Skip to main content
Inconsistent provenance

Files in this release originate from inconsistent repositories or configurations. View details.

GLLM Privacy

Description

This library protects Personally Identifiable Information (PII) in a Generative AI project.

Installation

Prerequisites

Required:

  1. Install Python 3.11.5+
  2. Install pip
  3. Install uv

Extras (required only for Artifact Registry installations):

  1. Install gcloud CLI, then log in using:
    gcloud auth login
    

Option 1: Install from Artifact Registry

This option requires authentication via the gcloud CLI.

uv pip install \
  --extra-index-url "https://oauth2accesstoken:$(gcloud auth print-access-token)@glsdk.gdplabs.id/gen-ai-internal/simple/" \
  gllm-privacy

Option 2: Install from PyPI

This option requires no authentication. It installs the binary wheel, which works fully but does not include source code.

uv pip install gllm-privacy-binary

Local development setup

Prerequisites

  1. Install Python 3.11.5+

  2. Install pip

  3. Install uv

  4. Install gcloud CLI, then log in using:

    gcloud auth login
    
  5. Install Git

  6. Access to the GDP Labs SDK GitHub repository


1. Clone repository

git clone git@github.com:GDP-ADMIN/gl-sdk.git
cd gl-sdk/libs/gllm-privacy

2. Set up authentication

Set the following environment variables to authenticate with internal package indexes:

export UV_INDEX_GEN_AI_INTERNAL_USERNAME=oauth2accesstoken
export UV_INDEX_GEN_AI_INTERNAL_PASSWORD="$(gcloud auth print-access-token)"
export UV_INDEX_GEN_AI_USERNAME=oauth2accesstoken
export UV_INDEX_GEN_AI_PASSWORD="$(gcloud auth print-access-token)"

3. Quick setup

Run:

make setup

4. Activate virtual environment

source .venv/bin/activate

Local development utilities

Use these Makefile commands:

Install uv

make install-uv

Install pre-commit

make install-pre-commit

Install dependencies

make install

Update dependencies

make update

Run tests

make test

Run unit tests and model-free integration tests without downloading neural checkpoints:

uv run pytest

The download-backed Indonesian model tests are opt-in. To include them (requires network access and time to download the checkpoint and initialize its inference backend):

RUN_REAL_MODEL_TESTS=1 uv run pytest

Use uv run pytest -rs to display skipped-test requirements.


Usage

from gllm_privacy.pii_detector import TextAnalyzer, TextAnonymizer
from gllm_privacy.pii_detector.constants import Entities
from gllm_privacy.pii_detector.anonymizer import Operation
from asyncio import run

text = """
    contoh nomor ktp 3525011212941001
    repeat nomor ktp 3525011212941001
    contoh email john.doe@example.com
    contoh nomor telepon +628121729819 dan 0812898029384.
    contoh npwp 01.123.456.7-891.234
"""
text_analyzer = TextAnalyzer()
entities = [Entities.EMAIL_ADDRESS, Entities.KTP, Entities.NPWP, Entities.PHONE_NUMBER]

text_anonymizer = TextAnonymizer(text_analyzer)
anonymized_text = run(text_anonymizer.run(text=text, entities=entities))
print(anonymized_text)

deanonymized_text = run(text_anonymizer.run(text=text, entities=entities, operation=Operation.DEANONYMIZE))
print(deanonymized_text)

Use TransformersRecognizer or ProsaRemoteRecognizer to detect person, organization, or location entities in Bahasa Indonesia text. For example:

from gllm_privacy.pii_detector.recognizer.config import CAHYA_BERT_CONFIGURATION
from gllm_privacy.pii_detector.recognizer.transformers_recognizer import TransformersRecognizer
from gllm_privacy.pii_detector import TextAnalyzer, TextAnonymizer
from gllm_privacy.pii_detector.constants import Entities

