# transform-columns

<mark style="color:purple;">`transform-columns`</mark> *adaptor transforms values in specified columns using an OpenAI language model.*

## Description

## Inputs

**`data`**\
Type: `datatable`\
Required: Yes\
The datatable containing the columns to be transformed.

**`columns`**\
Type: `list`\
Required: Yes\
The list of columns to be transformed.

**`model`**\
Type: `text`\
Required: No\
The name of the language models to run. Consider [price points](https://openai.com/pricing) of each model. If unspecified, defaults to `gpt-3.5-turbo`.

**`system message`**\
Type: `text`\
Required: Yes\
The system message helps set the behavior of the assistant. You can [modify the personality of the assistant](https://platform.openai.com/docs/guides/text-generation/chat-completions-api) or provide specific instructions about how it should behave throughout the conversation.

**`api token`**\
Type: `text`\
Required: Yes\
OpenAI [API token](https://platform.openai.com/account/api-keys)

## Outputs

**`data`**\
Type: `datatable`\
A datatable with the specified columns transformed.

**`summary`**\
Type: `dictionary`\
A summary of the transformed values.

## Examples

### Example 1: Default behaviour.

#### Inputs:

`data:`

| id | code | name           |
| -- | ---- | -------------- |
| 1  | GB   | United Kingdom |
| 2  | TR   | Turkey         |
| 3  | US   | United States  |
| 4  | IND  | India          |
| 5  | IND  | India          |
| 6  | us   | United States  |

`columns:`

1. code

`model:` *null (empty)*

`system message:` You will be provided a country code and your job is to return the country code in lowercase

`api token:` 12345

#### Outputs:

`data`:

| id | code | name           |
| -- | ---- | -------------- |
| 1  | gb   | United Kingdom |
| 2  | tr   | Turkey         |
| 3  | us   | United States  |
| 4  | ind  | India          |
| 5  | ind  | India          |
| 6  | us   | United States  |

-> Transformed the column `code` into lowercase.


---

# 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://cgps.gitbook.io/data-flo/reference-guide/transform-columns.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.