How does Snowflake Cortex Analyst support multi-turn conversations to maintain context across user interactions?
ABy storing previous interactions in a separate database
BBy using a session-based memory feature to track user queries
CBy passing full conversation histories to each LLM agent in the workflow
DBy using a summarization agent to rewrite questions based on conversation histories
A Gen AI Specialist needs to prepare lengthy documents for LLM ingestion.
Which Snowflake Cortex function will support this requirement by returning an array of text chunks?
AEMBED_TEXT_768
BFINETUNE
CPARSE_DOCUMENT
DSPLIT_TEXT_RECURSIVE_CHARACTER
Which Snowflake Cortex feature or function supports the ability of users to ask questions in natural language and receive direct responses without the need to write SQL code?
ACortex Search
BCortex Analyst
CThe Cortex CLASSIFY_TEXT function
DThe Cortex PARSE_DOCUMENT function
What governance principles does Snowflake guarantee when using its Gen AI features and the underlying models? (Choose two.)
ASnowflake customer data is never made available to other customers or model developers.
BSnowflake enforces Role-Based Access Control (RBAC) o ensure appropriate model access.
CSnowflake allows customers to create fine-tuned models that can be shared with other customers.
DSnowflake only allows third-party models to access Snowflake accounts using the Snowflake Model Registry.
ESnowflake mandates the use of Cortex Guard in the Cortex COMPLETE function to filter unsafe responses from a model.
Which commands will restrict access to Snowflake Cortex functions providing access only to roles that have been explicitly-granted privileges? (Choose two.)
AREVOKE ROLE SNOWELAKE.CORTEX_FUNCTIONS FROM ROLE PUBLIC;
BREVOKE ROLE SNOWFLAKE.CORTEX_USER FROM ROLE PUBLIC;
CREVOKE DATABASE ROLE SNOWFLAKE.CORTEX_USER FROM ROLE PUBLIC;
DREVOKE USAGE ON SCHENA SNOWFLAKE.CORTEX FROM ROLE PUBLIC;
EREVOKE IMPORTED PRIVILEGES ON DATABASE SNOWFLAKE FROM ROLE PUBLIC;
Which function is used to calculate the Manhattan distance between the two points in a vector space?
AVECTOR_INNER_PRODUCT
BVECTOR_L1_DISTANCE
CVECTOR_L2_DISTANCE
DVECTOR_COSINE_SIMILARITY
Which workflow should be used to perform data analysis on unstructured documents using Snowflake Cortex AI features, including Retrieval-Augmented Generation (RAG)?
A
Use EMBED_TEXT_768 to extract text from documents.2. Apply SUMMARTZE directly to the PDF files.3. Use TRANSLATE to retrieve the data.
B
Use SENTIMENT on binary files.2. Apply TRANSLATE to generate embedding vectors.3. Use CLASSIFY_TEXT to extract layout information from the PDF files.
C
Use COMPLETE to summarize documents directly from external URLs.2. Use COUNT_TOKENS to validate the output size.3. Store the output in a text file.
D
Use PARSE_DOCUMENT to extract text from documents.2. Store and vectorize the content using EMBED_TEXT_7683. Retrieve data using vector similarity, then use COMPLETE to analyze the data.
What cost categories are incurred by the Cortex Search Services and are tracked in the CORTEX_SEARCH_DAILY_USAGE_HISTORY view? (Choose two.)
AServing compute
BCloud services compute
CVirtual warehouse compute
DTOKEN_CREDITS
EEMBED_TEXT_TOKENS
Which object must have the CREATE SNOWFLAKE.ML.DOCUMENT_INTELLIGENCE privilege when building a Snowflake Document AI model?
AVirtual warehouse
BDatabase
CSchema
DStage
A Snowflake ACCOUNTADMIN needs to limit LLM usage by granting access only to individual roles. To do this, they disabled LLM usage for all models in the account.
Which commands will enable the GENAI_DEVELOPER role to use the COMPLETE function with the llama3.1–70b model?
A
B
C
D
Which proprietary LLM is used by Snowflake Document AI?
AArctic-TILT
Bdeepseek-rl
Cjamba-instruct
Dmistral-large2
Which Snowflake feature allows application integration for answering questions using structured data within Snowflake?
ADocument AI
BCopilot
CCortex Search
DCortex Analyst
Which parameters can be tuned in a SNOWFLAKE.CORTEX.COMPLETE function call to control for the randomness and diversity of an LLM response? (Choose two.)
Aguardrails
Bmax_tokens
Cresponse_format
Dtemperature
Etop_p
Use of which Snowflake feature will simplify the generation of vector embeddings and the calculation of vector similarities, thereby reducing the number of retrieval steps required in Retrieval Augmented Generation (RAG) pipelines?