# Load the model, if you run it for the first time, it will download the model from the Hugging Face model hub
transformers_recognizer = TransformersRecognizer(
  model_path=CAHYA_BERT_CONFIGURATION.get("DEFAULT_MODEL_PATH"),
  supported_entities=CAHYA_BERT_CONFIGURATION.get("PRESIDIO_SUPPORTED_ENTITIES"),
)
transformers_recognizer.load_transformer(**CAHYA_BERT_CONFIGURATION)
analyzer = TextAnalyzer(additional_recognizers=[transformers_recognizer])

text = "John Doe adalah seorang karyawan PT ABCD yang berlokasi di Jakarta."
text_analyzer = TextAnalyzer(additional_recognizers=[transformers_recognizer])
entities = [Entities.PERSON, Entities.LOCATION]

text_anonymizer = TextAnonymizer(text_analyzer)
anonymized_text = text_anonymizer.anonymize(text=text, entities=entities)
print(anonymized_text)

deanonymized_text = text_anonymizer.deanonymize(text=text)
print(deanonymized_text)

Detecting brand names

BRAND_NAME is a supported entity. Like PERSON, it is detected by a model-backed recognizer instead of a built-in regex pattern. Point the model's brand label at BRAND_NAME in MODEL_TO_PRESIDIO_MAPPING, add BRAND_NAME to supported_entities, then request it during analysis or anonymization:

from gllm_privacy.pii_detector import TextAnalyzer, TextAnonymizer
from gllm_privacy.pii_detector.constants import Entities
from gllm_privacy.pii_detector.recognizer.config import CAHYA_BERT_CONFIGURATION
from gllm_privacy.pii_detector.recognizer.transformers_recognizer import TransformersRecognizer

configuration = {
    **CAHYA_BERT_CONFIGURATION,
    "PRESIDIO_SUPPORTED_ENTITIES": [*CAHYA_BERT_CONFIGURATION["PRESIDIO_SUPPORTED_ENTITIES"], "BRAND_NAME"],
    "MODEL_TO_PRESIDIO_MAPPING": {**CAHYA_BERT_CONFIGURATION["MODEL_TO_PRESIDIO_MAPPING"], "BRD": "BRAND_NAME"},
}

brand_recognizer = TransformersRecognizer(
    model_path="<YOUR_BRAND_NER_MODEL>",
    supported_entities=configuration["PRESIDIO_SUPPORTED_ENTITIES"],
)
brand_recognizer.load_transformer(**configuration)

text = "Saya memakai sepatu Nike."
text_analyzer = TextAnalyzer(additional_recognizers=[brand_recognizer])
text_anonymizer = TextAnonymizer(text_analyzer, add_default_faker_operators=True)
entities = [Entities.BRAND_NAME]

anonymized_text = text_anonymizer.anonymize(text=text, entities=entities)
print(anonymized_text)

print(text_anonymizer.deanonymize(text=anonymized_text))

With add_default_faker_operators=True, BRAND_NAME values are pseudo-anonymized with Faker company names (fake.company()). Without it, they are replaced by the default <BRAND_NAME_n> placeholder.

The brand recognizer also accepts LINE_BREAK_TOKEN and CHUNK_SIZE:

  • LINE_BREAK_TOKEN (str | None, default None): token the model was trained on to represent a line break (for example "→"). When set, every "\n" in the input is replaced by " <token> " before inference and detected offsets are mapped back to the original text. Newlines remain intact when the model predicts separate entities per line; this is not enforced by the mapper. Leave it unset for models trained without a break token. The recognizer passes their input through unchanged. A literal token already present in the text is preserved and may split a model span. Conversely, a model span crossing an inserted token includes the original newline, so masking that span removes the line break. Such spans are not split into per-line results.
  • CHUNK_SIZE (int): maximum tokens per chunk, including special tokens. Set it to the model's real limit (for example 512 for XLM-R based checkpoints) so long multi-line documents are chunked instead of truncated.

TransformersRecognizer backends

Choose the inference backend with OPTIMUM_BACKEND in the configuration passed to load_transformer.

