Snowflake Architecture · Topic 10 of 18

AI/ML Pipelines, Snowflake ML Functions and Cortex LLM Functions

Design a basic AI/ML pipeline on Snowflake and choose between Snowflake ML functions, Cortex LLM functions, Snowpark and containers for each stage.

  • 5 min
In a nutshell
  • Pipeline: ingest, prepare, model, serve, all inside Snowflake governance.
  • Snowflake ML functions: forecasting, anomaly detection, classification, top insights. You call them with SQL and do not choose an algorithm.
  • Cortex LLM functions work on text, documents and audio: AI_COMPLETE, AI_CLASSIFY, AI_SENTIMENT, AI_SUMMARIZE, AI_EXTRACT, AI_TRANSLATE.

What it is

An AI/ML pipeline on Snowflake moves data through four stages: ingest, prepare, build or call a model, and serve the result. The exam gives you a business need such as "forecast daily sales", "classify support tickets" or "summarize call notes" and asks which Snowflake feature fits with the least effort and the least data movement.

The architect's rule is simple. Use the most managed option that meets the requirement, and move to custom code or containers only when a managed function cannot do the job. All the options keep data inside Snowflake governance, so roles, masking and row access policies still apply.

IngestSnowpipe or Snowpipe StreaminglandPreparedynamic tables or SnowparkfeedModelML functions, Cortex or customscoreServetable, Streamlit or Native App

How it works

Pipeline stages and the feature for each

StageTypical Snowflake featureWhy
IngestSnowpipe, Snowpipe Streaming, COPYFiles or rows arrive without a warehouse you manage
PrepareDynamic tables, streams and tasks, SnowparkKeep features fresh with declarative or code based transforms
Build a modelSnowflake ML (Model Registry, Feature Store), Snowpark, Snowpark Container Services for GPUs or custom stacksTrain and register models next to the data
Use a modelSnowflake ML functions, Cortex functions, model inference in SQLA function call replaces a model server
ServeTables and views, Streamlit in Snowflake, Snowflake Native App FrameworkShare results with people, apps or other accounts

A basic pipeline needs no external system. Data lands in a table, a dynamic table or task prepares it, a function scores it, and the result is written to a table that a dashboard or Streamlit app reads.

Snowflake ML functions

Snowflake ML functions are built in, SQL callable machine learning for common analytics. You do not choose an algorithm or write training code.

FunctionWhat it doesNeeds time series?
ForecastingPredicts future values of a metric from past trendsYes
Anomaly detectionFlags metric values that differ from what is expectedYes
ClassificationSorts rows into two or more classes from their most predictive featuresNo
Top insightsFinds dimensions and values that move a metric in unexpected waysNo

You train a model object with a CREATE statement (for example a forecast model over a table or view) and then call its method, such as FORECAST, using the model name. Training and prediction use compute you pay for, and each trained model instance uses storage, so delete models you no longer need.

CREATE SNOWFLAKE.ML.FORECAST sales_fc(
  INPUT_DATA => TABLE(SELECT day, revenue FROM daily_sales),
  TIMESTAMP_COLNAME => 'DAY',
  TARGET_COLNAME => 'REVENUE');
CALL sales_fc!FORECAST(FORECASTING_PERIODS => 14);
Exam tip

If the question says "no data science team", "SQL only" and "forecast" or "detect anomalies in a metric", the answer is a Snowflake ML function, not a custom model on a container.

Cortex LLM functions

Snowflake Cortex runs large language models inside Snowflake, so prompts and data stay on the platform. The task specific functions are called from SQL like any other function, and Snowflake manages the models and the GPUs.

NeedFunction
Free form prompt, chat, structured JSON outputAI_COMPLETE (older name COMPLETE)
Label text or files with categories you provideAI_CLASSIFY
Sentiment of textAI_SENTIMENT
Summarize one text or many rowsAI_SUMMARIZE, AI_SUMMARIZE_AGG
Pull values or answers out of text or documentsAI_EXTRACT, AI_PARSE_DOCUMENT
Translate or transcribeAI_TRANSLATE, AI_TRANSCRIBE
Filter or aggregate rows by natural languageAI_FILTER, AI_AGG
Embeddings and similarity for searchAI_EMBED, AI_SIMILARITY

These are the Cortex AISQL functions. Some individual functions are Preview Features, so check the status of a function before relying on it in production.

SELECT ticket_id,
       AI_CLASSIFY(body, ['billing', 'outage', 'how to']):labels[0]::STRING AS category,
       AI_SUMMARIZE(body) AS summary
FROM support_tickets;

Access is controlled with privileges. Your role needs the USE AI FUNCTIONS account privilege and the CORTEX_USER database role (or the AI_FUNCTIONS_USER database role). Cortex functions are billed by the amount of text processed, counted in tokens, so long prompts and long rows cost more.

Choosing between the options

Requirementmetric forecast or anomalyuseSnowflake ML functionRequirementtext task: classify, summarize, extractuseCortex functionRequirementcustom model, GPU or own codeuseSnowpark Container Servicesor Snowflake ML training

Cortex also includes services built on these models, such as Cortex Search for retrieval and Cortex Analyst for natural language questions over structured data. They sit in the use and serve stages of a pipeline.

Common mistakes

Building a container for a job a function does. If a built in function covers sentiment, summary or forecast, a custom service adds cost and operations for no gain.

Forgetting the privileges. A role without USE AI FUNCTIONS and the CORTEX_USER database role cannot call the Cortex functions, even with access to the data.

Treating ML functions and Cortex LLM functions as the same thing. ML functions work on numeric metrics and tabular features. Cortex LLM functions work on text, documents and audio.

Ignoring cost drivers. Calling an LLM function on every row of a very large table on every refresh is expensive. Run it on new rows only, for example from a stream.

What to remember for the exam

  • Pipeline: ingest, prepare, model, serve, all inside Snowflake governance.
  • Snowflake ML functions: forecasting, anomaly detection, classification, top insights. You call them with SQL and do not choose an algorithm.
  • Cortex LLM functions work on text, documents and audio: AI_COMPLETE, AI_CLASSIFY, AI_SENTIMENT, AI_SUMMARIZE, AI_EXTRACT, AI_TRANSLATE.
  • Access needs USE AI FUNCTIONS plus the CORTEX_USER or AI_FUNCTIONS_USER database role.
  • Most managed option first; containers or custom Snowpark code only for needs functions cannot meet.

Check yourself

  • A team with only SQL skills must forecast weekly demand per region. What do they use?

    The Snowflake ML forecasting function, trained on a table or view with a timestamp and a target column.

  • An Architect must tag thousands of support emails as billing, outage or how to without leaving Snowflake. Which feature?

    A Cortex function such as AI_CLASSIFY, called in SQL with the category list.

  • A role gets an authorization error when calling a Cortex function on data it can read. What is missing?

    The USE AI FUNCTIONS privilege or the CORTEX_USER (or AI_FUNCTIONS_USER) database role.

Topic 10 of 18 in Snowflake Architecture

Test yourself on Snowflake Architecture

The full Snowflake ARA-C01 question bank has 687 questions, with timed practice exams and an explanation for every answer.

This study guide is independent and is not affiliated with, endorsed by, or sponsored by Snowflake. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.