個人を特定できる情報（ PII ）を編集する¶

SELECT AI_REDACT(
    input => 'My name is John Smith and I live at twenty third street, San Francisco.'
);

SELECT AI_REDACT(
    input => 'My name is John and I live at twenty third street, San Francisco.',
    categories => ['NAME', 'EMAIL']
);

-- Create a table with unredacted text
CREATE OR REPLACE TABLE raw_table AS
  SELECT 'My previous manager, Washington, used to live in Kirkland. His first name was Mike.' AS my_column
  UNION ALL
  SELECT 'My name is William and I live in San Francisco. You can reach me at (415).450.0973';

-- view unredacted data
SELECT * FROM raw_table;

-- Create a redaction table
CREATE OR REPLACE TABLE redaction_table (
  value VARCHAR
);

-- Redact PII from raw_table and insert into redaction_table
INSERT INTO redaction_table
SELECT AI_REDACT(my_column) AS value FROM raw_table;

-- view redacted results
SELECT * FROM redaction_table;

-- Run AI_SENTIMENT on redacted text
SELECT
    value AS redacted_text,
    AI_SENTIMENT(value) AS summary_sentiment
FROM redaction_table;

ALTER SESSION SET AI_SQL_ERROR_HANDLING_USE_FAIL_ON_ERROR=FALSE;

-- Create a redaction table with columns for value and error message
CREATE OR REPLACE TABLE redaction_table (
  value VARCHAR,
  error VARCHAR
);

-- Redact PII from raw_table and insert into redaction_table
-- Both the redacted text and any error message are stored
INSERT INTO redaction_table
SELECT
  result:value::STRING AS value,
  result:error::STRING AS error
  FROM (SELECT AI_REDACT(my_column, TRUE) AS result FROM raw_table);

CREATE OR REPLACE TABLE patients (
    patient_id INT PRIMARY KEY,
    patient_notes text
);

CREATE OR REPLACE TABLE final_temp_table AS
WITH chunked_data AS (
    -- Step 1: Split text into chunks
    SELECT
        patient_id,
        chunk.value AS chunk_text,
        chunk.index AS chunk_index
    FROM
        patients,
        LATERAL FLATTEN(
            input => SNOWFLAKE.CORTEX.SPLIT_TEXT_RECURSIVE_CHARACTER(
                patient_notes,
                'none',
                1000
            )
        ) AS chunk
    WHERE
        patient_notes IS NOT NULL
        AND LENGTH(patient_notes) > 0
),
redacted_chunks AS (
    -- Step 2: Apply AI_REDACT to each chunk
  SELECT
  patient_id,
        chunk_index,
        chunk_text,
        TO_VARIANT(results:value) AS redacted_chunk,
        TO_VARIANT(results:error) AS error_string
        from (
    SELECT
        patient_id,
        chunk_index,
        chunk_text,
        AI_REDACT(chunk_text,TRUE) AS results
    FROM
        chunked_data
)
),

-- Step 3: Concatenate redacted chunks
final AS (
SELECT
chunk_text as original,
IFF(error_string IS NOT NULL, chunk_text, redacted_chunk) AS redacted_text,
patient_id,
chunk_index
FROM
    redacted_chunks
)
SELECT * FROM final;

SELECT
  patient_id,
  LISTAGG(redacted_text, '') WITHIN GROUP (ORDER BY chunk_index) AS full_output
  FROM final_temp_table
  GROUP BY patient_id;