Course contents

SnowPro Core COF-C03 Study GuidePart 7: AI featuresAI_EXTRACT, Cortex Code & the ML Functions

AI_EXTRACT, Cortex Code & the ML Functions

AI_EXTRACT, Cortex Code & the ML Functions

AI_EXTRACT turns documents into columns. Safia's supplier invoices arrive as PDFs in a stage, and one function call pulls the fields she names, each as a plain-English question in the responseFormat argument (a JSON schema works too, for lists and tables):

SELECT relative_path,
       AI_EXTRACT(
         file => TO_FILE('@invoice_stage', relative_path),
         responseFormat => [['vendor',   'Who is the vendor?'],
                            ['amount',   'What is the total amount due?'],
                            ['due_date', 'What is the due date?']]) AS fields
FROM DIRECTORY(@invoice_stage);

The output is JSON per document, with your field names under response, and it lands in the semi-structured pipeline from Part 6: path notation, casts, FLATTEN. Notice the supporting cast, a directory table listing the files and TO_FILE handing each one to the function. AI_EXTRACT bills by tokens, with each page counted as a fixed number of tokens. Until March 2026 this job took a Document AI model build, trained on labeled examples in Snowsight and called with !PREDICT; Snowflake retired both. When you need a document's full text rather than named fields, for example to chunk it for Cortex Search, use AI_PARSE_DOCUMENT: OCR mode returns plain text, LAYOUT mode returns Markdown that keeps headings and tables.

Cortex Code (the docs also call it CoCo) replaced the deprecated Snowflake Copilot as the assistant built into Snowsight. Alice asks for "top 10 customers by revenue last quarter, exclude internal accounts"; it drafts the SQL, shows the change before she applies it, and can run it, explore objects, or work in notebooks and dbt projects. It's an agent, not just a drafter, and the guard rail is role-based access control: it only performs actions her active role permits. Her role needs SNOWFLAKE.CORTEX_USER or the narrower SNOWFLAKE.CORTEX_AGENT_USER. Universal Search is smaller: natural-language lookup across your objects, Marketplace listings, and documentation. It finds the table Marc mentioned; it doesn't query it.

The classic ML functions

Before LLMs, Snowflake shipped statistical ML as SQL, and it's still there under SNOWFLAKE.ML. You create a model object from historical data, then call it. Forecasting projects a time series forward, anomaly detection flags points that break the pattern, classification assigns labels from training examples. These train and predict on your warehouse, not on AI credits, which is the billing distinction to remember. Big training jobs can run out of memory on a standard warehouse: for anomaly detection on one series beyond about 5 million rows, Snowflake suggests a Snowpark-optimized warehouse, Part 2's memory rule.

-- Thomas forecasting daily order volume 14 days out
CREATE SNOWFLAKE.ML.FORECAST order_forecast(
  INPUT_DATA => TABLE(SELECT order_date, order_count FROM daily_orders),
  TIMESTAMP_COLNAME => 'order_date',
  TARGET_COLNAME => 'order_count');

CALL order_forecast!FORECAST(FORECASTING_PERIODS => 14);

Which AI tool do I reach for?

Pick the AI tool from the job. Seven jobs, each with the tool that does it and how it is billed: text in rows, AI functions; free-form generation, AI_COMPLETE; chat over documents, Cortex Search with AI_COMPLETE; questions on tables, Cortex Analyst; fields from PDFs, AI_EXTRACT, which replaces the retired Document AI; help writing SQL, Cortex Code, which replaced Copilot; forecasts and anomalies, the ML functions on a warehouse.THE JOBTHE TOOLBILLED ASScore, classify, translate textAI functionsAI_SENTIMENT, AI_CLASSIFY…tokens + warehouseWrite anything from a promptAI_COMPLETEyou pick the modeltokens + warehouseChat over company documentsCortex Search+ AI_COMPLETEGB-month + tokensPlain-language questions on tablesCortex Analystsemantic viewper message + warehousePull fields out of PDFsAI_EXTRACTreplaces Document AItokensHelp a person write SQLCortex Codeacts as your rolewarehouse when runForecast, spot anomaliesML functionsFORECAST, ANOMALY_DETECTIONwarehouse
THE JOBTHE TOOL

Score, classify, translate text

AI functionsAI_SENTIMENT, AI_CLASSIFY…BILLED AS tokens + warehouse

Write anything from a prompt

AI_COMPLETEyou pick the modelBILLED AS tokens + warehouse

Chat over company documents

Cortex Search+ AI_COMPLETEBILLED AS GB-month + tokens

Plain-language questions on tables

Cortex Analystsemantic viewBILLED AS per message + warehouse

Pull fields out of PDFs

AI_EXTRACTreplaces Document AIBILLED AS tokens

Help a person write SQL

Cortex Codeacts as your roleBILLED AS warehouse when run

Forecast, spot anomalies

ML functionsFORECAST, ANOMALY_DETECTIONBILLED AS warehouse

Figure 7.5 Name the job and the tool follows. The right column is what drives the bill.
Memory aid

Name the job and the tool follows. Text in a column: AI functions, one call per row (AI_AGG for a whole group). Passages from documents: Search. Numbers from tables in plain language: Analyst. Fields out of documents: AI_EXTRACT. Help writing SQL: Cortex Code. Forecasts and anomalies: ML functions. Finding objects: Universal Search. Every AI scenario question resolves to one of these sentences.