RegexTextExtractor

Extract text from chat messages or strings using a regex pattern.

Key Features

• Extracts specific text from strings or ChatMessage lists using a regular expression pattern.
• Supports capture groups to isolate exactly the text you need.
• Returns the entire match when no capture group is defined.
• Configurable behavior when no match is found: return an empty string or skip output.
• Useful for parsing structured output from LLMs, such as URLs, codes, or tagged content.

Configuration

1. Drag the RegexTextExtractor component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Enter the regular expression pattern to use for extraction. Include a capture group to extract only the desired text. For example, <issue url="([^"]+)"> captures the URL from the tag.
4. Go to the Advanced tab to configure additional settings:
   • Set return_empty_on_no_match to control what happens when the pattern finds no match.

Connections

RegexTextExtractor accepts either a string or a list of ChatMessage objects as input. Connect it to the Input component or to any component that produces string or ChatMessage output, such as LLM.

Connect its captured_text output to any component that consumes a text string.

Source Code

To check this component's source code, open regex_text_extractor.py in the Haystack repository.

Usage Examples

Basic Configuration

  RegexTextExtractor:
    type: haystack.components.extractors.regex_text_extractor.RegexTextExtractor
    init_parameters:
      regex_pattern: <issue url="([^"]+)">
      return_empty_on_no_match: true

In a Pipeline

This query pipeline uses an LLM to analyze text and produce structured output, then uses RegexTextExtractor to extract a specific issue URL from the response:

# haystack-pipeline
components:
  RegexTextExtractor:
    type: haystack.components.extractors.regex_text_extractor.RegexTextExtractor
    init_parameters:
      regex_pattern: '<issue url="([^"]+)">'

  AnswerBuilder:
    type: haystack.components.builders.answer_builder.AnswerBuilder
    init_parameters:
      pattern:
      reference_pattern:

  LLM:
    type: haystack.components.generators.chat.llm.LLM
    init_parameters:
      chat_generator:
        init_parameters:
          model: gpt-5.5
        type: haystack.components.generators.chat.openai_responses.OpenAIResponsesChatGenerator
      system_prompt: ""
      user_prompt: >-
        {% message role="user" %}

        You are a helpful assistant that identifies issues in text.

        When you find an issue, format your response as:

        <issue url="https://github.com/example/repo/issues/123">Description of
        the issue</issue>

        Analyze the following text and identify any issues:

        {{ query }} 

        {% endmessage %}
      required_variables: "*"
      streaming_callback:

connections:
- sender: RegexTextExtractor.captured_text
  receiver: AnswerBuilder.replies
- sender: LLM.last_message
  receiver: RegexTextExtractor.text_or_messages

inputs:
  query:
  - AnswerBuilder.query
  - LLM.query

outputs:
  answers: AnswerBuilder.answers

max_runs_per_component: 100

metadata: {}

In this example:

1. LLM generates a response containing the structured output.
2. RegexTextExtractor uses the pattern <issue url="([^"]+)"> to extract the URL from the response. The capture group ([^"]+) matches any characters except quotes inside the url attribute.
3. AnswerBuilder formats the extracted URL as the final answer.

Parameters

Inputs

Parameter	Type	Description
text_or_messages	Union[str, List[ChatMessage]]	Either a string or a list of ChatMessage objects to search through.

Outputs

Parameter	Type	Description
captured_text	str	The matched text if a match is found. Empty string if no match is found and return_empty_on_no_match=False.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
regex_pattern	str		The regular expression pattern used to extract text. The pattern should include a capture group to extract the desired text. Example: '<issue url="(.+)">' captures the URL from the tag.
return_empty_on_no_match	bool	True	If True, returns an empty dictionary when no match is found. If False, returns {"captured_text": ""}.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Description
text_or_messages	Union[str, List[ChatMessage]]	Either a string or a list of ChatMessage objects to search through.