From Local Helper to Cloud‑Native RAG Chatbot on Google Cloud
How we turned a fragile single‑machine RAG into a session‑aware, PostgreSQL‑backed chatbot running on Cloud Run with Vertex AI doing the heavy lifting.
Nicole Tang · Hong Kong
Building things
to understand them.
I build practical AI systems, automate repetitive work, and write down what I learn.
From Local Scripts to Serverless: Architecting a Cloud-Native Data Collection Pipeline
Transforming a local Python automation into a scalable, serverless cloud application using Google Scheduler, Google Cloud Run and Telegram for on-demand execution.
Modular AI Pipelines: Lessons from a Video Translation "Puzzle” with Whisper
By decoupling transcription from translation and implementing robust error handling, we can build specialized AI pipelines that outperform generic multimodal models in both accuracy and debuggability.
02 · Recurring curiosities