FutureAI Releases Masterpiece Our Generative Application Architecture Aimed at Achieving FGS.
Read more
Masterpiece is our agentic architecture for developing generative applications. It leverages a dual dataset architecture specially designed for privacy and security, fast processing of data and autonomous generation for your interface.
There are three parts to Masterpiece. First, select the version first of Leo 1 you want to use with Masterpiece. You can use our Leo 1 Base model that is a fine-tuned version of Llama 70B specialized for contextualization. You can LoRa adapt our Leo 1 Base model for a more refined version, or you can fine-tune our Leo 1 Base model for the most performant results.
Leo 1 Base
Leo 1 Developer LoRa Trained
Leo 1 Developer Fine-Tuned
Once you have decided which version of Leo 1 you will use with Masterpiece, you are ready to implement our SDK for prompting users to get a generative experience with your application. Once you prompt users they will connect their data to FutureAI for processing.
Get a Generative Experience with FutureAI.
The second part of Masterpiece is our User Data Pipeline where we extract the most sensitive parts of a user’s data that we don’t use for generation. You can see all of the categories bellow that we remove when sifting a user’s data before it is vectorized and ingested for contextualization.
Content that is rude, disrespectful, or unreasonable.
Negative or harmful comments targeting identity and/or protected attributes.
Describes scenarios depicting violence against an individual or group, or general descriptions of gore.
Contains references to sexual acts or other lewd content.
Insulting, inflammatory, or negative comment towards a person or a group of people.
Obscene or vulgar language such as cursing.
Human deaths, tragedies, accidents, disasters, and self-harm.
Content that mentions knives, guns, personal weapons, and accessories such as ammunition, holsters, etc.
Human health, including: Health conditions, diseases, and disorders Medical therapies, medication, vaccination, medical practices, and resources for healing, including support groups.
Belief systems that deal with the possibility of supernatural laws and beings; religion, faith, belief, spiritual practice, churches, and places of worship. Includes astrology and the occult.
Recreational and illicit drugs; drug paraphernalia and cultivation, headshops, etc. Includes medicinal use of drugs typically used recreationally (e.g. marijuana).
War, military conflicts, and major physical conflicts involving large numbers of people. Includes discussion of military services, even if not directly related to a war or conflict.
Consumer and business financial services, such as banking, loans, credit, investing, and insurance.
Political news and media; discussions of social, governmental, and public policy.
Law-related content, including law firms, legal information, primary legal materials, paralegal services, legal publications and technology, expert witnesses, litigation consultants, and other legal service providers.
The third and final part of Masterpiece is where we contextualize a user’s data for pairing it with your application’s data to generate the most relevant candidates to be presented to the user in their interface. All of this processing happens within 5,000ms from the moment we ingest a user’s data to when we generate the interface for the user for your application.
Text & Multi - Modal Embeddings
Clustering & Pairing User and Developer Data
Leo 1 Contextulization