Add Central and Eastern European PII language packs

README.md

@@ -32,7 +32,7 @@ No cloud. No vendor lock-in. No patient data leaving your network.</p>
 </p>
 
 <p>
-  <b>2,000+ models</b> &nbsp;·&nbsp; <b>17 model-backed PII languages</b> &nbsp;·&nbsp; <b>600+ PII checkpoints</b> &nbsp;·&nbsp; <b>100% on-device</b> &nbsp;·&nbsp; <b>Apache-2.0</b>
+  <b>2,000+ models</b> &nbsp;·&nbsp; <b>20 model-backed PII languages</b> &nbsp;·&nbsp; <b>600+ PII checkpoints</b> &nbsp;·&nbsp; <b>100% on-device</b> &nbsp;·&nbsp; <b>Apache-2.0</b>
 </p>
 
 <p>
@@ -503,10 +503,10 @@ On non-Apple-Silicon hosts, MLX model names are automatically substituted with t
 
 ---
 
-## Multilingual PII (17 model-backed languages)
+## Multilingual PII (20 model-backed languages)
 
-Extraction and de-identification support **17 supported PII language codes**:
-`ar`, `de`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`, `ko`, `nl`, `pt`, `ro`, `te`, `th`, and `tr`, with **600+ PII checkpoints** in total.
+Extraction and de-identification support **20 supported PII language codes**:
+`ar`, `cs`, `de`, `el`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`, `ko`, `nl`, `pt`, `ro`, `te`, `th`, `tr`, and `uk`, with **600+ PII checkpoints** in total.
 These are the model-backed PII language allow-list.
 OpenMed also includes validator-backed national-ID coverage for additional
 ID-only locales such as Polish, Latvian, Slovak, Malay, Filipino, and Danish.

clients/go/client.go

@@ -87,6 +87,9 @@ const (
 	LangTH PIILanguage = "th"
 	LangKO PIILanguage = "ko"
 	LangRO PIILanguage = "ro"
+	LangUK PIILanguage = "uk"
+	LangCS PIILanguage = "cs"
+	LangEL PIILanguage = "el"
 )
 
 // DeidentificationMethod selects how detected PII spans are transformed by the

clients/typescript/src/index.ts

@@ -26,7 +26,10 @@ export type PIILanguage =
   | "id"
   | "th"
   | "ko"
-  | "ro";
+  | "ro"
+  | "uk"
+  | "cs"
+  | "el";
 
 export type DeidentificationMethod =
   | "mask"

docs/anonymization.md

@@ -341,8 +341,8 @@ local attention, sink tokens, RoPE+YaRN, tiktoken `o200k_base`), differing
 only in their training data:
 
 The per-language PII API uses `openmed.core.pii_i18n.SUPPORTED_LANGUAGES`
-as its source of truth and supports **17 supported PII language codes**:
-`ar`, `de`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`, `ko`, `nl`, `pt`, `ro`, `te`, `th`, and `tr`.
+as its source of truth and supports **20 supported PII language codes**:
+`ar`, `cs`, `de`, `el`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`, `ko`, `nl`, `pt`, `ro`, `te`, `th`, `tr`, and `uk`.
 These are the model-backed PII language allow-list.
 Additional validator-backed national-ID providers cover ID-only locales such as
 Polish, Latvian, Slovak, Malay, Filipino, and Danish without adding

docs/api/openapi.json

@@ -196,7 +196,10 @@
               "id",
               "th",
               "ko",
-              "ro"
+              "ro",
+              "uk",
+              "cs",
+              "el"
             ],
             "title": "Lang",
             "type": "string"
@@ -417,7 +420,10 @@
               "id",
               "th",
               "ko",
-              "ro"
+              "ro",
+              "uk",
+              "cs",
+              "el"
             ],
             "title": "Lang",
             "type": "string"
@@ -540,7 +546,10 @@
               "id",
               "th",
               "ko",
-              "ro"
+              "ro",
+              "uk",
+              "cs",
+              "el"
             ],
             "title": "Lang",
             "type": "string"
@@ -636,7 +645,10 @@
               "id",
               "th",
               "ko",
-              "ro"
+              "ro",
+              "uk",
+              "cs",
+              "el"
             ],
             "title": "Lang",
             "type": "string"
@@ -752,7 +764,10 @@
               "id",
               "th",
               "ko",
-              "ro"
+              "ro",
+              "uk",
+              "cs",
+              "el"
             ],
             "title": "Lang",
             "type": "string"
@@ -876,7 +891,10 @@
               "id",
               "th",
               "ko",
-              "ro"
+              "ro",
+              "uk",
+              "cs",
+              "el"
             ],
             "title": "Lang",
             "type": "string"

docs/faq.md

@@ -87,13 +87,13 @@ model argument. Override `model_name` only when you need a specific checkpoint,
 
