AIE Chain
  • AIE Chain SoK
    • Introduction
    • Challenges
      • Blockchain Scalability
      • Gas Issues
      • Unfriendly UX
    • AIE Unique Propositions
    • AIE Chain
      • Building Blocks
      • AIE Chain Architecture
      • AIE Chain Specifications
        • Contracts
        • Contract addresses & RPCs
      • AIE Name Service
      • Bridges
      • AIE Block Explorer
    • AIE Embedded Wallet
      • Account Abstraction
      • Smart Wallet Creation
      • Privacy and Security
      • Gasless Transaction
      • ANS Compatible
      • Export & Import
      • Backup & Recovery
    • AIE Token
    • Onboarding the next billion Web3-users
      • Genesis Marketplace
        • Bring your imagination to life
        • Sign your creative works
        • Mint your creative works into NFT
        • NFTs Marketplace
      • RizzAI: Web3 AI-powered virtual companions
        • Register
        • Log-in
        • Create AI Character
        • View your AI characters
        • Edit your AI character
        • Chat with AI companions
        • Premium Subscription
        • Gallery
      • Rakis: Decentralized Verifiable Inference Network
        • Overview
        • Architecture
        • Data Flow
        • Consensus
      • Interactive AI LiveStreaming
      • Collaborative Content Creations
      • Decentralized Licensing
    • FAQs
Powered by GitBook
On this page
  1. AIE Chain SoK
  2. Onboarding the next billion Web3-users
  3. Rakis: Decentralized Verifiable Inference Network

Data Flow

The data flow within Rakis follows a well-defined path, ensuring efficient processing and communication between components. Here is a high-level overview of the data flow:

Step 1: Inference Requests Inference requests originate from various sources, such as smart contracts or decentralized applications (dApps). These requests, containing prompts, security frames, and other parameters, are received by the P2P and Peering layer.

Step 2: Inference Management The Inference layer handles these requests by managing the scheduling, execution, and result processing through inference workers and embedding workers.

Step 3: Coordination The Coordination layer manages the commit-reveal process, timeout-based scheduling, and quorum building for the inference requests.

Step 4: Consensus Computation The Consensus layer computes the final consensus using embeddings and hashing algorithms, then propagates the consensus results to the network.

Step 5: Persistence The Persistence layer integrates with various blockchains, ensuring the persistence of inference results, implementing incentivization mechanisms, and supporting cross-chain operations.

PreviousArchitectureNextConsensus

Last updated 11 months ago