> For the complete documentation index, see [llms.txt](https://docs.ebbot.ai/ebbot-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ebbot.ai/ebbot-docs/core-capabilities/chat/dishwasher.md).

# Dishwasher

## Regex <a href="#regex" id="regex"></a>

Regex (Regular Expressions) is the most straightforward method. Entities are defined using specific patterns, and the function searches the text for matches. Regex is reliable when the input follows expected formats, but it may be less effective when handling misspellings or more complex structures.

## Email <a href="#email" id="email"></a>

Pattern: `[a-zåäöA-ZÅÄÖ0-9]+[\._]?[a-zåäöA-ZÅÄÖ0-9]+[@]\w+[.]\w{2,3}`

**Examples (matches):**

✅ <user@example.com>

✅ <user.name+alias@domain.se>

✅ någon\@exempel.åäö

✅ [me@sub.example.com ](mailto:me@sub.example.com)**Examples (non-matches):**

❌ @example.com

❌ <user@.com>

❌ user\@examp

❌ user\@example..com

## Social number <a href="#social-number" id="social-number"></a>

Pattern: `(19|20)([0-9]{4,6})([-+]|\s)?([0-9]{4})|([0-9]{2})([0-1][0-9][0-3][0-9])([-+]|\s)?([0-9]{4})`

**Examples (matches):**

✅ 19900101-1234

✅ 199001011234

✅ 900101-1234

✅ 9001011234

✅ 18991231+5678

## **Credit card number** <a href="#credit-card-number" id="credit-card-number"></a>

Pattern: `(4\d{3}|5[1-5]\d{2}|6011)(-?\s?)(\d{4})(-?\s?)(\d{4})(-?\s?)(\d{4}|3[4,7]\d{13})`

| Card type        | Begins with | Digits | Example             |
| ---------------- | ----------- | ------ | ------------------- |
| Visa             | 4xxx        | 16     | 4123-5678-9012-3456 |
| Mastercard       | 51-55xx     | 16     | 5214-5678-9012-3456 |
| Discovery        | 6011        | 16     | 6011-5678-9012-3456 |
| American Express | 34,37       | 15     | 371234567890123     |

***

## Multilingual anonymiser model <a href="#multilingual-anonymiser-model-ai4privacy-llama-ai4privacy-multilingual-categorical-anonymiser-openpi" id="multilingual-anonymiser-model-ai4privacy-llama-ai4privacy-multilingual-categorical-anonymiser-openpi"></a>

🔗[ai4privacy/llama-ai4privacy-multilingual-categorical-anonymiser-openpii · Hugging Face](https://huggingface.co/ai4privacy/llama-ai4privacy-multilingual-categorical-anonymiser-openpii)

This is a bidirectional, encoder-only Transformer model trained to detect and redact personally identifiable information (PII) from multilingual text. It goes beyond simple pattern matching and can identify entities in more complex or unstructured formats.

Entities detected by this model include:

* AGE
* BUILDINGNUM
* CITY
* CREDITCARDNUMBER
* DATE
* DRIVERLICENSENUM
* EMAIL
* GENDER
* GIVENNAME
* IDCARDNUMBER
* PASSPORTNUM
* SEX
* SOCIALNUM
* STREET
* SURNAME
* TAXNUM
* TELEPHONENUM
* TIME
* TITLE
* ZIPCODE

## Swedish anonymiser model <a href="#swedish-anonymiser-model" id="swedish-anonymiser-model"></a>

🔗 [RecordedFuture/Swedish-NER · Hugging Face](https://huggingface.co/RecordedFuture/Swedish-NER)

This model is similar to the Multilingual anonymiser but specifically trained on Swedish data.

Entities detected by this model include:

* LOCATION
* ORGANIZATION
* PERSON
* RELIGION
* TITLE