🕵️ NeMo Anonymizer¶
NeMo Anonymizer detects and protects PII through context-aware replacement and rewriting. It offers high-quality user-guided entity detection, followed by modification options that maintain context while inducing privacy. You can review what sensitive information was found, adjust your masking strategy, and generate anonymized text.
Pick a strategy:
Alice met with Bob and his daughter to review kindergarten application #A9349.
Maya met with Daniel and his daughter to review kindergarten application #B5821.
[REDACTED_FIRST_NAME] met with [REDACTED_FIRST_NAME] and his daughter to review kindergarten application #[REDACTED_ID].
<Alice, first_name> met with <Bob, first_name> and his daughter to review kindergarten application #<A9349, id>.
<HASH_FIRST_NAME_3bc51062973c> met with <HASH_FIRST_NAME_cd9fb1e148cc> and his daughter to review kindergarten application #<HASH_ID_f2a5f83e2a4c>.
The family met with the admissions counselor to review their school application.
Get Started¶
Install¶
pip install nemo-anonymizerSetup¶
# Get an API key from build.nvidia.com
export NVIDIA_API_KEY="your-nvidia-api-key"Default hosted models are best for experimentation
The default build.nvidia.com setup is a convenient way to try Anonymizer and iterate on previews. For privacy-sensitive or production data, configure Anonymizer to use a secure endpoint you trust and to which you are comfortable sending data.
Request and token rate limits on build.nvidia.com vary by account and model access, and lower-volume development access can be slow for full-dataset runs. Start with preview() on a small sample, then move to your own endpoint if you need stronger privacy guarantees or higher throughput.
Record length
Records up to 2,000 tokens each work with the default model configs. Longer text will require adjustment of model providers and model configs.
Anonymize¶
from anonymizer import Anonymizer, AnonymizerConfig, AnonymizerInput, Substitute
input_data = AnonymizerInput(
source="patient_data.csv",
text_column="notes",
data_summary="Records containing detailed notes on patient encounters",
)
anonymizer = Anonymizer()
config = AnonymizerConfig(replace=Substitute())
anonymizer.validate_config(config)
preview = anonymizer.preview(
config=config,
data=input_data,
num_records=5,
)
preview.display_record()
# Inspect the preview, adjust parameters if needed, then run full data.
output = anonymizer.run(
config=config,
data=input_data,
)# Preview a few rows first
anonymizer preview \
--source patient_data.csv \
--text-column notes \
--data-summary "Records containing detailed notes on patient encounters" \
--replace substitute \
--num-records 5
# Then run the full dataset
anonymizer run \
--source patient_data.csv \
--text-column notes \
--data-summary "Records containing detailed notes on patient encounters" \
--replace substitute \
--output patient_data_anonymized.csvdata_summary improves detection
data_summary is optional but recommended for domain-specific data. It helps the LLM find more entities and reduce false drops.
Language And Regional Coverage¶
Anonymizer has been tested most extensively on English-language data. Multilingual quality has not yet been evaluated systematically across languages, domains, and models.
Although testing so far has been primarily in English, the supported entity set is not limited to U.S.-specific identifiers. Detection and anonymization can also apply to international formats such as non-U.S. phone numbers, addresses, legal references, and national or regional identification numbers, though coverage will vary by language, region, and model configuration.
If you are working with another language, we encourage you to experiment on a small sample first with preview(), validate detected entities and transformed output carefully, and adjust your model providers and model configs as needed.
Inspect¶
View an interactive visualization with entity highlights.
preview.display_record()preview.dataframepreview.trace_dataframe