> ## Documentation Index
> Fetch the complete documentation index at: https://docs.exploratory.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Create N-gram Tokens

## How to Access This Feature

### From + (plus) Button

You can access it from 'Add' (Plus) button. "Text Mining..." -> "Create N-Gram Tokens".

![](https://mintcdn.com/exploratory-inc/VL_CUSf6Xsk2Ztlz/en/text/images/do_ngram_add.png?fit=max\&auto=format\&n=VL_CUSf6Xsk2Ztlz\&q=85\&s=495e81615d1251c83b78cfa020600919)

## How to Use?

![](https://mintcdn.com/exploratory-inc/VL_CUSf6Xsk2Ztlz/en/text/images/do_ngram_param.png?fit=max\&auto=format\&n=VL_CUSf6Xsk2Ztlz\&q=85\&s=3ecc6f2a4234a7fb4bd271bf2c5d239a)

* Select a column that has tokenized text - Set a column that has tokens. This is "token" column if it's tokenized by [do\_tokenize](https://docs.exploratory.io/en/text/do_tokenize.md) function.
* Select a column as a document - A column considered as document id. If you run [do\_tokenize](https://docs.exploratory.io/en/text/do_tokenize.md) beforehand, this can be document\_id.
* Select a column as sentence id - A column considered as sentence id in a document. If you run do\_tokenize beforehand, this can be sentence\_id.
* Max # of Tokens to be Concatenated (Optional) - The default is 2. Maximum number of tokens to be connected.
* Text to Concatenate Words (Optional) - The default is "\_". Character to be used to connect ngrams.
  )


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.