AI Generate Table

BigQuery now integrates with Vertex AI and Gemini 2.5 Pro/Flash models to extract structured insights from unstructured data like text, images, audio, and video

[{"selector":"#anim-b77c5105-f4d8-4f61-90b3-eedc0b3923c4 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-953bf8ab-1f79-4c98-ae48-25a0361291ba","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-9ba7983e-0c32-44e0-97b3-34d7a488e154","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

Google Cloud’s new AI.GENERATE_TABLE() function in BigQuery automates transforming unstructured data into structured tables using AI models

[{"selector":"#anim-6996f853-c6e4-4a1d-bcf2-2b9bfda2779d [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-bbfe4282-d221-4af4-aa49-9fb580018a84","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-54c08e53-69e5-44c3-9c76-7dfff31abf6f","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

The function works with a prompt and a defined output schema, ensuring the results are consistent and compatible with BigQuery tools

[{"selector":"#anim-22d07ead-56e2-4751-b1c0-ef48ae1d1704 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-4170304f-19f7-4f28-ad00-423927b59381","keyframes":{"transform":["rotate(-540deg) scale(0.1)","none"],"opacity":[0,1]},"delay":0,"duration":1000,"fill":"both","iterations":1}]

You can analyze a wide range of data types, including documents, photos, videos, and medical transcriptions, using this approach

[{"selector":"#anim-51f1d7b7-90cf-48a9-af95-911b32342943 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-18dc05ff-058c-49c7-a649-e989fe8d016e","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-b924ea21-5cee-4b92-8c78-364abc0e97f6","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

To use AI.GENERATE_TABLE(), first create an external table in BigQuery that references your unstructured data (e.g., images in a Cloud Storage bucket)

[{"selector":"#anim-a55ae4a0-0e64-4c58-99bb-5be98b60b239 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-4a7d55a3-8989-4751-bb70-2ca8eef492e3","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-f9cf8731-d3b4-43e8-85b3-257625eda0f6","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

The output schema is defined in SQL, specifying the fields and data types you want to extract (e.g., city_name STRING, state STRING, attractions ARRAY<STRING>)

[{"selector":"#anim-32a8dd8d-d504-46e2-9902-c0fd989ef34f [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-1d2413cb-e5a9-40d3-8d49-88e366e58223","keyframes":{"transform":["translate3d(-115.55555%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-c9bdea85-4c82-40f2-b19e-084cc84b1b50","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-0f75b705-8097-43e0-a794-faa04ed51239","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

The function can extract detailed information from images, such as city names, states, histories, and tourist attractions, or return nothing if the image is not relevant

[{"selector":"#anim-0c04bbf9-aea5-4de1-bd8e-2584eaeb5f61 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(12.514648210040342%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-f59e02d7-cb88-46db-8a4d-ea47ed043e25","keyframes":{"transform":["translate3d(-115.2381%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-fcf2299d-54cc-47ec-b533-b65f58c991dd","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-debdf284-2230-44a2-841f-e10ec07bf014","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

For more details visit Govindhtech.com

[{"selector":"#anim-fa59320c-2afb-46d2-80cf-11116e13ba27 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(0%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]