Skip to main content

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Project description

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. Guardrails (or "rails" for short) are specific ways of controlling the output of an LLM, e.g., not talking about politics, responding in a particular way to specific user requests, following a predefined dialog path, using a particular language style, extracting structured data, etc.

Key Benefits:

- Building Trustworthy, Safe and Secure LLM Conversational Systems: The core value of
using NeMo Guardrails is the ability to write fuzzy rails to steer select conversations.
Developers can choose to define the behavior of their LLM-powered bots on certain
topics and keep their creativity un-encumbered for others!

- Connect models, chains, services, and more via actions: LLMs don't need to solve
all the challenges. NeMo Guardrails provides the ability to connect your codebase or
services to your chatbot seamlessly and securely!

Project details


Download files

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

Source Distribution

custom-guardrails-0.1.0.tar.gz (13.7 MB view hashes)

Uploaded Source

Built Distribution

custom_guardrails-0.1.0-py3-none-any.whl (13.7 MB view hashes)

Uploaded Python 3

Supported by

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