Bridge & Chat API

Overview

This project provides two core APIs that power the GenLayer Intelligent Oracle:

A Bridge API for deploying Intelligent Oracles to the GenLayer blockchain
A Chat API that integrates OpenAI's GPT models to provide natural language assistance in the UI wizard component

Features

Bridge API

Handles deployment of Intelligent Oracles to GenLayer
Manages transaction signing and blockchain interactions
Provides status updates during deployment process

Chat API

Integrates with OpenAI's GPT models
Streams AI responses in real-time
Processes natural language inputs for the wizard interface
Maintains conversation context for multi-step configurations

Technologies Used

Node.js
OpenAI API
GenLayer SDK
Edge Functions (Vercel/Cloudflare)

Setup

Clone the repository
Set up environment variables by copying the .env.example file in the root directory to .env and adding your own values.

Usage

Install dependencies:
```
npm install
```
Start the development server:
```
npm run dev
```
Open your browser and navigate to http://localhost:3000

Note: the port may vary depending on the configuration of your local machine and other running services. For example, if you are running the ui-wizard project, it will use port 3001 by default.

API Reference

Bridge API Endpoints

POST /api/bridge/deploy-intelligent-oracle: Deploy a new Intelligent Oracle

The following schema describes the required fields when creating a new oracle:

{
  predictionMarketId?: string;  // Optional, defaults to "0"
  title: string;                // Title of the prediction market
  description: string;          // Detailed description of the market
  potentialOutcomes: string[];  // Array of possible outcomes
  rules: string[];             // Array of resolution rules
  dataSourceDomains: string[]; // Array of allowed data source domains. If set, `resolutionURLs` need to be empty.
  resolutionURLs: string[];    // Array of URLs to be used for resolution. If set, `dataSourceDomains` need to be empty.
  earliestResolutionDate: string; // ISO date string for earliest resolution
}

Example request:

{
  "predictionMarketId": "1",
  "title": "Will Bitcoin reach $100k in 2024?",
  "description": "This market predicts whether Bitcoin will reach...",
  "potentialOutcomes": ["Yes", "No"],
  "rules": [
    "Price must be reached on at least 3 major exchanges",
    "Must maintain price for 1 hour minimum"
  ],
  "dataSourceDomains": [
    "coinbase.com",
    "binance.com",
    "kraken.com"
  ],
  "resolutionURLs": [
    "https://api.coinbase.com/v2/prices/BTC-USD/spot",
    "https://api.binance.com/api/v3/ticker/price?symbol=BTCUSDT"
  ],
  "earliestResolutionDate": "2024-12-31T23:59:59Z"
}

Chat API Endpoints

POST /api/chat: Send message to AI assistant

Chat Request Schema

{
  "messages": [
    {
      "role": "user" | "assistant" | "system",
      "content": "string"
    }
  ]
}

Example request:

{
  "messages": [
    {
      "role": "user",
      "content": "__start__"
    }
  ]
}

The __start__ message is used to initialize a new chat session. The API will maintain conversation context across multiple messages in a session.

Example response:

{
  "role": "assistant",
  "content": "Hello! I'm here to help you configure your Intelligent Oracle. Would you like to start setting up a new prediction market?"
}

Introduction Explorer