Available backends

OPTIMUM_BACKEND Runtime Extra to install
auto (default) The best available: ONNX Runtime with CUDA, then ONNX Runtime on CPU, then Apple Silicon MPS, then standard transformers Any of the extras below
onnx ONNX Runtime with the CPU provider onnx
cuda ONNX Runtime with the CUDA provider onnx-cuda
openvino OpenVINO optimum-openvino
mps PyTorch on Apple Silicon MPS transformers
transformers Standard transformers pipeline transformers

The onnx and cuda backends run ONNX Runtime and the tokenizers library directly. They do not need PyTorch, Transformers, or Optimum, so install only the onnx or onnx-cuda extra to keep those packages out of the process. If PyTorch is installed, spaCy still imports it when Presidio loads, whichever backend you choose.

The ONNX backends load a local directory that contains model.onnx, tokenizer.json, config.json, and tokenizer_config.json or special_tokens_map.json, such as the output of optimum-cli export onnx --task token-classification. The last two files name the padding and unknown tokens. Keep model.onnx next to its external weight file, if it has one. The ONNX backends do not download models or convert PyTorch checkpoints. For a Hugging Face Hub ID or a PyTorch checkpoint, the recognizer falls back to the transformers backend when Transformers is installed. Otherwise, it raises the ONNX loading error.

When the requested backend is not available, the recognizer logs a warning and falls back: onnx and cuda fall back to transformers, cuda without the CUDA provider falls back to onnx, openvino falls back to onnx, then to transformers, and mps without Apple Silicon falls back to the standard CPU pipeline. If ONNX Runtime lists the CUDA provider but cannot run the model on it, ONNX Runtime runs the model on the CPU, and get_pipeline_info() reports the onnx backend.

Configuration options

config = {
    **CAHYA_BERT_CONFIGURATION,
    "OPTIMUM_BACKEND": "auto",              # "auto", "onnx", "cuda", "openvino", "mps", "transformers"
    "OPTIMUM_DEVICE": "auto",               # "auto", "cuda", "mps", "cpu"
    "ONNX_INTRA_OP_THREADS": 0,             # 0 lets ONNX Runtime decide
    "ONNX_INTER_OP_THREADS": 0,             # 0 lets ONNX Runtime decide
    "ONNX_ENABLE_CPU_MEM_ARENA": True,
    "OPENVINO_PERFORMANCE_HINT": "THROUGHPUT",  # "THROUGHPUT" or "LATENCY"
    "OPENVINO_NUM_STREAMS": "AUTO",
    "OPENVINO_INFERENCE_NUM_THREADS": 0,    # 0 lets OpenVINO decide
}

Usage example

from gllm_privacy.pii_detector import TextAnalyzer
from gllm_privacy.pii_detector.recognizer.config import CAHYA_BERT_CONFIGURATION
from gllm_privacy.pii_detector.recognizer.transformers_recognizer import TransformersRecognizer

config = {**CAHYA_BERT_CONFIGURATION, "OPTIMUM_BACKEND": "onnx", "CHUNK_SIZE": 512}

transformers_recognizer = TransformersRecognizer(
    model_path="<LOCAL_ONNX_MODEL_DIRECTORY>",
    supported_entities=config["PRESIDIO_SUPPORTED_ENTITIES"],
)
transformers_recognizer.load_transformer(**config)

pipeline_info = transformers_recognizer.get_pipeline_info()
print(f"Backend: {pipeline_info['backend']}")
print(f"Device: {pipeline_info['device']}")
print(f"Optimizations: {pipeline_info['optimizations']}")

# Use as before
analyzer = TextAnalyzer(additional_recognizers=[transformers_recognizer])

To use ProsaRemoteRecognizer, replace <PROSA_API_URL> and <PROSA_API_KEY> with valid values:

from gllm_privacy.pii_detector.recognizer.prosa_remote_recognizer import ProsaRemoteRecognizer
from gllm_privacy.pii_detector import TextAnalyzer, TextAnonymizer
from gllm_privacy.pii_detector.constants import Entities

text = "John Doe adalah seorang karyawan PT ABCD yang berlokasi di Jakarta."
prosa_recognizer = ProsaRemoteRecognizer('<PROSA_API_URL>', '<PROSA_API_KEY>')
text_analyzer = TextAnalyzer(additional_recognizers=[prosa_recognizer])
entities = [Entities.PERSON, Entities.LOCATION]

text_anonymizer = TextAnonymizer(text_analyzer)
anonymized_text = text_anonymizer.anonymize(text=text, entities=entities)
print(anonymized_text)

deanonymized_text = text_anonymizer.deanonymize(text=text)
print(deanonymized_text)

