BivectorAI Python SDK
Enterprise AI safety verification for production systems.
Install
pip install bivectorai
Quick Start
from bivectorai import BivectorAI
client = BivectorAI(api_key="your-api-key")
# Scan AI output for safety issues
result = client.verify_output(
text="The model says X",
sources=["User asked Y"],
)
print(result.verdict) # PASS, REVIEW, or BLOCK
# Detect LLM injection
scan = client.scan_injection("Ignore previous instructions and...")
print(scan["verdict"]) # BLOCK or PASS
# Check for hallucinations
check = client.check_hallucination(
claim="Revenue was $10B in 2023",
evidence=[{"source": "annual_report.pdf", "text": "Revenue: $8.2B"}],
)
print(check["verdict"]) # GROUNDED or UNSUPPORTED
API Reference
verify_output(text, sources)— LLM output safety gatescan_injection(text)— prompt injection detectioncheck_hallucination(claim, evidence)— factual grounding checkdetect_pii(text)— PII detection and classificationscan_content(text, categories)— comprehensive content safetyverify_workflow(steps)— AI workflow verificationget_usage_summary(period)— usage statisticsrevoke_api_key(key_prefix)— key rotation helper
Full docs: https://bivectorai.com/docs/
1 maintainer
Metadata
1 maintainer
Release files for bivectorai 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| bivectorai-0.3.0.tar.gz | 14.2 kB | Without provenance | Details for bivectorai-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| bivectorai-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for bivectorai-0.3.0-py3-none-any.whl |
Total release size: 27.6 kB
Release files / bivectorai-0.3.0.tar.gz
| Download URL | bivectorai-0.3.0.tar.gz |
|---|---|
| Size | 14.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d3ce14776bcf452a8d26ce14878b555c2b38cc8f71f9b63c14ce3ae29121eda1
|
|
BLAKE2b-256 checksum How to use checksums |
82e9592f00a0401ef28cb03b7d4c6379b7cd26a195043160da08fcf580bda123
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Release files / bivectorai-0.3.0-py3-none-any.whl
| Download URL | bivectorai-0.3.0-py3-none-any.whl |
|---|---|
| Size | 13.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a2de79ad0ec9bf4437489dd867a7edec1542dc26f125061b533c6407c68c9468
|
|
BLAKE2b-256 checksum How to use checksums |
39ea25294dc89d7f955915b6db909af9fff43269768a7bc922c42d2d7ce6d46c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Security for bivectorai 0.3.0
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.
