# Generative AI

Components to leverage native Generative AI capabilities on Data Warehouses.

## ML Generate Text

**Description**

This components calls [`ML.GENERATE_TEXT`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-generate-text) function in BigQuery for each row on the input table.

{% hint style="info" %}
In order to use this component, a [BigQuery ML model](https://cloud.google.com/bigquery/docs/bqml-introduction) needs to be provided by the user.

Also, having the BigQuery Connection User (`roles/bigquery.connectionUser`) role granted in your BigQuery project is required.
{% endhint %}

**Inputs**

* `Model [FQN]`: The path for the model to be used in the format `project_id.dataset.model`
* `Prompt column`: The column in the input source used to generate the prompt.
* `Max Output Tokens`: an `INT64` value in the range `[1,1024]` that sets the maximum number of tokens that the model outputs. Specify a lower value for shorter responses and a higher value for longer responses. The default is `50`.
* `Temperature`: a `FLOAT64` value in the range `[0.0,1.0]` that is used for sampling during the response generation, which occurs when `top_k` and `top_p` are applied. It controls the degree of randomness in token selection. Lower `temperature` values are good for prompts that require a more deterministic and less open-ended or creative response, while higher `temperature` values can lead to more diverse or creative results. A `temperature` value of `0` is deterministic, meaning that the highest probability response is always selected. The default is `1.0`.
* `Top P`: an `INT64` value in the range `[1,40]` that changes how the model selects tokens for output. Specify a lower value for less random responses and a higher value for more random responses. The default is `40`.
* `Top K`: a `FLOAT64` value in the range `[0.0,1.0]` that changes how the model selects tokens for output. Specify a lower value for less random responses and a higher value for more random responses. The default is `1.0`.

  Tokens are selected from the most (based on the `top_k` value) to least probable until the sum of their probabilities equals the `top_p` value. For example, if tokens A, B, and C have a probability of `0.3`, `0.2`, and `0.1` and the `top_p` value is `0.5`, then the model selects either A or B as the next token by using the `temperature` value and doesn't consider C.

**Outputs**

* `Result table [Table]`

**External links**

* [BigQuery reference](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-generate-text)


---

# 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://docs.carto.com/carto-user-manual/workflows/components/generative-ai.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.