From RSS to Insight: Building a Production‑Ready RAG System with the Stripe Blog Feed
When my data‑science team needed instant answers about Stripe’s latest product moves, we hit a wall: pulling the entire blog dump every time we ans…
rag
Beyond Guesswork: Engineering Rigorous RAG Evaluation Pipelines with Ragas and Live GitHub Data
Building reliable production RAG systems requires shifting from subjective evaluation to automated, deterministic evaluation harnesses using Ragas,…
Beyond Vector Search: Engineering a Two‑Stage Reranking Pipeline for Production RAG
When I upgraded the zero‑downtime RAG system that streams Stripe’s blog, the bi‑encoder kept pulling dozens of loosely related posts, and the LLM s…
Keeping RAG Fresh: Dynamic Ingestion and Multi-Stage Retrieval for Cloudflare's Blog
Traditional Retrieval-Augmented Generation systems often choke on data freshness, leaving your models to hallucinate answers from outdated document…
Beyond LLM-as-a-Judge: Implementing Custom Ragas Evaluation Metrics for Production RAG Pipelines
When I first switched from a simple keyword‑match RAG to a fully fledged agentic semantic chunking pipeline for the Stripe Engineering Blog feed, t…