Protecting PII around a component

PrivacyComponent wraps a gllm_core.schema.Component. On each call, it masks the selected arguments, calls the wrapped component with the masked values, and restores the known placeholders in the result. The wrapper accepts the same arguments as the wrapped component, so you can use it anywhere the wrapped component works.

from gllm_privacy.backend import TextAnonymizerBackend
from gllm_privacy.component import PrivacyComponent
from gllm_privacy.pii_detector import TextAnalyzer

private_synthesizer = PrivacyComponent(
    component=response_synthesizer,
    backend=TextAnonymizerBackend(
        text_analyzer=TextAnalyzer(),
        entities=["EMAIL_ADDRESS", "PHONE_NUMBER"],
        language="id",
    ),
    mask_inputs=["query", "chunks"],
    restore_output=True,
)

answer = await private_synthesizer.run(query=user_query, chunks=retrieved_chunks)

The wrapper also works in a pipeline with the existing step() function. gllm-pipeline needs no privacy-specific step. mask_inputs names the component's arguments, not the pipeline state keys.

from gllm_pipeline.steps import step

answer_step = step(
    component=private_synthesizer,
    input_map={"query": "user_query", "chunks": "retrieved_chunks"},
    output_state="answer",
)

Each call opens its own masking session. The selected arguments and the result share that session's mapping, so a repeated value gets the same placeholder in every argument. Concurrent calls never share a mapping, and no mapping outlives its call.

The wrapper masks and restores these values:

  • Strings.
  • Lists, tuples, and dicts of supported values. The wrapper keeps their type and structure, and keeps dict keys as they are.
  • Chunk objects. The wrapper masks the text in content and additional_context, and keeps the ID, metadata, and score. A subclass of Chunk needs a PrivacyValueAdapter, because it may add text fields that the wrapper does not know.
  • None and booleans. Restoring also keeps ints and floats.

Any other value raises UnsupportedValueError. The wrapper never converts an unknown object to text and never passes it through unmasked. To support a type, pass a PrivacyValueAdapter in value_adapters.

restore_output controls the result:

  • True restores every supported value in the result.
  • A list of field names restores only those fields of a dict result. Fields that the result does not have are skipped. A result that is not a dict raises UnsupportedValueError.
  • False returns the result with its placeholders.

The wrapper fails closed. If masking fails, it does not call the wrapped component. If restoring fails, it discards the result. In both cases it raises a BasePrivacyError, so catch that class to handle every masking or restoring failure:

  • A privacy error that the backend raises propagates unchanged, so you can still retry a retryable one. With TextAnonymizerBackend, a detection failure arrives as PrivacyRuntimeError or as a remote recognizer error, such as RemoteRecognizerTimeoutError.
  • Any other exception from the backend becomes MaskingError or RestorationError. A custom backend that raises plain exceptions produces these errors.

Errors from the wrapped component and cancellation propagate unchanged.

The wrapper's trace span records "[REDACTED]" instead of its input and output. When component I/O capture is on, the wrapped component's span records the masked input and output. The wrapper restores only the returned value. Events that the wrapped component streams through event_emitter still contain placeholders. The wrapper does not mask new PII that the wrapped component generates.

TextAnonymizerBackend runs detection in a worker thread, so it does not block the event loop. To use another masking engine, such as a remote privacy service, implement PrivacyBackend and PrivacySession from gllm_privacy.backend.

Error handling

Errors raised by gllm-privacy subclass BasePrivacyError, which is built on BaseError from gllm-core. Each error has a stable code, a message that you can show to users, a debug_info dict for logs, and a recovery dict that says whether a retry can succeed. str(error) returns only the message. Diagnostics contain metadata only. They exclude external messages, URLs, source frames, request payloads, response bodies, and headers. Unknown language values do not enter diagnostics.

