https://hugo-blog-923.pages.dev/tags/etl/ Recent content in Etl on Technical Blog Hugo en Tue, 07 Apr 2026 00:00:00 +0000 https://hugo-blog-923.pages.dev/posts/rag-ingestion-embedding-pipeline/ Tue, 07 Apr 2026 00:00:00 +0000 https://hugo-blog-923.pages.dev/posts/rag-ingestion-embedding-pipeline/ <p align="center"> <img src="pexels_7605981.jpg" alt="Desk with project documents and charts — turning paper policy into structured retrieval." style="max-width: min(100%, 820px); height: auto;" /> </p> <p>Retrieval quality in an <strong>internal policy RAG</strong> is rarely fixed by swapping the chat model first. It is usually capped by <strong>how documents enter the system</strong>: file types, chunk boundaries, stable identifiers, and a repeatable path from <strong>source object</strong> to <strong>vector index</strong>. In practice you often see <strong>batch jobs or Lambdas</strong>, <strong>object storage</strong> for artifacts, and a <strong>managed vector service</strong> wired together the same way.</p>