Microsoft has launched NLWeb, an open project designed to simplify the creation of natural language interfaces for websites. This technology enables web publishers to turn their site into an AI-powered app, allowing users to query the contents of the site using natural language.
NLWeb is built on top of existing data formats such as Schema.org, RSS, and other semi-structured data, combining them with large language model (LLM)-powered tools. The system enhances this structured data by incorporating external knowledge from LLMs for richer user experiences.
As an open project, NLWeb is technology agnostic, supporting all major operating systems and allowing developers to choose the components that best suit their needs. This makes it easy for web publishers to create intelligent natural language interfaces for their site.
Benefits of using NLWeb include:
* Simplifying the creation of AI-powered websites
* Enabling users to query website content using natural language
* Enhancing user experiences with external knowledge from LLMs
Key adopters of NLWeb include Chicago Public Media, Common Sense Media, DDM (Allrecipes/Serious Eats), Eventbrite, and others. The NLWeb GitHub repo provides everything needed to get started, including lightweight code, documentation, connectors to popular models and vector databases, and tools for adding data in various formats.
The project was conceived and developed by R.V. Guha, a CVP and Technical Fellow at Microsoft, who is also the creator of widely used web standards such as RSS, RDF, and Schema.org.
Source: https://news.microsoft.com/source/features/company-news/introducing-nlweb-bringing-conversational-interfaces-directly-to-the-web