Developers can now use Nvidia‘s recently launched open-source software to steer generative AI applications towards producing relevant and coherent text responses. Named NeMo Guardrails, the software has been designed to guarantee the precision, relevance, appropriateness and security of intelligent applications utilising large language models (LLMs).
This software can also provide users with all the necessary codes, examples, and documentation that they’ll need to incorporate safety measures into their text-generating AI applications.
According to the GPU manufacturer, Nemo Guardrails, “Comes as many industries are adopting LLMs, the powerful engines behind these AI apps. They’re answering customers’ questions, summarising lengthy documents, even writing software and accelerating drug design.”
A path towards safe AI use
“Safety in generative AI is an industry-wide concern. Nvidia designed NeMo Guardrails to work with all LLMs, such as OpenAI’s ChatGPT,” said Nvidia. The company adds that Nemo Guardrails will allow developers to align LLM-powered apps so they’re safe and, “Stay within the domains of a company’s expertise.”
The software also allows developers to set up three kinds of boundaries including Topical guardrails that stop apps from veering off into undesired locations; Safety guardrails that ensure apps respond with accurate, appropriate information; and Security guardrails that restrict apps to making connections only to external third-party applications known to be safe.
“Virtually every software developer can use NeMo Guardrails — no need to be a machine learning expert or data scientist. They can create new rules quickly with a few lines of code.”
Open source availability
The GPU maker is incorporating NeMo Guardrails into its NeMo framework which according to Nvidia, has everything users will need to train and tune and tune language models using its proprietary data. The Santa Clara company said, “Much of the NeMo framework is already available as open source code on GitHub. Enterprises also can get it as a complete and supported package, part of the Nvidia AI Enterprise software platform.”
In addition, NeMo is also available as a service and as part of NvidiAI Foundations, a family of cloud services for businesses that want to create and run custom generative AI models based on their own datasets and domain knowledge.
“Together, our efforts on guardrails will help companies keep their smart services aligned with safety, privacy and security requirements so these engines of innovation stay on track” Nvidia concluded.
Isa Muhammad is a writer and video game journalist covering many aspects of entertainment media including the film industry. He's steadily writing his way to the sharp end of journalism and enjoys staying informed. If he's not reading, playing video games or catching up on his favourite TV series, then he's probably writing about them.