 ### Which languages are supported?
 
-PII extraction and de-identification support **17 supported PII language codes**:
-`ar`, `de`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`, `ko`, `nl`, `pt`, `ro`, `te`, `th`, and `tr`.
+PII extraction and de-identification support **20 supported PII language codes**:
+`ar`, `cs`, `de`, `el`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`, `ko`, `nl`, `pt`, `ro`, `te`, `th`, `tr`, and `uk`.
 These are the model-backed PII language allow-list.
 Validator-backed national-ID coverage is broader for specific ID-only locales,
 including Polish, Latvian, Slovak, Malay, Filipino, and Danish.
 The README keeps a short multilingual example set in
-[Multilingual PII](https://github.com/maziyarpanahi/openmed#multilingual-pii-17-model-backed-languages).
+[Multilingual PII](https://github.com/maziyarpanahi/openmed#multilingual-pii-20-model-backed-languages).
 
 Clinical NER coverage depends on the selected registry model. Check each model's `languages`, `entity_types`, and
 specialization in the [Model Registry](model-registry.md) before putting it behind an API or batch job.

docs/feature-map.md

@@ -15,7 +15,7 @@ coverage, see
 | Canonical span contracts | Versioned `OpenMedSpan`, schema fingerprints, redaction action schemas, provenance, and compatibility gates. | `openmed/core/schemas/`, [De-identification API](./api/deidentification.md), `examples/v16_policy_audit_release_gates.py` |
 | Audit and review evidence | Signed audit reports, reproducibility hashes, review bundles, FHIR `Provenance`/`AuditEvent`, audit diffs, and PHI-safe previews. | `openmed/core/audit.py`, `openmed/core/redaction_preview.py`, `openmed/risk/audit_diff.py`, `openmed/clinical/exporters/fhir/provenance.py`, `examples/v16_policy_audit_release_gates.py` |
 | Runtime de-identification features | `DeidentificationResult.to_dataframe`, surrogate vaults, patient-keyed date shifting, format-preserving redaction, minimum-necessary action selection, streaming redaction, explain traces, section stamping, and risk budgets. | `openmed/core/pii.py`, `openmed/core/surrogate_vault.py`, `openmed/core/date_shift.py`, `openmed/core/anonymizer/format_preserve.py`, `openmed/core/redaction_strength.py`, `openmed/core/streaming.py`, `openmed/core/explain.py`, `openmed/risk/budget.py` |
-| Multilingual PII | 17 supported PII language codes: ar, de, en, es, fr, he, hi, id, it, ja, ko, nl, pt, ro, te, th, and tr in the model-backed allow-list; locale validators, script detection, date/number normalization, deterministic locale PHI generation, and ID-only national-ID providers for additional locales. | `openmed/core/pii_i18n.py`, `openmed/core/script_detect.py`, `openmed/core/locale_formats.py`, `openmed/core/anonymizer/locales.py`, `openmed/training/synthetic/locale_phi.py`, `examples/pii_multilingual_new_languages.py` |
+| Multilingual PII | 20 supported PII language codes: ar, cs, de, el, en, es, fr, he, hi, id, it, ja, ko, nl, pt, ro, te, th, tr, and uk in the model-backed allow-list; locale validators, script detection, date/number normalization, deterministic locale PHI generation, and ID-only national-ID providers for additional locales. | `openmed/core/pii_i18n.py`, `openmed/core/script_detect.py`, `openmed/core/locale_formats.py`, `openmed/core/anonymizer/locales.py`, `openmed/training/synthetic/locale_phi.py`, `examples/pii_multilingual_new_languages.py` |
 
