HomePage
Create NFT
Collections
Chat Options
API endpoints

NeuraNFT: Tokenizing Intelligence on Constellation Metagraph

Inspiration

The inspiration for NeuraNFT stemmed from a desire to customize AI models to better suit individual needs while addressing the value distribution gap among key stakeholders in the AI ecosystem. This ecosystem comprises four primary stakeholders: data owners, model owners, hosting platforms, and end users.

We observed that the current market structure often fails to equitably distribute benefits and rewards. This realization led to the conception of NeuraNFT, a platform designed to rebalance the value proposition for all stakeholders involved. By leveraging Constellation's Metagraph technology and the Data API, NeuraNFT aims to create a more equitable, innovative, and collaborative AI ecosystem.

What it does

NeuraNFT is a decentralized AI system built on Constellation's Metagraph architecture. It addresses the growing need for personalized, secure, and decentralized artificial intelligence by combining the privacy and security of blockchain with a high-performance computing infrastructure to deploy machine learning models securely.

At its core, NeuraNFT leverages Constellation's Data API to represent AI models, including their fine-tuning data, architecture information, and training parameters. This approach enables true ownership of AI models, allowing users to buy, sell, or rent them in a decentralized marketplace. The system currently utilizes our own network of HPC nodes for model training and inference, ensuring high performance. In the future, we plan to transition this to a fully blockchain-based compute system, further enhancing decentralization and leveraging Constellation's Hypergraph capabilities.

How we built it

We built NeuraNFT using Constellation's Metagraph technology and the Euclid SDK. The system utilizes Metagraph's Data API for managing AI model data, user authentication, and interaction with our HPC nodes.

For our AI model backend, we used Ollama to work with LLaMA 3.1 as our base model. We chose LLaMA 3.1 for its powerful language understanding capabilities and Ollama for its efficient management of large language models. To ensure scalability and ease of deployment, we containerized our Ollama setup using Docker. Our HPC nodes run on docker cluster and load balancer is written in python fastAI. For Frontend we are using ReactJS and Dag4.js and integrated with Stargazer Wallet. We implemented a prototype using Metagraph's Data API for AI model data storage and retrieval, while utilizing our own HPC nodes for AI model training, fine-tuning, and inference. Our future plans include transitioning to a fully decentralized, blockchain-based compute network leveraging Constellation's Hypergraph. This approach allowed us to demonstrate the core functionalities of NeuraNFT while laying the groundwork for a more distributed system.

Challenges we ran into

One of the most significant challenges we faced was adapting to the Scala programming environment and dealing with WSL (Windows Subsystem for Linux) bugs. As newcomers to Scala, we encountered a steep learning curve, which was initially compounded by inconsistencies in our development environment.

However, these challenges were largely mitigated thanks to Constellation's Hydra CLI and shell scripts. The Hydra tools provided a streamlined way to set up our development environment, build our project, and manage our local Metagraph clusters. This significantly reduced the friction we experienced with WSL and allowed us to focus more on the actual development of NeuraNFT. The Video instructions and mentorships along with sample projects were key to figuring out development of Metagraph and deploying our contract.

Another challenge we encountered was in hosting the AI model efficiently. Initially, building the Docker container repeatedly caused reinstallation of packages, which was time-consuming and data-intensive. To address this, we implemented a package caching strategy. This approach significantly reduced build times and data usage, ensuring smoother and more efficient running of the container. This optimization was crucial in maintaining a responsive and resource-efficient development environment.

Accomplishments that we're proud of

One of our major accomplishments was learning and implementing Constellation's Metagraph technology and Scala, which have steep learning curves.

We're proud of creating a system that has the potential to democratize AI ownership and usage while maintaining high standards of security and privacy, leveraging the unique capabilities of Constellation's Hypergraph.

What we learned

This project was a significant learning experience. We gained proficiency in Scala programming and learned how to leverage Constellation's Metagraph architecture for decentralized AI applications. We also learned how to effectively use the Hydra CLI and shell scripts to streamline our development process and overcome environment-related challenges.

The process of integrating AI models with Constellation's Data API taught us valuable lessons about managing large datasets in a decentralized context. We also gained insights into the potential of Metagraphs for creating scalable and interoperable AI systems.

What's next for NeuraNFT

The future of NeuraNFT on Constellation's Metagraph is exciting and ambitious. Our roadmap includes:

Transitioning our current HPC network to a fully decentralized, blockchain-based compute system leveraging Constellation's Hypergraph for improved scalability and performance.
Enhancing our use of the Data API to allow for model composition and fractional ownership.
Creating a decentralized marketplace for AI models using Constellation's L0 tokens.
Implementing a DAO for ecosystem governance using Constellation's consensus mechanisms.
Improving interoperability with other Metagraphs and AI systems within the Constellation ecosystem.
Enhancing privacy and security features, leveraging Constellation's built-in cryptographic capabilities.
Developing an ethical AI framework and compliance tools tailored for decentralized AI on Metagraphs.
Expanding AI capabilities to handle various data types and enable continuous learning using Constellation's scalable architecture.
Focusing on real-world integration, including IoT device integration and enterprise-grade solutions that leverage Constellation's high throughput capabilities.

We're committed to positioning NeuraNFT at the forefront of decentralized AI technology on Constellation, creating a robust, scalable, and innovative ecosystem that revolutionizes how AI models are created, owned, and utilized in a decentralized world.