PresidioDocumentCleaner

PresidioDocumentCleaner replaces personally identifiable information (PII) in the text content of Documents with entity type placeholders such as <PERSON> or <EMAIL_ADDRESS>. Original Documents are not mutated. Documents without text content pass through unchanged.

Most common position in a pipeline	In an indexing pipeline, before writing Documents to a Document Store
Mandatory run variables	documents: A list of Document objects
Output variables	documents: A list of Document objects 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. PresidioDocumentCleaner uses Presidio's Analyzer and Anonymizer engines to scan document text and replace detected entities with type placeholders such as <PERSON> or <EMAIL_ADDRESS>.

This is useful when you want to store sanitized versions of your documents in a Document Store — for example, to prevent sensitive information from being indexed or returned in search results.

If you want to annotate PII without modifying the text, see PresidioEntityExtractor. For sanitizing plain strings such as user queries, see PresidioTextCleaner.

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 PresidioDocumentCleaner.

bash

pip install presidio-haystack

On its own

python

from haystack import Document
from haystack_integrations.components.preprocessors.presidio import (
    PresidioDocumentCleaner,
)

cleaner = PresidioDocumentCleaner()
result = cleaner.run(
    documents=[
        Document(content="Contact Alice Smith at alice@example.com or 212-555-1234."),
    ],
)
print(result["documents"][0].content)
# Contact <PERSON> at <EMAIL_ADDRESS> or <PHONE_NUMBER>.

In a pipeline

python

from haystack import Document, Pipeline
from haystack.components.writers import DocumentWriter
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack_integrations.components.preprocessors.presidio import (
    PresidioDocumentCleaner,
)

document_store = InMemoryDocumentStore()

indexing_pipeline = Pipeline()
indexing_pipeline.add_component("cleaner", PresidioDocumentCleaner())
indexing_pipeline.add_component("writer", DocumentWriter(document_store=document_store))
indexing_pipeline.connect("cleaner", "writer")

indexing_pipeline.run(
    {
        "cleaner": {
            "documents": [
                Document(content="Alice Smith's email is alice@example.com"),
                Document(content="Call Bob at 212-555-9876"),
            ],
        },
    },
)

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 (
    PresidioDocumentCleaner,
)

cleaner = PresidioDocumentCleaner(
    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 import Document
from haystack_integrations.components.preprocessors.presidio import (
    PresidioDocumentCleaner,
)

# No `models` parameter needed — de_core_news_lg is selected automatically
cleaner = PresidioDocumentCleaner(language="de")
result = cleaner.run(
    documents=[
        Document(
            content="Mein Name ist Hans Müller und meine E-Mail ist hans@example.com",
        ),
    ],
)
print(result["documents"][0].content)
# Mein Name ist <PERSON> und meine E-Mail ist <EMAIL_ADDRESS>

Supported languages and their default models are listed in PresidioDocumentCleaner.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 = PresidioDocumentCleaner(
    language="fr",
    models=[{"lang_code": "fr", "model_name": "fr_core_news_md"}],
)