 ## Multimodal And Structured Inputs
 

docs/index.md

@@ -20,8 +20,8 @@ coverage, and stronger release evidence:
 - **Python, Swift, Kotlin/Android, REST, gRPC, React Native, TypeScript, and
   browser paths** including OpenMedKit, typed REST clients, ONNX/WebGPU, and
   Transformers.js export bundles.
-- **17 supported PII language codes: ar, de, en, es, fr, he, hi, id, it, ja,
-  ko, nl, pt, ro, te, th, and tr** in the model-backed allow-list, with
+- **20 supported PII language codes: ar, cs, de, el, en, es, fr, he, hi, id,
+  it, ja, ko, nl, pt, ro, te, th, tr, and uk** in the model-backed allow-list, with
   locale-aware validation and surrogate generation, plus additional
   validator-backed national-ID coverage for ID-only locales.
 - **Release evidence** for leakage heatmaps, model scorecards, threshold

docs/languages.md

@@ -36,7 +36,9 @@ locale resolution, determinism, and cross-document surrogate vaults, see
 | Code   | Language   | Default PII model                                          | Faker locale | Notes                                                        |
 | ------ | ---------- | ---------------------------------------------------------- | ------------ | ----------------------------------------------------------- |
 | `ar`   | Arabic     | `OpenMed/OpenMed-PII-Arabic-SnowflakeMed-Large-568M-v1`    | `ar_EG`      | Egypt is the most-populous Arabic locale; override per call. |
+| `cs`   | Czech      | `OpenMed/privacy-filter-multilingual`                       | `cs_CZ`      | Rodné číslo checksum-aware surrogates.                       |
 | `de`   | German     | `OpenMed/OpenMed-PII-German-SuperClinical-Small-44M-v1`    | `de_DE`      | Steuer-ID surrogates via `GermanSteuerIdProvider`.           |
+| `el`   | Greek      | `OpenMed/privacy-filter-multilingual`                       | `el_GR`      | AMKA Luhn-aware surrogates.                                  |
 | `en`   | English    | `OpenMed/OpenMed-PII-SuperClinical-Small-44M-v1`           | `en_US`      | Default model splits names into `first_name`/`last_name`.    |
 | `es`   | Spanish    | `OpenMed/OpenMed-PII-Spanish-SuperClinical-Small-44M-v1`   | `es_ES`      | DNI/NIE checksum-aware surrogates.                           |
 | `fr`   | French     | `OpenMed/OpenMed-PII-French-SuperClinical-Small-44M-v1`    | `fr_FR`      | NIR / INSEE surrogates via `fr_FR.ssn`.                      |
@@ -52,6 +54,7 @@ locale resolution, determinism, and cross-document surrogate vaults, see
 | `te`   | Telugu     | `OpenMed/OpenMed-PII-Telugu-SuperClinical-Large-434M-v1`   | `en_IN`      | No Faker Telugu locale — `en_IN` approximation (warns once). |
 | `th`   | Thai       | `OpenMed/privacy-filter-multilingual`                      | `th_TH`      | Served by the multilingual privacy filter; Thai NID-aware.   |
 | `tr`   | Turkish    | `OpenMed/OpenMed-PII-Turkish-SuperClinical-Small-44M-v1`   | `tr_TR`      | TCKN surrogates.                                             |
+| `uk`   | Ukrainian  | `OpenMed/privacy-filter-multilingual`                       | `uk_UA`      | RNOKPP checksum-aware surrogates.                            |
 
 Codes outside this list (for example `zh`, `pl`, `lv`, `sk`, `ms`, `tl`, `da`)
 are **not** model-backed PII languages. Several of them still have
@@ -76,6 +79,15 @@ Before: المريضة ليلى حسن، الهاتف +20 10 1234 5678
 After:  المريضة [NAME]، الهاتف [PHONE]
 ```
 
+### Czech — `cs`
+
+- Model: `OpenMed/privacy-filter-multilingual` · locale `cs_CZ`
+
+```text
+Before: Pacient Jan Novák, rodné číslo 751116/0008
+After:  Pacient [NAME], rodné číslo [ID]
+```
+
 ### German — `de`
 
 - Model: `OpenMed/OpenMed-PII-German-SuperClinical-Small-44M-v1` · locale `de_DE`
@@ -85,6 +97,15 @@ Before: Patientin Anna Müller, Steuer-ID 86095742719
 After:  Patientin [NAME], Steuer-ID [ID]
 ```
 
