FutureAI Releases Masterpiece Our Generative Application Architecture Aimed at Achieving FGS.

Read more

Introducing Masterpiece

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.

Leo 1 Base, LoRa or Fine-tuned

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

Offering Users a Generative Experience

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.

Sensitive User Data Agentic 70B Sift

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.

Attributes Masterpiece Extracts Before Ingestion

Toxic

Content that is rude, disrespectful, or unreasonable.

Derogatory

Negative or harmful comments targeting identity and/or protected attributes.

Violence

Describes scenarios depicting violence against an individual or group, or general descriptions of gore.

Sexual

Contains references to sexual acts or other lewd content.

Insult

Insulting, inflammatory, or negative comment towards a person or a group of people.

Profanity

Obscene or vulgar language such as cursing.

Death, Harm & Tragedy

Human deaths, tragedies, accidents, disasters, and self-harm.

Firearms & Weapons

Content that mentions knives, guns, personal weapons, and accessories such as ammunition, holsters, etc.

Health

Human health, including: Health conditions, diseases, and disorders Medical therapies, medication, vaccination, medical practices, and resources for healing, including support groups.

Religion & Beliefs

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.

Illicit Drugs

Recreational and illicit drugs; drug paraphernalia and cultivation, headshops, etc. Includes medicinal use of drugs typically used recreationally (e.g. marijuana).

War & Conflict

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.

Financial

Consumer and business financial services, such as banking, loans, credit, investing, and insurance.

Political

Political news and media; discussions of social, governmental, and public policy.

Legal

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.

Embeddings, RAG and Leo 1 Contextualization

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

Start Building Generatively