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
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
custom-guardrails-0.1.0.tar.gz
(13.7 MB
view hashes)
Built Distribution
Close
Hashes for custom_guardrails-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | be552973277dc0c06d674bd72b4b7263b72714974bffd3861ffa375c03f44e31 |
|
MD5 | e1a0c9066ba19a628ccb2a3e3ff310d5 |
|
BLAKE2b-256 | 96c0b4e3e3da9c5b98618619173a06c88edd7d56c0919d870d623e760171fe59 |