+### Greek — `el`
+
+- Model: `OpenMed/privacy-filter-multilingual` · locale `el_GR`
+
+```text
+Before: Ασθενής Γιώργος Παπαδόπουλος, ΑΜΚΑ 16117508024
+After:  Ασθενής [NAME], ΑΜΚΑ [ID]
+```
+
 ### English — `en`
 
 - Model: `OpenMed/OpenMed-PII-SuperClinical-Small-44M-v1` · locale `en_US`
@@ -221,3 +242,12 @@ After:  ผู้ป่วย [NAME] โทร [PHONE]
 Before: Hasta Ayşe Yılmaz, TCKN 10000000146
 After:  Hasta [NAME], TCKN [ID]
 ```
+
+### Ukrainian — `uk`
+
+- Model: `OpenMed/privacy-filter-multilingual` · locale `uk_UA`
+
+```text
+Before: Пацієнтка Олена Коваль, РНОКПП 2974281300
+After:  Пацієнтка [NAME], РНОКПП [ID]
+```

docs/rest-recipes.md

@@ -174,9 +174,10 @@ hardware):
 ## Extract PII — `POST /pii/extract`
 
 Detect personally identifiable information. Unless `model_name` is set, OpenMed
-selects the recommended PII model for `lang`. The 17 supported PII language
-codes: `ar`, `de`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`, `ko`, `nl`,
-`pt`, `ro`, `te`, `th`, and `tr`. `confidence_threshold` defaults to `0.5`.
+selects the recommended PII model for `lang`. The 20 supported PII language
+codes: `ar`, `cs`, `de`, `el`, `en`, `es`, `fr`, `he`, `hi`, `id`, `it`, `ja`,
+`ko`, `nl`, `pt`, `ro`, `te`, `th`, `tr`, and `uk`. `confidence_threshold`
+defaults to `0.5`.
 
 ```bash
 curl -sS --max-time 310 -X POST "$OPENMED_URL/pii/extract" \

docs/troubleshooting.md

@@ -383,12 +383,12 @@ text = validate_input(user_supplied_text, max_length=2000, allow_empty=False)
 **Symptom.** A PII call with an unrecognized `lang` raises:
 
 ```text
-ValueError: Unsupported language 'xx'. Supported: ['ar', 'de', 'en', 'es', 'fr', 'he', 'hi', 'id', 'it', 'ja', 'ko', 'nl', 'pt', 'ro', 'te', 'th', 'tr']
+ValueError: Unsupported language 'xx'. Supported: ['ar', 'cs', 'de', 'el', 'en', 'es', 'fr', 'he', 'hi', 'id', 'it', 'ja', 'ko', 'nl', 'pt', 'ro', 'te', 'th', 'tr', 'uk']
 ```
 
-**Cause.** PII extraction and de-identification support **17 supported PII language codes: ar, de, en, es,
-fr, he, hi, id, it, ja, ko, nl, pt, ro, te, th, and tr**. Passing anything outside that set (or a mistyped
-code) raises this error.
+**Cause.** PII extraction and de-identification support **20 supported PII language codes: ar, cs, de, el,
+en, es, fr, he, hi, id, it, ja, ko, nl, pt, ro, te, th, tr, and uk**. Passing anything outside that set (or a
+mistyped code) raises this error.
 
 **Fix.** Use one of the supported codes with `extract_pii(..., lang="<code>")`. Clinical NER coverage depends
 on the selected registry model — check each model's `languages` in the

docs/website/assets/script.js

@@ -117,7 +117,7 @@ function moonSVG() {
     return `<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.6" stroke-linecap="round" stroke-linejoin="round"><path d="M21 12.8A9 9 0 1 1 11.2 3a7 7 0 0 0 9.8 9.8z"/></svg>`;
 }
 
-/* ---------- PHI Demo (cycles through 7 of the 17 languages OpenMed supports) ------ */
+/* ---------- PHI Demo (cycles through 7 of the 20 languages OpenMed supports) ------ */
 const PHI_SAMPLES = [
     {
         lang: "en",