Text Operations

import Icon from "@site/src/components/icon"; import PartialParams from '@site/docs/_partial-hidden-params.mdx';

The Text Operations component performs operations on text strings.

The output type depends on the selected operation: most operations return a Message, Word Count returns a JSON object, and Text to DataFrame returns a Table.

Use the Text Operations component in a flow

The following example demonstrates how to use a Text Operations component to clean text output from a language model before passing it to another component:

1. Create a flow with a Language Model component and a Text Operations component, and then connect the Language Model component's Message output to the Text Operations component's Text Input.

   All operations in the Text Operations component require a text string as input. If the preceding component doesn't produce Message or text output, you can use the Type Convert component to reformat the data first.

2. In the Operation field, select the operation you want to perform. For this example, select Text Clean.

   :::tip You can select only one operation. If you need to perform multiple operations, chain multiple Text Operations components together to execute each operation in sequence. :::

3. Configure the operation's parameters. For this example, enable Remove Extra Spaces and Remove Empty Lines to normalize the model's output.

4. Optional: Connect the output to a Chat Output component to view the result in the Playground.

5. Click <Icon name="Play" aria-hidden="true" /> Run component on the Text Operations component, and then click <Icon name="TextSearch" aria-hidden="true" /> Inspect output to view the result.

Text Operations parameters

Many parameters are conditional based on the selected Operation (operation).

<PartialParams />

Name	Display Name	Info
text_input	Text Input	Input parameter. The text string to process. Required for all operations.
operation	Operation	Input parameter. The operation to perform on the text. See Available text operations.
case_type	Case Type	Input parameter. The case conversion to apply. Options: uppercase, lowercase, title, capitalize, swapcase. Default: lowercase. Only shown for Case Conversion.
search_pattern	Search Pattern	Input parameter. The text or regex pattern to find. Only shown for Text Replace.
replacement_text	Replacement Text	Input parameter. The text to substitute for each match. Only shown for Text Replace.
use_regex	Use Regex	Input parameter. If enabled, treats Search Pattern as a regular expression. Default: Disabled. Only shown for Text Replace.
extract_pattern	Extract Pattern	Input parameter. The regular expression pattern to match against the text. Only shown for Text Extract.
max_matches	Max Matches	Input parameter. Maximum number of matches to return. Default: 10. Only shown for Text Extract.
head_characters	Characters from Start	Input parameter. Number of characters to return from the beginning of the text. Must be non-negative. Default: 100. Only shown for Text Head.
tail_characters	Characters from End	Input parameter. Number of characters to return from the end of the text. Must be non-negative. Default: 100. Only shown for Text Tail.
strip_mode	Strip Mode	Input parameter. Which side(s) of the text to strip. Options: both (default), left, right. Only shown for Text Strip.
strip_characters	Characters to Strip	Input parameter. Specific characters to remove. Leave empty to strip whitespace. Only shown for Text Strip.
text_input_2	Second Text Input	Input parameter. The second text string to join with the first. Only shown for Text Join.
remove_extra_spaces	Remove Extra Spaces	Input parameter. Collapse multiple consecutive spaces into a single space. Default: Enabled. Only shown for Text Clean.
remove_special_chars	Remove Special Characters	Input parameter. Remove all characters except alphanumeric and spaces. Default: Disabled. Only shown for Text Clean.
remove_empty_lines	Remove Empty Lines	Input parameter. Remove blank lines from the text. Default: Disabled. Only shown for Text Clean.
table_separator	Table Separator	Input parameter. The character used to delimit columns. Default: |. Only shown for Text to DataFrame.
has_header	Has Header	Input parameter. Whether the first row is a header row. Default: Enabled. Only shown for Text to DataFrame.
count_words	Count Words	Input parameter. Include word count and unique word count in the output. Default: Enabled. Only shown for Word Count.
count_characters	Count Characters	Input parameter. Include character count (with and without spaces) in the output. Default: Enabled. Only shown for Word Count.
count_lines	Count Lines	Input parameter. Include total and non-empty line count in the output. Default: Enabled. Only shown for Word Count.

Available text operations

Options for the operation input parameter are as follows.

Name	Required Inputs	Output	Process
Word Count	None	JSON	Counts words, unique words, characters, and lines in the text.
Case Conversion	case_type	Message	Converts the text to the specified case.
Text Replace	search_pattern, replacement_text, use_regex	Message	Replaces occurrences of a pattern with replacement text.
Text Extract	extract_pattern, max_matches	Message	Extracts all substrings matching a regex pattern, returned as newline-separated text.
Text Head	head_characters	Message	Returns the first n characters of the text.
Text Tail	tail_characters	Message	Returns the last n characters of the text.
Text Strip	strip_mode, strip_characters	Message	Removes whitespace or specified characters from the edges of the text.
Text Join	text_input_2	Text, Message	Concatenates two text inputs separated by a newline.
Text Clean	remove_extra_spaces, remove_special_chars, remove_empty_lines	Message	Normalizes text by removing extra spaces, special characters, and empty lines.
Text to DataFrame	table_separator, has_header	Table	Converts a delimiter-separated text table into a Table.

See also

• Table Operations
• Parser
• JSON Operations