How we built our own RAG and MCP server at Finom for the iOS and Android mobile repositories. From a local prototype to a shared service running in Kubernetes on Qdrant. Huge thanks to Dmitrii Bystrov ...

This is a clean, production-ready Retrieval-Augmented Generation (RAG) system built in Python 3.10+ for an ML Engineer Assessment. It indexes AI governance documents (the AGORA dataset) and enables ...

The Setup: - Install the hll extension in Postgres. - Store one sketch per video, region, and time bucket. - Use a Python worker to batch writes. - Cache the results at the edge. The Trade-offs: - No ...