# Checklist: BigQuery AI/ML Methods

## Using LLM Features with BigQuery

{% embed url="<https://github.com/GoogleCloudPlatform/generative-ai/blob/main/open-models/use-cases/bigquery_ml_llama_inference.ipynb>" %}

## Usage Overview

<table><thead><tr><th width="343.39453125">Function Method</th><th>Input e.g. what is inserted in the function method</th><th width="113.62109375">Output</th><th>Notes on ways to use them in Gaby</th><th>Related Action<select multiple><option value="gCOZQsn0bHtE" label="data cleaning" color="blue"></option><option value="Z1v8Xw8RX4Ls" label="data analytics" color="blue"></option></select></th></tr></thead><tbody><tr><td><code>AI.GENERATE_TABLE</code> </td><td>Text inputs containing data of any form, Data table, Data fields to append</td><td>Data table</td><td><ul><li>Text Data Summary can be reinserted and a schema is built out of this method, can be used to verify consistency over text / object dataset during data cleaning stage</li></ul></td><td><span data-option="gCOZQsn0bHtE">data cleaning</span></td></tr><tr><td><code>AI.GENERATE_BOOL</code></td><td>Any prompt</td><td>Boolean Value</td><td><ul><li>Used to check if something exists or not in a column field, useful for cases for outlier detection.</li></ul></td><td><span data-option="gCOZQsn0bHtE">data cleaning, </span><span data-option="Z1v8Xw8RX4Ls">data analytics</span></td></tr><tr><td><code>AI_GENERAGE_DOUBLE</code></td><td>Any prompt</td><td>Extracts a double / float number from given prompt (and data column? hopefully this is true - to self-check)</td><td><ul><li>Outlier / Anomality detection</li></ul></td><td><span data-option="gCOZQsn0bHtE">data cleaning</span></td></tr><tr><td><code>AI.GENERATE_INT</code></td><td>Any prompt</td><td>Extracts an integer number from given prompt (and data column? hopefully this is true - to self-check)</td><td><ul><li>Outlier / Anomality detection</li></ul></td><td><span data-option="gCOZQsn0bHtE">data cleaning</span></td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://whoamimi.gitbook.io/blog/projects/readme-1/participated-competitions/bigquery-ai-building-the-future-of-data/checklist-bigquery-ai-ml-methods.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.