The default messages are written for end users. They do not name the library, the model, or a setting. The developer fix for each code is in the table below. Some errors include a library-authored explanation in debug_info.get("reason"). This field is optional. Normalized fallback errors identify the original error type instead.

When a GDP Labs NER API call fails with an HTTP status, debug_info also holds upstream_error_code (the public code of the NER API error response, such as INVALID_ENTITY_TYPE) and upstream_request_id (its request_id). Use the request ID to find the NER API log record. Each field is present only when the response has the {"error": {...}} envelope and the value has the expected format: an upper-case code of up to 64 characters, or a UUID.

Branch on code, not on the message. Each error that existed before the error codes keeps its previous builtin base, such as ValueError, so existing except clauses keep working. Newer errors have no builtin base.

from gllm_privacy.exceptions import BasePrivacyError, BaseRemoteRecognizerError

try:
    results = text_analyzer.analyze(text=text, language="id", entities=entities)
except BaseRemoteRecognizerError as error:
    # A remote NER service failed. The text was not checked, so do not treat it as PII-free.
    logger.warning("PII detection failed: %s", error.code, extra={"debug_info": error.debug_info})
    # Retry only through the bounded caller policy described below.
    raise
except BasePrivacyError as error:
    logger.error("PII detection failed: %s", error.code, extra={"debug_info": error.debug_info})
    raise

Remote recognizers (ProsaRemoteRecognizer, GDPLabsNerApiRemoteRecognizer, and GDPLabsNerApiRemoteRecognizerAsync) use specific remote error codes for known transport and response failures. Unexpected remote failures use the non-retryable PrivacyRuntimeError fallback. TextAnalyzer.analyze and TextAnonymizer.anonymize also normalize unexpected operation failures. Transformers inference uses ModelInferenceError. Backend creation uses ModelLoadError. None of these boundaries return an empty result in place of a failure. Existing typed errors retain their identity. These boundaries do not convert cancellation or process-control signals into Privacy errors.

Default tracebacks suppress raw upstream exception context. Python still retains the original context in memory. Do not serialize __context__, exception objects, local variables, or source frames to a log or response.

Service log policy

The library retains safe operational logs for dependency availability, backend selection, and model lifecycle events. These logs exclude raw exceptions, model paths, detected text, and arbitrary configuration values. Failure-path logs use fixed messages. A secondary log failure does not interrupt backend fallback or best-effort client cleanup. The service owns its log sinks and dependency log policy. Existing Presidio log suppression remains unchanged. HTTP clients can put full URLs in INFO or DEBUG logs. Model dependencies can expose model paths or input values. Use WARNING or higher for HTTP client logs. Disable raw dependency output unless the service applies a reviewed allowlist. Do not treat this level policy as a redactor for arbitrary dependency warnings. Use only error.code, error.message, and reviewed diagnostic fields at the service boundary. The service must exclude request bodies, headers, and raw exception text from all sinks.

Bounded retries and escalation

TextAnalyzer.analyze raises UnsupportedLanguageError when no recognizer supports the language, and InvalidInputError when no recognizer can detect any of the requested entities.

Only the remote timeout, connection, rate limit and server errors are retryable. A rate limit or server error also carries recovery["retry_after_seconds"] when the service sends a valid Retry-After header. The library does not retry automatically.

Use the executable caller example for an idempotent synchronous operation. It permits three total attempts. Without Retry-After, it waits one second, then two seconds. It honors provider delays up to 30 seconds. For a longer delay, stop without an early retry and contact the service owner. Each request also needs a finite transport timeout. These limits bound attempts and waits, not the complete request duration. Do not retry authentication, TLS, configuration, input, model, or unexpected runtime failures without a corrective action.

When attempts expire, stop the operation. Do not return unchecked text as PII-free. Give the user the safe error message. Give the service owner the code, version, and metadata-only diagnostics. For authentication or TLS failures, contact the credential or certificate owner before another attempt. For repeated connection, timeout, rate-limit, or server failures, contact the remote service owner. For unexpected failures, contact the Privacy maintainer.

