RadarDrop
πŸ“ž Book a Call
  • βšͺProduct
    • Overview
    • Disclaimer
    • Today's market / problems
    • Our solutions
      • πŸͺ‚AI-powered Airdrop Finder
      • πŸ€–Airdrop Farming AI Agent
      • πŸ’¬RadarDrop AI Agent
      • πŸ“ŠPortfolio tracking
      • ⏰Customized Notifications
      • πŸŽ“RadarDrop Academy
      • πŸ”RadarDrop Discovery
      • 🀝RadarDrop Synergy
    • Gamification
    • Socialization
    • Referral System
    • Telegram App
    • Why RadarDrop is unique
  • πŸ’΅Token ($RDAI)
    • Overview
    • Token utilities, mechanisms and revenue sources
    • Tokenomics
  • Conclusion
  • πŸ”—Useful links
    • Team
    • Tokenomics sheet
    • Roadmap
    • Documentation
    • Founders live presentation
    • Book a call
Powered by GitBook
On this page
  • Key points
  • Technology
  1. Product
  2. Our solutions

RadarDrop AI Agent

PreviousAirdrop Farming AI AgentNextPortfolio tracking

Last updated 5 months ago

Finding information about airdrop projects is not easy. Understanding crypto keywords, digging into documentation, and searching for posts on social networks can quickly become difficult and overwhelming.

➑️ Introducing our AI agent, expertly trained on each airdrop with dozens of sources! Quickly access crucial information in any language and stay ahead of the game.

Key points

🏎️ Fast: We use the latest, most performant models from OpenAI and Mixtral to answer user requests.

πŸ‘Œ Accurate: By leveraging multiple data sources, our AI agent provides precise and up-to-date information about airdrop projects, ensuring users have all the details they need.

🌎 Multilingual: The AI agent supports multiple languages, making it accessible to a global audience.

Technology

From the user’s text input to the model’s response, there are a few steps:

We use WebSocket to ensure communication between the client and the server. Since the server instances are scalable, only one instance starts the WebSocket server.

User’s prompt request

Once the user has joined a channel (linked to an airdrop or not), he can send his message through the WebSocket connection. The message is then almost instantly sent to our queue system from BullMQ.

We can handle up to 100 messages simultaneously with our current infrastructure. We can easily increase this number to meet demand.

Holders of the $RDAI token are automatically prioritized in the BullMQ queue.

Gathering documents from the vector database

Streaming the response to the user

Once the relevant documents are gathered, we use our pre-trained AI models to understand the context and generate a coherent and accurate response. The response is then streamed back to the user through the WebSocket connection, ensuring real-time communication and quick resolution.

Once the request is handled by our chat service, we gather all the split documents from the vector database.

Those documents were previously fetched from social networks and the web. The documents were then split using our homemade splitters and embedded using .

ChromaDB
OpenAI Embeddings
User’s prompt request
Gathering documents from the vector database
Streaming the response to the user
βšͺ
πŸ’¬
Whole process (simplified)
Page cover image