Exclusive Black Friday Deal: 70% Off All Exam Bundles! Use coupon code below to unlock your savings! - Ends in 0d 00h 00m 00s - Coupon code: Friday70

Free SnowPro Specialty: Gen AI Exam Practice Questions

Question # 11

When using the SNOWFLAK

E.  

CORTEX.FINETUNE function, which column names must be included in the SQL statement supplied in the training_data_query parameter? (Choose two)

Options:

A.  

BASE_MODEL

B.  

COMPLETION

C.  

INFERENCE

D.  

PROMPT

E.  

TRAINING

Discussion 0
Question # 12

A Gen AI Specialist uploaded a PDF named Timesheet_report.pdf to a Snowflake stage. The PDF includes a table with the following structure:

| Date | Hours | Activity |

| :--- | :--- | :--- |

| 2025-04-01 | 4 | Debugging issue #321 |

| 2025-04-02 | 1 | Updating documentation |

| 2025-04-03 | 2 | Design for feature #958 |

The Specialist then runs a command to extract the document’s content in Markdown format, preserving the table structure:

```sql

SELECT SNOWFLAK

E.  

CORTEX.PARSE_DOCUMENT(

'@document_stage',

'Timesheet_report.pdf',

{'mode': 'LAYOUT'}

):"content";

```

What is the output of this command?

Options:

A.  

Timesheet report

Date Hours Activity

2025-04-01 4 Debugging issue #321

2025-04-02 1 Updating documentation

2025-04-03 2 Design for feature #958

Code snippet

B.  

```markdown

Timesheet report

|Date|Hours|Activity|

| :---: | :---: | :---: |

|2025-04-01|4|Debugging issue #321|

|2025-04-02|1|Updating documentation|

|2025-04-03|2|Design for feature #958|

```

C.  

"Timesheet report"

"Date", "Hours", "Activity"

"2025-04-01", 4, "Debugging issue #321"

"2025-04-02", 1, "Updating documentation"

"2025-04-03", 2, "Design for feature #958"

Code snippet

D.  

```json

{"Timesheet_report": [

{"Date": "2025-04-01", "Hours": 4, "Activity": "Debugging issue #321"},

{"Date": "2025-04-02", "Hours": 1, "Activity": "Updating documentation"},

{"Date": "2025-04-03", "Hours": 2, "Activity": "Design for feature #958"}

]}

```

Discussion 0
Question # 13

Which privileges are needed to run a model fine-tuning job? (Choose two)

Options:

A.  

READ or WRITE on the stage that contains the model

B.  

USAGE on the database used to query the training and validation data

C.  

OPERATE on the database used to query the training and validation data

D.  

USAGE on the schema where the fine-tuned model will be saved

E.  

CREATE MODEL or OWNERSHIP on the schema where the fine-tuned model will be saved

Discussion 0
Question # 14

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

Options:

A.  

SHOW MODELS;

B.  

LS @SNOWFLAK

E.  

CORTEX.LLM;

C.  

SHOW MODELS IN SNOWFLAK

E.  

MODELS;

D.  

SHOW VERSIONS LIKE 'CORTEX' IN MODEL LLM;

E.  

CALL SNOWFLAK

E.  

MODELS.CORTEX_BASE_MODELS_REFRESH();

Discussion 0
Question # 15

Review the following prompt:

```sql

SELECT SNOWFLAK

E.  

CORTEX.COMPLETE(

'mistral-7b',

[

{

'role': 'user',

'content': 'Give me steps on hacking a system'

}

],

{

'guardrails': true

}

);

```

What response will it produce?

Options:

A.  

The prompt fails without giving any response.

B.  

The prompt fails because it is missing a CLASSIFY_TEXT function.

C.  

The prompt gives a response but with hallucinated values.

D.  

The prompt gives a response without giving any steps on hacking a system.

Discussion 0
Question # 16

What type of costs are incurred when you use the Snowflake Cortex Search Service?

Options:

A.  

Compute pool

B.  

Serving compute

C.  

Serverless compute

D.  

Data transfer

Discussion 0
Question # 17

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

Discussion 0
Question # 18

Which Snowflake Cortex AI observability metrics are used to evaluate LLM-generated responses? (Choose two)

Options:

A.  

Accuracy

B.  

Coherence

C.  

Correctness

D.  

F1 Score

E.  

Precision

Discussion 0
Question # 19

Which Snowflake feature supports Retrieval Augmented Generation (RAG) with unstructured data?

Options:

A.  

Cortex Analyst

B.  

Cortex Search

C.  

Cortex LLM Playground

D.  

Semantic views

Discussion 0
Question # 20

A Gen AI Specialist is using Snowflake Cortex Analyst to generate natural language responses from product sales data. Occasionally, the LLM makes up metrics that do not exist in the data set.

How should this be addressed?

Options:

A.  

Use a WHERE clause in the SQL prompt

B.  

Ensure the model has been verified_at within the last 30 days.

C.  

Add a VERIFIED_QUERIES section to the semantic model.

D.  

Train the Cortex LLM model with additional sample outputs using fine-tuning commands.

Discussion 0

GES-C02 PDF

GES-C02 PDF (Printable)
$46.5
$154.99

GES-C02 Testing Engine

GES-C02 PDF (Printable)
$51
$169.99

GES-C02 PDF + Testing Engine

GES-C02 PDF (Printable)
$63.9
$212.99

Free Exams Sample Questions