Code Class Builtin base Retryable Meaning What to do
GLLM-PRIV-INVALID-INPUT InvalidInputError ValueError No text or language is missing, empty, or not a string, or no recognizer can detect any of the requested entities. Pass a non-empty string. Request entities that the analyzer supports for the language.
GLLM-PRIV-INVALID-CONFIG InvalidConfigError ValueError No A configuration value is invalid, such as CHUNK_BATCH_SIZE <= 0, a missing model_path, an mTLS certificate without its key, a token limit that is too small, or a PrivacyComponent whose mask_inputs names an argument the wrapped component does not accept. Fix the parameter named in debug_info["parameter"] or debug_info["argument"]. debug_info["reason"] holds the detail when there is one.
GLLM-PRIV-UNSUPPORTED-LANGUAGE UnsupportedLanguageError ValueError No The language is not supported by the NLP engine or recognizer. Use one of the languages listed in the message.
GLLM-PRIV-UNSUPPORTED-TOKENIZER UnsupportedTokenizerError ValueError No The tokenizer cannot provide character offsets for chunking. Read debug_info["reason"]. Use a fast Hugging Face tokenizer.
GLLM-PRIV-MISSING-DEPENDENCY MissingDependencyError ImportError No An optional dependency, such as transformers or flair, is not installed. Install the matching gllm-privacy extra.
GLLM-PRIV-MODEL-LOAD ModelLoadError RuntimeError No The NER tokenizer, model, or pipeline cannot be loaded. Check the model path and access to the model files.
GLLM-PRIV-MODEL-INFERENCE ModelInferenceError RuntimeError No The NER model failed while predicting entities. Check the model installation and the available memory.
GLLM-PRIV-MODEL-OUTPUT ModelOutputError ValueError No The NER model returned results that do not match its input. Read debug_info["reason"]. Check that the model is a token classification model.
GLLM-PRIV-RUNTIME PrivacyRuntimeError RuntimeError No An internal step failed unexpectedly. Report the code, package version, and metadata-only debug_info to the gllm-privacy maintainers. Do not retry without a corrective action.
GLLM-PRIV-REMOTE-TIMEOUT RemoteRecognizerTimeoutError RuntimeError Yes The remote NER service did not respond in time. Retry later, or increase the timeout.
GLLM-PRIV-REMOTE-CONNECTION RemoteRecognizerConnectionError RuntimeError Yes The remote NER service cannot be reached. Check the URL and network access, then retry.
GLLM-PRIV-REMOTE-TLS RemoteRecognizerTLSError RuntimeError No The TLS certificates could not be loaded, or the TLS handshake failed, such as a missing certificate file, a rejected client certificate or an unverifiable server certificate. Check the client certificate, key, and CA certificate. Do not retry as is.
GLLM-PRIV-REMOTE-AUTH RemoteRecognizerAuthError RuntimeError No The service rejected the credentials (HTTP 401 or 403). Fix the API key or client certificate. Do not retry as is.
GLLM-PRIV-REMOTE-RATE-LIMIT RemoteRecognizerRateLimitError RuntimeError Yes The service throttled the request (HTTP 429). Wait, then retry.
GLLM-PRIV-REMOTE-SERVER RemoteRecognizerServerError RuntimeError Yes The service failed on its side (HTTP 5xx). Retry later. If it keeps failing, contact the service owner.
GLLM-PRIV-REMOTE-REQUEST RemoteRecognizerRequestError RuntimeError No The request failed for another reason, such as another HTTP 4xx status. Check the recognizer configuration.
GLLM-PRIV-REMOTE-INVALID-RESPONSE RemoteRecognizerInvalidResponseError RuntimeError No The service returned a response that is not JSON, misses required entity keys, or has an entity without offsets. Check that the URL points to a compatible NER API.
GLLM-PRIV-UNSUPPORTED-VALUE UnsupportedValueError None No PrivacyComponent has no rule to mask a selected argument or restore the result, such as a number, binary chunk content, or a custom object. Read debug_info["argument"] and debug_info["value_type"]. Pass text, or add a PrivacyValueAdapter for the type.
GLLM-PRIV-INVALID-TOOL-ARGUMENTS InvalidToolArgumentsError None No A PrivacyComponent tool was called with arguments that the wrapped main method does not accept, such as a missing required argument or an unexpected one. The wrapped component was not called. Call the tool with the arguments in its input schema.
GLLM-PRIV-MASKING MaskingError None No The PrivacyComponent backend raised an exception that is not a privacy error while masking. The wrapped component was not called. Read debug_info["error_type"], then check the backend.
GLLM-PRIV-RESTORATION RestorationError None No The PrivacyComponent backend raised an exception that is not a privacy error while restoring the result. The result was discarded. Read debug_info["error_type"], then check the backend.

