OriginTrail
  • Get started with OriginTrail
  • OriginTrail Ecosystem — Call for Papers (Coming Soon)
  • Key Concepts
    • Decentralized Knowledge Graph (DKG)
    • DKG key concepts
  • TRAC: DKG utility token
  • Build with DKG
    • Quickstart (test drive the DKG in 5 mins)
      • Quickstart with Node.js
      • Quickstart with Python
    • Querying the DKG
    • DKG Edge Node
      • DKG Edge Node architecture
      • Get started with the Edge Node boilerplate
        • Automated setup with the installer
        • Manual setup
        • Usage example
      • Customize & build with the Edge Node
      • Knowledge Mining and dRAG examples
      • Deploy your Edge Node based project
        • Automated deployment with installer
      • DKG Edge Node inception program
      • DKG Edge Node API documentation
    • DKG Core Node
      • Run a V8 Core Node on testnet
        • Preparation for V8 DKG Core Node deployment
        • V8 DKG Core Node installation
      • Run a V8 Core Node on mainnet
        • Preparation for V8 DKG Core Node deployment
        • V8 DKG Core Node installation
      • How to open up your node for publishing
    • DKG toolkit
      • DKG SDK
        • Development environment setup
        • DKG Javascript SDK (dkg.js)
          • Interact with DKG paranets
          • Permissioned Paranets
          • Knowledge submission & curation
          • Paranet's incentives pool implementation
        • DKG Python SDK (dkg.py)
      • DKG paranets
        • Deploying a DKG paranet
        • Building with DKG paranets
        • Syncing a DKG Paranet
        • Initial Paranet Offerings (IPOs)
          • IPO specification
          • Launching your IPO
          • Paranet's incentives pool
          • IPO voting
      • AI agents
        • ElizaOS DKG agent
        • Custom DKG Python agent
        • Custom DKG JavaScript agent
      • Using the DKG with MCP
    • Ecosystem call for papers
  • DKG under the hood
    • Introduction
    • Delegated staking
      • Step-by-step staking
      • Redelegating stake
  • Random Sampling DKG Proof System
    • Random sampling rollout
    • Random Sampling FAQ
  • DKG Sync
  • Integrated Blockchains
    • Base blockchain
      • Connect to Base
    • Gnosis chain
      • Connect to Gnosis
    • NeuroWeb
    • Teleport instructions - NeuroWeb
    • Bridging to Moonbeam
    • Deployed smart contracts
  • Bounties & rewards
    • General bug bounty
    • Code contributions & V8 bug bounty
  • Whitepapers & RFCs
    • OriginTrail whitepaper
    • OriginTrail RFCs
  • Useful Resources
    • What's new with OriginTrail V8
    • DKG V8 guidebook
      • Protocol updates
      • Feature roadmap
      • How to upgrade to V8?
    • Public nodes
    • Tutorials
    • Test token faucet
    • Development principles
    • Community created resources
    • Linked data & knowledge graphs
    • Available networks, network details and RPCs
    • OT Node Engine implementation details
      • Modules
      • Command Executor
    • Contribution guidelines
      • Guidelines for automated test contributions
    • Explore the OriginTrail ecosystem
Powered by GitBook
On this page
  • Purpose of the Example
  • Focused on UI
  • Interacting with the Web UI
  • Logging in
  • Publishing a Knowledge Asset
  • Passing a query

Was this helpful?

Edit on GitHub
  1. Build with DKG
  2. DKG Edge Node
  3. Get started with the Edge Node boilerplate

Usage example

You can find a simple example of the DKG Edge Node usage below to help you get started.

This page demonstrates a simple end-to-end example of how you can process any kind of JSON data using the example pipeline provided in the Knowledge Mining service, and then ask questions about that data through the AI Assistant interface. The AI Assistant communicates directly with the DRAG (Decentralized Retrieval-Augmented Generation) module, for which we’ve also prepared a basic example to showcase its functionality.

