鐵人檔案
本系列將用 30 天從零打造一套完整的 AI Engineering 系統。首先使用 vLLM 部署開源大型語言模型，逐步加入 Embedding、Vector Database、RAG、Re-ranking 與 Recommendation System，建立具備知識檢索與個人化推薦能力的 AI 應用；接著使用 LangChain 實作 Tool Calling、Memory 與 AI Agent 工作流程，最後進一步探索 Codex Coding Agent，讓 AI 從「回答問題」進化到能理解專案、使用工具、修改程式與完成工程任務，完整呈現從 LLM Inference 到 Agent
In Day 10, we rebuilt our RAG pipeline with LangChain, connecting document retri...
In the previous days, we used embeddings, FAISS, LangChain, and LangGraph to bui...
In Day 12, we introduced the idea of recommendation as a process of retrieving,...
In Day 13, we introduced the basic ideas behind recommendation systems, includin...
In Day 14, we built a content-based recommedation system using Amazon Reviews' 2...
In Day 14, we built a simple content-based recommendation system using Amazon Re...
In Day 15, we built a recommendation workflow with LangGraph by separating the s...
In Day 16, we improved our LangGraph recommendation system by introducing condit...
In Day 17, we improved our recommendation system by introducing LLM-based rerank...