Metadata

Release files for gllm-privacy-binary 0.4.45

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Inconsistent provenance

These files originate from different repositories or configurations.

We recommend inspecting each repository and configuration before proceeding. View details.

Built distributions (wheels)

Table of built distributions (wheels) for gllm-privacy-binary 0.4.45
File Actions
gllm_privacy_binary-0.4.45-cp313-cp313-win_amd64.whl CPython 3.13 CPython 3.13 Windows x86-64 Details for gllm_privacy_binary-0.4.45-cp313-cp313-win_amd64.whl
gllm_privacy_binary-0.4.45-cp313-cp313-manylinux_2_28_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.28+ x86-64 Details for gllm_privacy_binary-0.4.45-cp313-cp313-manylinux_2_28_x86_64.whl
gllm_privacy_binary-0.4.45-cp313-cp313-macosx_13_0_arm64.whl CPython 3.13 CPython 3.13 macOS 13.0+ ARM64 Details for gllm_privacy_binary-0.4.45-cp313-cp313-macosx_13_0_arm64.whl
gllm_privacy_binary-0.4.45-cp312-cp312-win_amd64.whl CPython 3.12 CPython 3.12 Windows x86-64 Details for gllm_privacy_binary-0.4.45-cp312-cp312-win_amd64.whl
gllm_privacy_binary-0.4.45-cp312-cp312-manylinux_2_28_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ x86-64 Details for gllm_privacy_binary-0.4.45-cp312-cp312-manylinux_2_28_x86_64.whl
gllm_privacy_binary-0.4.45-cp312-cp312-macosx_13_0_arm64.whl CPython 3.12 CPython 3.12 macOS 13.0+ ARM64 Details for gllm_privacy_binary-0.4.45-cp312-cp312-macosx_13_0_arm64.whl

Total release size: 5.6 MB

Release files / gllm_privacy_binary-0.4.45-cp313-cp313-win_amd64.whl

Inconsistent provenance

This file belongs to a release with inconsistent provenance: the files in this release originate from different repositories or configurations.

We recommend inspecting each repository and configuration before proceeding. View details.

Download URL gllm_privacy_binary-0.4.45-cp313-cp313-win_amd64.whl
Size 782.5 kB
Tags CPython 3.13 Windows x86-64
SHA-256 checksum
How to use checksums
e7b6e1299e9cb1670b28e9bc08f934416b0b58713bd2dc63e6dd0cb476d99a39
BLAKE2b-256 checksum
How to use checksums
9e6eee396842a23662ac545b14bfa2755f7e26a0eea15e1d60dce426a32b89a2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

Release files / gllm_privacy_binary-0.4.45-cp313-cp313-manylinux_2_28_x86_64.whl

Inconsistent provenance

This file belongs to a release with inconsistent provenance: the files in this release originate from different repositories or configurations.

We recommend inspecting each repository and configuration before proceeding. View details.

