Skip to main content

Guardrails module for Ragbits components

Project description

Ragbits Guardrails

Ragbits Guardrails is a Python package that contains utilities for ensuring the safety and relevance of responses generated by Ragbits components.

Installation

You can install the latest version of Ragbits Guardrails using pip:

pip install ragbits-guardrails

Quickstart

Example of using the OpenAI Moderation Guardrail to verify a message:

import asyncio
from ragbits.guardrails.base import GuardrailManager, GuardrailVerificationResult
from ragbits.guardrails.openai_moderation import OpenAIModerationGuardrail


async def verify_message(message: str) -> list[GuardrailVerificationResult]:
    manager = GuardrailManager([OpenAIModerationGuardrail()])
    return await manager.verify(message)


if __name__ == '__main__':
    print(asyncio.run(verify_message("Test message")))

Documentation

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ragbits_guardrails-0.16.0.tar.gz (3.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ragbits_guardrails-0.16.0-py3-none-any.whl (3.7 kB view details)

Uploaded Python 3

File details

Details for the file ragbits_guardrails-0.16.0.tar.gz.

File metadata

  • Download URL: ragbits_guardrails-0.16.0.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.17

File hashes

Hashes for ragbits_guardrails-0.16.0.tar.gz
Algorithm Hash digest
SHA256 5c3a0b31cd17ed2de3602e9db69a7dc6d4b2ef7275562e6f789d17ca0c1aec59
MD5 1a54dcf12cfb6bcb7dfae6ae382a050c
BLAKE2b-256 03931d505017ef14b8f99df118974186f97b48e18c09344409c7127efe8970ef

See more details on using hashes here.

File details

Details for the file ragbits_guardrails-0.16.0-py3-none-any.whl.

File metadata

File hashes

Hashes for ragbits_guardrails-0.16.0-py3-none-any.whl
Algorithm Hash digest
SHA256 db162a4f50745c243d91186ed4ee254c0e6e080ae2f0fd6c5e385e8cfb7887ed
MD5 15408f2ed7d9407917b4309f66323211
BLAKE2b-256 51645f6e1c6cd0fb2e3bd3f12253c2260f72c49401cc33e7e7efbc756abc4e04

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page