Financial / Universe Robot Dialogue AI Interface

Low-latency LLM + RAG dialogue backend for service robots, supporting real-time financial data queries, financial news retrieval, historical price analysis, and private-domain restaurant service search.
Highlights
  • Sub-500ms response latency for key query scenarios
  • Real-time stock, cryptocurrency, and precious metal price lookup
  • LLM-based historical trading price analysis
  • Financial hot-news retrieval
  • Million-scale structured private knowledge base for restaurant queries and reviews
  • Showcased at a Hong Kong technology exhibition
Tech Stack LLM · RAG · Real-time Data API · Structured Knowledge Retrieval · Financial QA · Service Robot Interface
Whisper’s Encoder-Decoder Pipeline, Special Tokens, and a Comparison with Qwen3-ASRPyTorch DataLoader Multiprocessing
Loading...