Download URL gllm_privacy_binary-0.4.45-cp313-cp313-manylinux_2_28_x86_64.whl
Size 1.2 MB
Tags CPython 3.13 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
924e5e67eac02a74a56e2972654a268ae6233cd9f0eb4bab9ab0cc814a7d4e40
BLAKE2b-256 checksum
How to use checksums
7f33111f78016d5e7bd62a8ff867b2522686703de1f709d1cef032a18ae44b2c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.4 {"installer":{"name":"uv","version":"0.13.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"AlmaLinux","version":"8.10","id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by Google Cloud, verified by PyPI on Nov 16, 2026.

Transparency log

Release files / gllm_privacy_binary-0.4.45-cp313-cp313-macosx_13_0_arm64.whl

Inconsistent provenance

This file belongs to a release with inconsistent provenance: the files in this release originate from different repositories or configurations.

We recommend inspecting each repository and configuration before proceeding. View details.

Download URL gllm_privacy_binary-0.4.45-cp313-cp313-macosx_13_0_arm64.whl
Size 866.4 kB
Tags CPython 3.13 macOS 13.0+ ARM64
SHA-256 checksum
How to use checksums
6ee59b09ecb3f50705b29ac4ee817357885d07b1f1848f98b2c53796b14b336a
BLAKE2b-256 checksum
How to use checksums
42ef3eb88ecdd2affab95045f6bf0fe22b5ef67cc6748a01b2128753c822ac45
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

Release files / gllm_privacy_binary-0.4.45-cp312-cp312-win_amd64.whl

Inconsistent provenance

This file belongs to a release with inconsistent provenance: the files in this release originate from different repositories or configurations.

We recommend inspecting each repository and configuration before proceeding. View details.

Download URL gllm_privacy_binary-0.4.45-cp312-cp312-win_amd64.whl
Size 780.7 kB
Tags CPython 3.12 Windows x86-64
SHA-256 checksum
How to use checksums
73f8be9349136d4c8fb64c07d5aa8620495ac94309d6b3aba9d9585cf9b076a3
BLAKE2b-256 checksum
How to use checksums
2a8a07d976c8230f58e0639981c61bbab194dbacf863a3ada8dbbe6092c779dd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

Release files / gllm_privacy_binary-0.4.45-cp312-cp312-manylinux_2_28_x86_64.whl

Inconsistent provenance

This file belongs to a release with inconsistent provenance: the files in this release originate from different repositories or configurations.

We recommend inspecting each repository and configuration before proceeding. View details.

Download URL gllm_privacy_binary-0.4.45-cp312-cp312-manylinux_2_28_x86_64.whl
Size 1.2 MB
Tags CPython 3.12 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
fdbf5ce74fea0d73563a358cd056f73300fdace8ca06f7ac3c6e799fdab52d6a
BLAKE2b-256 checksum
How to use checksums
c716e50f7627939462f1fb8b8589a61fd36369e3cd1e615b5a38665f1a4d06f1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.4 {"installer":{"name":"uv","version":"0.13.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"AlmaLinux","version":"8.10","id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by Google Cloud, verified by PyPI on Nov 16, 2026.

Transparency log

Release files / gllm_privacy_binary-0.4.45-cp312-cp312-macosx_13_0_arm64.whl

Inconsistent provenance

This file belongs to a release with inconsistent provenance: the files in this release originate from different repositories or configurations.

We recommend inspecting each repository and configuration before proceeding. View details.

Download URL gllm_privacy_binary-0.4.45-cp312-cp312-macosx_13_0_arm64.whl
Size 840.7 kB
Tags CPython 3.12 macOS 13.0+ ARM64
SHA-256 checksum
How to use checksums
0151037b39163ffe0f25f231ad4a0285b624e272158763c6143d1432da24e007
BLAKE2b-256 checksum
How to use checksums
e1db610e0a0314b4a4ddb30ecbabdff777d2cad5208d9403099d7c775df1a47a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

Security for gllm-privacy-binary 0.4.45

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Inconsistent provenance

The release files originate from multiple, inconsistent repositories.

While this could reflect a legitimate choice by the project maintainers, it may also indicate that the release has been compromised.

Repository/Account

Select from 6 files

Attestation for gllm_privacy_binary-0.4.45-cp313-cp313-win_amd64.whl

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page