Note: This is a simplified example meant to demonstrate the concept and basic flow.

Purpose of the Example

The goal of this example is to provide a quick and intuitive way to explore the potential of the DKG Edge Node through the UI. It’s designed to help you understand:

  • How input data (in standard JSON format) can be processed through a Knowledge Mining pipeline to generate structured graph data in JSON-LD or N-Quads format.

  • How this graph-structured output is published to the OriginTrail Decentralized Knowledge Graph (DKG) as a Knowledge Asset – making the data verifiable, discoverable, and ensuring data integrity and ownership.

  • How AI-powered question answering is performed on top of these Knowledge Assets through the DRAG service, which builds RAG (Retrieval-Augmented Generation) systems on decentralized data using powerful LLMs.

Focused on UI

To keep things as accessible as possible, this example focuses purely on UI-based usage. If you're looking to explore programmatic interaction with the services (e.g., building custom pipelines, publishing data, or querying via APIs), please refer to the dedicated API Documentation section.

Note on Simplicity

This example is intentionally basic and does not represent a production-ready pipeline. Instead, it serves to highlight what’s possible when using:

  • Knowledge Mining Pipelines – for transforming raw inputs into semantically rich formats (e.g., JSON-LD).

  • Edge Node API – for publishing structured data to the Decentralized Knowledge Graph (DKG).

  • Edge Node DRAG – for creating RAG (Retrieval-Augmented Generation) applications based on verifiable, decentralized data.

The main idea is that users can build their own Knowledge Mining workflows tailored to their domain-specific data and leverage the DKG infrastructure for secure, decentralized, and intelligent knowledge applications.

Interacting with the Web UI

You can access the user interface at http://your-nodes-ip-address.

Logging in

When accessing your node endpoint, you will be redirected to the login page.

The default login credentials are as follows:

username: my_edge_node

password: edge_node_pass

Publishing a Knowledge Asset

We have prepared a simple example, which is processing JSON files that represent movies.

Example JSON for a movie:

{
    "title": "The Terminator",
    "release_year": 1984,
    "genre": [
        "Action",
        "Sci-Fi",
        "Thriller"
    ],
    "director": "James Cameron",
    "writers": [
        "James Cameron",
        "Gale Anne Hurd",
        "William Wisher"
    ],
    "cast": [
        {
            "actor": "Arnold Schwarzenegger",
            "role": "The Terminator"
        },
        {
            "actor": "Linda Hamilton",
            "role": "Sarah Connor"
        },
        {
            "actor": "Michael Biehn",
            "role": "Kyle Reese"
        },
        {
            "actor": "Paul Winfield",
            "role": "Lieutenant Ed Traxler"
        }
    ],
    "plot": "A cyborg assassin, known as a Terminator, is sent back from the future to kill Sarah Connor, a woman whose unborn son will lead humanity in a war against machines. A soldier from the future is sent back to protect her.",
    "runtime": "107 minutes",
    "language": "English",
    "country": "USA",
    "imdb_rating": 8.1,
    "imdb_link": "https://www.imdb.com/title/tt0088247/"
}

You can create any kind of JSON representing a book, movie, or music following the example above.

Go to http://your-nodes-ip-address/contribute and upload your JSON.

If you are using WSL, the node's IP address will be the IP address of the virtual machine.

The Edge Node will:

  1. Process your input file and create a JSON-LD out of it.

  2. Publish the Knowledge Asset on the Decentralized Knowledge Graph (DKG) from that JSON-LD.

Passing a query

After successfully creating the Knowledge Asset, go to http://your-nodes-ip-address/ai-assistant, and ask the AI Assistant a question about the movie (or other work) you put in the JSON to see how it works.

PreviousManual setupNextCustomize & build with the Edge Node

Last updated 2 months ago

Was this helpful?

If you don’t get a good answer right away, feel free to tweak — this is just an example pipeline, and it may not work perfectly with every type of JSON structure out of the box.

JSON Knowledge pipeline