PresidioTextCleaner

PresidioTextCleaner replaces personally identifiable information (PII) in plain strings. It takes a list[str] as input and returns a list[str], making it easy to sanitize user queries before they are sent to an LLM.

Most common position in a pipeline	In a query pipeline, before a Generator or Chat Generator
Mandatory run variables	texts: A list of strings
Output variables	texts: A list of strings with PII replaced
API reference	Presidio
GitHub link	https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/presidio

Overview

Microsoft Presidio is an open-source framework for PII detection and anonymization. PresidioTextCleaner uses Presidio's Analyzer and Anonymizer engines to scan plain text strings and replace detected entities with type placeholders such as <PERSON> or <US_SSN>.

This is useful when you want to sanitize user queries before sending them to an LLM, ensuring that no personally identifiable information is passed to the model.

For sanitizing Haystack Document objects rather than plain strings, see PresidioDocumentCleaner.

Configuration

Parameter	Default	Description
language	"en"	ISO 639-1 language code for PII detection. The appropriate spaCy model is selected automatically for supported languages. See Presidio supported languages.
entities	None	List of PII entity types to detect and anonymize (e.g. ["PERSON", "EMAIL_ADDRESS"]). If None, all supported types are detected. See supported entities.
score_threshold	0.35	Minimum confidence score (0–1) for a detected entity to be anonymized.
models	None	Advanced override: explicit list of spaCy model configs, e.g. [{"lang_code": "fr", "model_name": "fr_core_news_md"}]. Use this only when you need a specific model variant or a language not in the built-in mapping. If None, the model is selected automatically based on language.

Usage

Install the presidio-haystack package to use the PresidioTextCleaner.

bash

pip install presidio-haystack

On its own

python

from haystack_integrations.components.preprocessors.presidio import PresidioTextCleaner

cleaner = PresidioTextCleaner()
result = cleaner.run(texts=["My name is John Doe, my SSN is 123-45-6789"])
print(result["texts"][0])
# My name is <PERSON>, my SSN is <US_SSN>

In a pipeline

python

from haystack import Pipeline
from haystack.components.builders import ChatPromptBuilder
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage
from haystack_integrations.components.preprocessors.presidio import PresidioTextCleaner

template = [ChatMessage.from_user("Answer this question: {{query}}")]

query_pipeline = Pipeline()
query_pipeline.add_component("cleaner", PresidioTextCleaner())
query_pipeline.add_component("prompt_builder", ChatPromptBuilder(template=template))
query_pipeline.add_component("llm", OpenAIChatGenerator(model="gpt-4o-mini"))
query_pipeline.connect("cleaner.texts[0]", "prompt_builder.query")
query_pipeline.connect("prompt_builder", "llm")

query_pipeline.run(
    {"cleaner": {"texts": ["My name is John Smith. What is the capital of France?"]}},
)

Using Custom Parameters

Use entities to limit anonymization to the PII types you actually care about. This reduces false positives and improves performance by skipping recognizers you don't need.

Use score_threshold to tune the precision-recall tradeoff. The default 0.35 casts a wide net and may anonymize some false positives. Raise it (e.g. 0.7) when you need high confidence before replacing text; lower it when missing any PII is the bigger risk.

python

from haystack_integrations.components.preprocessors.presidio import PresidioTextCleaner

cleaner = PresidioTextCleaner(
    language="de",
    entities=["PERSON", "EMAIL_ADDRESS"],  # only anonymize names and emails
    score_threshold=0.7,  # higher precision, fewer false positives
)

Non-English languages

For any language in the built-in mapping, just set language — the right spaCy model is selected and loaded automatically at warm-up time.

python

from haystack_integrations.components.preprocessors.presidio import PresidioTextCleaner

# No `models` parameter needed — de_core_news_lg is selected automatically
cleaner = PresidioTextCleaner(language="de")
result = cleaner.run(
    texts=["Hallo, ich bin Thomas Schmidt und meine E-Mail ist thomas@example.com"],
)
print(result["texts"][0])
# Hallo, ich bin <PERSON> und meine E-Mail ist <EMAIL_ADDRESS>

Supported languages and their default models are listed in PresidioTextCleaner.SPACY_DEFAULT_MODELS. Using a language not in that mapping without providing models raises a ValueError at warm-up time with a list of the supported language codes.

To use a non-default model variant, or a language outside the built-in mapping, pass models explicitly:

python

cleaner = PresidioTextCleaner(
    language="fr",
    models=[{"lang_code": "fr", "model_name": "fr_core_news_md"}],
)