Skip to main content

Openlayer Guardrails

Open source guardrail implementations that work with Openlayer tracing.

Installation

pip install openlayer-guardrails

Usage

Standalone Usage

from openlayer_guardrails import PIIGuardrail

# Create guardrail
pii_guard = PIIGuardrail(
    block_entities={"CREDIT_CARD", "US_SSN"},
    redact_entities={"EMAIL_ADDRESS", "PHONE_NUMBER"}
)

# Check inputs manually
data = {"message": "My email is john@example.com and SSN is 123-45-6789"}
result = pii_guard.check_input(data)

if result.action.value == "block":
    print(f"Blocked: {result.reason}")
elif result.action.value == "modify":
    print(f"Modified data: {result.modified_data}")

With Openlayer Tracing

from openlayer_guardrails import PIIGuardrail
from openlayer.lib.tracing import trace

# Create guardrail
pii_guard = PIIGuardrail()

# Apply to traced functions
@trace(guardrails=[pii_guard])
def process_user_data(user_input: str):
    return f"Processed: {user_input}"

# PII is automatically handled
result = process_user_data("My email is john@example.com")
# Output: "Processed: My email is [EMAIL-REDACTED]"

Toxicity Guardrail (Brazilian Portuguese)

Detects toxic content in Brazilian Portuguese using the ToxiGuardrailPT model.

pip install 'openlayer-guardrails[toxicity]'
from openlayer_guardrails import ToxicityPTGuardrail

# Create guardrail (default threshold=0.0; positive scores = safe, negative = toxic)
toxicity_guard = ToxicityPTGuardrail()

# Check inputs
result = toxicity_guard.check_input({"message": "Você é um idiota!"})
print(result.action)  # GuardrailAction.BLOCK

# Check outputs with contextual scoring (sentence-pair encoding)
result = toxicity_guard.check_output(
    output="Claro, aqui está a informação solicitada.",
    inputs={"prompt": "Me ajude com meu trabalho."},
)
print(result.action)  # GuardrailAction.ALLOW

Toxicity Guardrail (English)

Detects toxic content in English across six categories using unitary/toxic-bert.

pip install 'openlayer-guardrails[toxicity]'
from openlayer_guardrails import ToxicityENGuardrail

# Create guardrail (default threshold=0.5)
toxicity_guard = ToxicityENGuardrail()

# Check inputs
result = toxicity_guard.check_input({"message": "You are terrible and should die"})
print(result.action)  # GuardrailAction.BLOCK
print(result.metadata["triggered_categories"])
# e.g. {'toxic': 0.98, 'severe_toxic': 0.72, 'insult': 0.89, 'threat': 0.81}

# Monitor only specific categories
guard = ToxicityENGuardrail(categories={"threat", "severe_toxic"})

Handling long texts

By default, all guardrails truncate inputs to 512 tokens for fast inference. To evaluate the full text, enable chunking mode by setting max_length=None:

guard = ToxicityPTGuardrail(max_length=None)   # or ToxicityENGuardrail(max_length=None)

In chunking mode, long texts are split into overlapping 512-token windows and each window is scored independently. The most toxic score across all windows is used. Latency scales linearly with the number of chunks.

Model Limitations

Prompt Injection Guardrail

Property Value
Model meta-llama/Llama-Prompt-Guard-2-86M
Max tokens 512
Language English
Parameters 86M
Scope Input-only (outputs are not checked)

Texts longer than 512 tokens are truncated. Only the first 512 tokens are evaluated.

Toxicity Guardrail (PT-BR)

Property Value
Model nicholasKluge/ToxiGuardrailPT
Max tokens 512
Language Brazilian Portuguese
Parameters 109M
Architecture BERTimbau (bert-base-portuguese-cased)
Output type Single scalar reward score (positive = safe, negative = toxic)
Reported accuracy 70.36% (hatecheck-portuguese), 74.04% (told-br)
Scope Input and output (output uses sentence-pair encoding for context)

By default, texts longer than 512 tokens are truncated. Set max_length=None to enable chunking for full-text coverage. The model was trained on Brazilian Portuguese data and may not generalize well to European Portuguese or other languages.

Toxicity Guardrail (EN)

Property Value
Model unitary/toxic-bert
Max tokens 512 (chunking available via max_length=None)
Language English
Parameters 110M
Architecture BERT (bert-base-uncased)
Output type Multi-label probabilities across 6 categories
Categories toxic, severe_toxic, obscene, threat, insult, identity_hate
Reported AUC 0.98636 (Jigsaw Toxic Comment Challenge)
Scope Input and output

By default, texts longer than 512 tokens are truncated. Set max_length=None to enable chunking for full-text coverage. The model was trained on English data.

Metadata

Release files for openlayer-guardrails 1.0.0

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

Source distribution (sdist)

Source distribution for openlayer-guardrails 1.0.0
File Size Uploaded Provenance Actions
openlayer_guardrails-1.0.0.tar.gz 235.2 kB Without provenance Details for openlayer_guardrails-1.0.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for openlayer-guardrails 1.0.0
File Interpreter ABI Platform Actions
openlayer_guardrails-1.0.0-py3-none-any.whl Python 3 none any Details for openlayer_guardrails-1.0.0-py3-none-any.whl

Total release size: 288.6 kB

Release files / openlayer_guardrails-1.0.0.tar.gz

Download URL openlayer_guardrails-1.0.0.tar.gz
Size 235.2 kB
Tags Source
SHA-256 checksum
How to use checksums
9c7f2b98c8cbd0df1005f8379f0ebf041dbd78b04499aaa7d76fd09a9b3de98c
BLAKE2b-256 checksum
How to use checksums
47242c02d26c99d9b4a29517bec0af45fdf314b7453095471dcfd33b10b09fb9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / openlayer_guardrails-1.0.0-py3-none-any.whl

Download URL openlayer_guardrails-1.0.0-py3-none-any.whl
Size 53.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6c2ba0e9a9805c8e8b1d96ae4b887ec5533b77cbcd6d386c7efaad4da00adbcb
BLAKE2b-256 checksum
How to use checksums
cbb983bee036e307cb67a0332f98cbadf46fc878fe61bcc26186d596e3ff7ecf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for openlayer-guardrails 1.0.0

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

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.

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