Dio the Chatbot
LangChainRAGRetrievalEmbeddingsTypeScriptNext.jsHybrid SearchQdrantBM25Redis
The problem
A recruiter should find relevant evidence without reading every portfolio page.
How I solved it
- AI Chatbot with tool-using RAG architecture built around a curated knowledge base of projects, experience, education, certificates, publications and engineering notes to answer questions.
- Hybrid retrieval combines semantic embeddings with keyword matching through Qdrant and BM25, with Redis supporting caching and shared request controls.
- Portfolio questions return source cards, allowing visitors to inspect the evidence behind each answer.
- Can automatically send Hans' CV to your email by opening form in chat UI
- Can automatically send directly Hans a message via Line after review-and-approval flow, requiring the visitor to approve the exact message before anything is sent.
The results
- to understand Hans quickly
- 1 chat
An interactive guide that lets visitors ask about Hans’s work and get source-backed answers without reading every portfolio page.