update README.md and notebook.ipynb

README.md

@@ -29,9 +29,6 @@ task:
 
 # tanaos-text-anonymizer-v1: A small but performant Text Anonymization model
 
-> [!TIP]
-> Looking for a custom Text Anonymization model, or any other task-specific Small Language Model fine-tuned to your specific needs? We will do it for you! https://tanaos.com/#try-it-out
-
 This model was created by Tanaos with the [Artifex Python library](https://github.com/tanaos/artifex).
 
 This is a **Named Entity Recognition model** based on [tanaos/tanaos-NER-v1](https://huggingface.co/tanaos/tanaos-NER-v1) and fine-tuned on [a synthetic dataset](https://huggingface.co/datasets/tanaos/synthetic-text-anonymizer-dataset-v1) to recognize Personal Identifiable Information (PII) entities in text. Once identified, the entities are redacted to ensure privacy and confidentiality, before sharing or processing text data.
@@ -48,112 +45,27 @@ While the base NER model was trained to recognize 14 named entity categories, th
 
 ## How to Use
 
-<!-- ### Via the Tanaos API -->
-
-Use this model for free via the [Tanaos API](https://tanaos.com/) in 3 simple steps:
-
-1. Sign up for a free account at [https://platform.tanaos.com/](https://platform.tanaos.com/)
-2. Create a free API Key from the [API Keys section](https://platform.tanaos.com/profile/api-keys)
-3. Replace `<YOUR_API_KEY>` in the code below with your API Key and use this snippet:
-
-```python
-import requests
-
-session = requests.Session()
-
-ta_out = session.post(
-    "https://slm.tanaos.com/models/text-anonymization",
-    headers={
-        "X-API-Key": "<YOUR_API_KEY>",
-    },
-    json={
-        "text": "John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567.",
-        "include_mask_type": True,
-        "include_mask_counter": True
-    }
-)
-
-print(ta_out.json()["data"])
-# >>> ['[MASKED_PERSON_3] lives at [MASKED_ADDRESS_2] [MASKED_LOCATION_1] His phone number is [MASKED_PHONE_NUMBER_0]']
-```
-
-<!-- ### Via the Artifex library (`pip install artifex`)
-
-```python
-from artifex import Artifex
-
-ta = Artifex().text_anonymization
-
-print(ta("John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567."))
-# >>> ["[MASKED] lives at [MASKED]. His phone number is [MASKED]."]
-```
-
-### Via the Transformers library
-
-Using this model through the `transformers` library, Personal Identifiable Information (PII) are only identified, but not automatically redacted; you will have to implement your own redaction logic.
-
-```python
-from transformers import pipeline
-
-ta = pipeline(
-    task="token-classification",
-    model="tanaos/tanaos-text-anonymizer-v1",
-    aggregation_strategy="first"
-)
-
-print(ta("John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567."))
-# >>> [{'entity_group': 'PERSON', 'score': 0.90219176, 'word': 'John Doe', 'start': 0, 'end': 8}, {'entity_group': 'ADDRESS', 'score': 0.9522348, 'word': ' 123 Main St,', 'start': 18, 'end': 30}, {'entity_group': 'LOCATION', 'score': 0.97109795, 'word': ' New York.', 'start': 31, 'end': 40}, {'entity_group': 'PHONE_NUMBER', 'score': 0.9054972, 'word': ' (555) 123-4567.', 'start': 61, 'end': 76}]
-```
-
-## How to fine-tune (without training data)
+Use this model through the [Artifex library](https://github.com/tanaos/artifex):
 
-Use the [Artifex library](https://github.com/tanaos/artifex) to fine-tune the model to any language other than English or to custom domains by generating synthetic training data on-the-fly. Install Artifex with 
+install Artifex with
 
 ```bash
 pip install artifex
 ```
 
-### Fine-tune to any language
+use the model with
 
 ```python
 from artifex import Artifex
 
-ta = Artifex().text_anonymization
+ta = Artifex().text_anonymization()
 
-model_output_path = "./output_model/"
+anonymized_text = ta("John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567.")
+print(anonymized_text)
 
-ta.train(
-    domain="documentos medicos en Español",
-    language="spanish",
-    output_path=model_output_path
-)
-
-ta.load(model_output_path)
-print(ta("El paciente John Doe visitó Nueva York el 12 de marzo de 2023 a las 10:30 a. m."))
-
-# >>> ["El paciente [MASKED] visitó [MASKED] el [MASKED] a las [MASKED]."]
+# >>> ["[MASKED] lives at [MASKED]. His phone number is [MASKED]."]
 ```
 
-### Fine-tune to custom domains
-
-```python
-from artifex import Artifex
-
-text_anonym = Artifex().text_anonymization
-
-model_output_path = "./output_model/"
-
-text_anonym.train(
-    domain="legal documents",
-    output_path=model_output_path
-)
-
-ta.load(model_output_path)
-print(ta("John Doe signed the contract on 12/03/2023 at 123 Main St, New York."))
-
-# >>> ["[MASKED] signed the contract on [MASKED] at [MASKED]."]
-``` -->
-
 ## Model Description
 
 - **Base model:** `FacebookAI/roberta-base`
@@ -174,7 +86,7 @@ by providing the following instructions and generating 10,000 synthetic training
 ```python
 from artifex import Artifex
 
-ta = Artifex().text_anonymization
+ta = Artifex().text_anonymization()
 
 ta.train(
     domain="general",

notebook.ipynb

@@ -13,11 +13,11 @@
    "id": "e94691be",
    "metadata": {},
    "source": [
-    "Use this model for free via the [Tanaos API](https://tanaos.com/) in 3 simple steps:\n",
+    "Use the [Artifex library](https://github.com/tanaos/artifex). Install it with\n",
     "\n",
-    "1. Sign up for a free account at [https://platform.tanaos.com/](https://platform.tanaos.com/)\n",
-    "2. Create a free API Key from the [API Keys section](https://platform.tanaos.com/profile/api-keys)\n",
-    "3. Replace `<YOUR_API_KEY>` in the code below with your API Key and use this snippet:"
+    "```bash\n",
+    "pip install artifex\n",
+    "```"
    ]
   },
   {
@@ -31,23 +31,12 @@
    },
    "outputs": [],
    "source": [
-    "import requests\n",
+    "from artifex import Artifex\n",
     "\n",
-    "session = requests.Session()\n",
+    "ta = Artifex().text_anonymization()\n",
     "\n",
-    "ta_out = session.post(\n",
-    "    \"https://slm.tanaos.com/models/text-anonymization\",\n",
-    "    headers={\n",
-    "        \"X-API-Key\": \"<YOUR_API_KEY>\",\n",
-    "    },\n",
-    "    json={\n",
-    "        \"text\": \"John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567.\",\n",
-    "        \"include_mask_type\": True,\n",
-    "        \"include_mask_counter\": True\n",
-    "    }\n",
-    ")\n",
-    "\n",
-    "print(ta_out.json()[\"data\"])"
+    "anonymized_text = ta(\"John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567.\")\n",
+    "print(anonymized_text)"
    ]
   }
  ],