# 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)