ACortex Analyst
BCortex Search
CCortex Fine-tuning
DCortex COMPLETE function
How can the costs directly associated with calling the Snowflake Cortex COMPLETE function be minimized? (Choose two.)
ASet max_tokens to limit the number of input tokens.
BSet max_tokens to limit the number of output tokens in the response.
CReduce the size of the virtual warehouse used to run the function.
DUse an LLM that has more parameters than the current LLM being used.
EUse an LLM that has fewer parameters than the current LLM being used.
Which key factors should be considered when using the Snowflake Model Registry to manage models? (Choose two.)
AOnce a model is registered, it cannot be updated or deleted.
BModels need to be exported to external storage before they are registered.
CModels can be deployed and invoked directly using SQL commands in Snowflake.
DModels registered in the Model Registry can only be used with Snowpark for Python.
EThe Model Registry supports versioning so that multiple versions of a model can be tracked.
How are suggested questions generated in Snowflake Cortex Analyst? (Choose two.)
ACortex Analyst only returns questions that are guaranteed to return results.
BOnboarding questions flagged in the Verified Query Repository (VQR) are only shown if the user provides no input.
CWhen no Verified Query Repository (VQR) is present, Cortex Analyst uses the underlying LLMs to generate up to three suggested questions.
DWhen a Verified Query Repository (VQR) is defined, Cortex Analyst suggests up to five questions based on semantic similarity to the user's input.
ECortex Analyst prioritizes queries in the Verified Query Repository (VQR) as suggestions based on the queries that reference the most-frequently used logical columns.
Which Snowflake Gen AI feature or service offers connectivity through an exposed REST API?
ACopilot
BCortex LLM Playground
CA SNOWFLAKE.CORTEX.COMPLETE SQL function
DA snowflake.cortex.complete Python function
A Gen AI Specialist is building an internal chatbot for a company that will use Streamlit and Snowflake Cortex Analyst to interpret and respond to user queries against Snowflake data.
Team members need to be able to ask a question like:
Can you provide the sales trend for the last 6 months?
The tool needs to be able to answer follow-up questions like:
Can you break that down by region?
What factors contributed to the dip in February?
To ensure the tool interprets the follow-up questions correctly, what must be included in the API request to Cortex Analyst?
AThe most recent user message
BA session token to maintain session state across API requests
CThe entire conversation history in the messages field of the API request
DA Snowflake session parameter to maintain conversation context among the previous API requests
Which action will minimize costs for Snowflake Cortex Search Services?
AMake frequent but small updates to the source data.
BSplit the text search columns into chunks of no more than 612 tokens.
CReduce the target tag from 5 minutes to 1 minute for real-time indexing.
DSuspend serving when it is not necessary to run the service.
A table in pipeline contains a VARCHAR column containing free-form text responses. A Ger AI Specialist needs to generate three new columns from the text responses.
How should this requirement be met? (Choose two.)
AUse 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 tree new columns.
BUse the SNOWFLAKE.CORTEX.COMPLETE function specifying a TOP_P in the options argument. and parse the value of the CHOICES response key.
CUse the SNOWFLAKE.CORTEX.ENTITY_SENTIMENT function in a SELECT statement once for each of the three new columns.
DCall the SNOWFLAKE.CORTEX.EXTRACT_ANSWER function in a SELECT statement, and use dot notation to extract data to put into the three new columns,
ECall the SNOWFLAKE.CORTEX.EXTRACT_ANSWER function in a SELECT statement once for each of the three new columns.
This command is executed:
This error is received:
What is causing this error?
AThe temperature option cannot be used with the guardrails option,
BThe options argument must be the second parameter in the function call
CThe max_tokens option must be included when using the guardrails option.
DThe prompt_or_history argument must be an array of objects when using the options argument.
Which arguments are required when using the SNOWFLAKE.CORTEX.COMPLETE function? (Choose two.)
Amodel
Btop_p
Cresponse_format
Dmax_tokens
Eprompt_or_history
Review this query:
SELECT DEMO_DB.DEMO_SCHEMA.EXM_DOC_AI_BUILD!PREDICT(
GET_PRESIGNED_URL(@<stage_name>, '<relative_file_path>'), 9);
What will be the output?
AThe query will produce structured data from a document stored in a Snowflake internal stage using Document AI with a model-version identifier
BThe query will produce structured data from a document stored in a Snowflake external stage using Document AI with a model-version identifier
CThe query will produce semi-structured data from a document stored in a Snowflake internal stage using Document AI with a model-version identifier
DThe query will produce semi-structured data from a document stored in a Snowflake external stage using Document AI with a model version identifier
A Gen AI Specialist creates this table:
Which function will measure the relationship between vectors without considering their magnitudes?