{"id":805,"date":"2025-11-02T19:00:49","date_gmt":"2025-11-02T19:00:49","guid":{"rendered":"https:\/\/datadandies.nl\/?p=805"},"modified":"2025-11-02T19:01:21","modified_gmt":"2025-11-02T19:01:21","slug":"extract-insights-from-freeform-values-in-a-column-in-snowflake-using-snowflake-cortex-ai","status":"publish","type":"post","link":"https:\/\/datadandies.nl\/index.php\/2025\/11\/02\/extract-insights-from-freeform-values-in-a-column-in-snowflake-using-snowflake-cortex-ai\/","title":{"rendered":"Extract insights from freeform values in a column in Snowflake using Snowflake Cortex AI"},"content":{"rendered":"\n

Ever wanted to extract insights from freeform values in a table?<\/p>\n\n\n\n

Snowflake AI might be able to assist with that. Snowflake Cortex is a part of the AI features in Snowflake.<\/p>\n\n\n\n

Snowflake Cortex according to the documentation is…<\/p>\n\n\n\n

\u201c… <\/strong>a suite of AI features that use large language models (LLMs) to understand unstructured data, answer freeform questions, and provide intelligent assistance.\u201d<\/p>\n\n\n\n

Several interesting functions are present in a notebook that has been created by Snowflake as a demo-notebook:<\/p>\n\n\n\n

SNOWFLAKE.CORTEX.SENTIMENT( FREE_FORM_COLUMN )<\/p>\n\n\n\n

SNOWFLAKE.CORTEX.SUMMARIZE( FREE_FORM_COLUMN )<\/p>\n\n\n\n

SNOWFLAKE.CORTEX.AI_CLASSIFY( FREE_FORM_COLUMN, [‘category1’, ‘category2’] )<\/p>\n\n\n\n

See the screenshot below for an example of how these functions work.<\/p>\n\n\n\n

The demo notebook is called \u201cAnalyze sentiment in unstructured data\u201d and again, I did not create it. Snowflake did, and it should be available to you in your account. Are you using these functions and if so, for what purpose?<\/p>\n\n\n\n

\n
\"\"<\/figure>\n<\/figure>\n\n\n\n
SQL<\/span><\/span><\/path><\/path><\/svg><\/span>
SELECT<\/span> <\/span><\/span>\n  REVIEW_ID,<\/span><\/span>\n  REVIEW,<\/span><\/span>\n  <\/span>LEN<\/span>(REVIEW) <\/span>AS<\/span> LENTH_REVIEW, <\/span>-- Length of the review.<\/span><\/span>\n  SNOWFLAKE.CORTEX.SUMMARIZE(REVIEW) <\/span>AS<\/span> SUMMARY, <\/span>-- Summary of the review.<\/span><\/span>\n  <\/span>LEN<\/span>(SUMMARY) <\/span>AS<\/span> LEN_SUMMARY, <\/span>-- Length of the summary of the review. Still quite long, apparently this function is not a a fan of one-liners. Should take lessons from Arnold. <\/span><\/span>\n  SNOWFLAKE.CORTEX.SENTIMENT(REVIEW) <\/span>AS<\/span> SENTIMENT, <\/span>-- Extracts the sentiment of this review<\/span><\/span>\n  SNOWFLAKE.CORTEX.AI_CLASSIFY(REVIEW, ['negative', 'positive']) <\/span>AS<\/span> CATEGORY_RAW, <\/span>-- Classify a review with either the category 'negative' or 'positive'. Raw value from the function.<\/span><\/span>\n  <\/span>REPLACE<\/span>(SNOWFLAKE.CORTEX.AI_CLASSIFY(REVIEW, ['negative', 'positive']):labels[0], <\/span>'"'<\/span>) <\/span>AS<\/span> CATEGORY <\/span>-- Classify a review with either the category 'negative' or 'positive'.<\/span><\/span>\nFROM<\/span> TRUCK_REVIEWS<\/span><\/span>\nLIMIT<\/span> <\/span>15<\/span>;<\/span><\/span><\/code><\/pre>SQL<\/span><\/div>\n","protected":false},"excerpt":{"rendered":"
Ever wanted to extract insights from freeform values in a table? Snowflake AI might be able to assist with that. Snowflake Cortex is a part of the AI features in Snowflake. Snowflake Cortex according to the documentation is… \u201c… a suite of AI features that use large language models (LLMs) to understand unstructured data, answer…<\/p>\n
Read More<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[65,40],"class_list":["post-805","post","type-post","status-publish","format-standard","hentry","category-blog","tag-ai","tag-snowflake"],"_links":{"self":[{"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/posts\/805","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/comments?post=805"}],"version-history":[{"count":2,"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/posts\/805\/revisions"}],"predecessor-version":[{"id":808,"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/posts\/805\/revisions\/808"}],"wp:attachment":[{"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/media?parent=805"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/categories?post=805"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datadandies.nl\/index.php\/wp-json\/wp\/v2\/tags?post=805"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}