m 00s - Coupon code = simple75

Pass the Snowflake SnowPro Specialty GES-C02 Questions and answers with Dumpstech

Exam GES-C02 Premium Access

View all detail and faqs for the GES-C02 exam

Practice at least 50% of the questions to maximize your chances of passing.
Viewing page 1 out of 3 pages
Viewing questions 1-10 out of questions
Questions # 1:

A Gen AI Specialist is creating a semantic model for Snowflake Cortex Analyst and must supply details for every field. One field holds complex, high-cardinality data.

Which technique keeps the semantic model concise?

Options:

A.

Include custom_instructions to truncate the field.

B.

Reference the search optimization service on this field.

C.

Reference a Snowflake Cortex Search Service on this field.

D.

Reference a Snowflake Cortex Analyst Verified Query Repository (VQR) on this field

Questions # 2:

Which commands restrict access to Snowflake Cortex functions so that access is provided only to roles with explicitly granted privileges? (Choose two)

Options:

A.

REVOKE ROLE SNOWFLAKE.CORTEX_FUNCTIONS FROM ROLE PUBLIC;

B.

REVOKE ROLE SNOWFLAKE.CORTEX_USER FROM ROLE PUBLIC;

C.

REVOKE DATABASE ROLE SNOWFLAKE.CORTEX_USER FROM ROLE PUBLIC;

D.

REVOKE USAGE ON SCHEMA SNOWFLAKE.CORTEX FROM ROLE PUBLIC;

E.

REVOKE IMPORTED PRIVILEGES ON DATABASE SNOWFLAKE FROM ROLE PUBLIC;

Questions # 3:

Which action can minimize costs for Snowflake Cortex Search Services?

Options:

A.

Make frequent but small updates to the source data.

B.

Split the text search columns into chunks of no more than 612 tokens.

C.

Reduce the target lag from 5 minutes to 1 minute for real-time indexing.

D.

Suspend serving when it is not necessary to run the service.

Questions # 4:

What role do event tables serve in the Snowflake Cortex Analyst observability features?

Options:

A.

To archive historical versions of semantic models

B.

To generate and store user authentication logs

C.

To maintain a history of virtual warehouse performance metrics

D.

To log data about requests including questions asked and generated SQL

Questions # 5:

A Gen AI Specialist requires a solution that supports asking questions in natural language and receiving answers based on structured data in Snowflake without using SQL.

How can this be achieved? (Choose two)

Options:

A.

Create a custom data model, apply the data model to a database, and ask questions from the Snowflake Document AI option in the AI & ML Studio in Snowsight.

B.

Create a custom data model, enhance the model with cross-region inference, and ask questions in a custom-built application that calls the Snowflake Cortex Agent API.

C.

Create a semantic model, upload the semantic model to a stage, and ask questions from the Snowflake Cortex Analyst option in the AI & ML Studio in Snowsight.

D.

Create a semantic model, upload the semantic model to a stage, and ask questions in a custom-built application that calls the Snowflake Cortex Analyst API.

E.

Create a Snowflake Cortex Agent in Snowsight, extract data from the database, and ask questions by fine-tuning an LLM with the extracted data.

Questions # 6:

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'),

)

Questions # 7:

How does Snowflake Cortex Analyst enable multi-turn conversations while preserving context across user interactions?

Options:

A.

By storing previous interactions in a separate database

B.

By using a session-based memory feature to track user queries

C.

By passing full conversation histories to each LLM agent in the workflow

D.

By using a summarization agent to rewrite questions based on conversation histories

Questions # 8:

A Gen AI Specialist creates the following table:

SQL

CREATE TABLE vectors (a VECTOR(FLOAT, 3), b VECTOR(FLOAT, 3));INSERT INTO vectors SELECT [1.1,2.2,3]::VECTOR (FLOAT, 3), [1,1,1] ::VECTOR (FLOAT, 3);INSERT INTO vectors SELECT [1,2.2,3]::VECTOR(FLOAT, 3), [4,6,8] ::VECTOR(FLOAT, 3);

```

Which function measures the relationship between vectors without considering their magnitudes?

Options:

A.

VECTOR_L1_DISTANCE

B.

VECTOR_L2_DISTANCE

C.

VECTOR_INNER_PRODUCT

D.

VECTOR_COSINE_SIMILARITY

Questions # 9:

A Gen AI Specialist used the ACCOUNTADMIN role to invoke the ` < model_build_name > !PREDICT` method on a Document AI model build and received this error:

`{ "processingErrors": [ "File extension does not match actual mime type. Mime-Type: application/octet-stream" ] }`

What is the MOST LIKELY cause?

Options:

A.

The file URL has expired and must be regenerated.

B.

The documents that the query tried to process do not meet the Document AI requirements.

C.

The SNOWFLAKE_SSE encryption type was not specified when creating the internal stage that will be used to store the documents.

D.

The CREATE SNOWFLAKE.ML.DOCUMENT_INTELLIGENCE privilege was not granted to the ACCOUNTADMIN role.

Questions # 10:

When working with a multimodal model, what may the SNOWFLAKE.CORTEX.COMPLETE function be used for? (Choose two)

Options:

A.

Adding audio to images

B.

Labeling image files

C.

Completing fragmentary images

D.

Classifying landmarks in images

E.

Replacing extracted objects from images

Viewing page 1 out of 3 pages
Viewing questions 1-10 out of questions