From 157f40851d406bfdc69de588c77579a29f40c07a Mon Sep 17 00:00:00 2001 From: Shirley Cohen Date: Wed, 30 Aug 2023 11:59:51 -0500 Subject: [PATCH] reworded intro --- apps/query_cookbook/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apps/query_cookbook/README.md b/apps/query_cookbook/README.md index 3b66fd2..bf26f2f 100644 --- a/apps/query_cookbook/README.md +++ b/apps/query_cookbook/README.md @@ -1,6 +1,6 @@ ## Query Cookbook Workflow -This folder contains a workflow that produces metadata tags in Data Catalog which contain access patterns for data assets in BigQuery. The workflow calls the ML.GENERATE_TEXT function in BigQuery, which uses the Vertex AI text-bison large language model (LLM) for inferences. More details on the ML.GENERATE_TEXT function are available in the [product documentation](https://cloud.google.com/bigquery/docs/generate-text). +This folder contains a workflow computes access patterns for data assets in BigQuery and produces metadata tags in Data Catalog with the results. The workflow calls the `ML.GENERATE_TEXT` function in BigQuery, which uses the Vertex AI text-bison large language model (LLM) for inferences. More details on `ML.GENERATE_TEXT` are available in the [product documentation](https://cloud.google.com/bigquery/docs/generate-text). For each table or view in BigQuery, the Query Cookbook workflow computes a metadata tag with these fields: 1) `top_users`: Most active users who have queried this data asset