Harshwardhan Singh — web engineer writing about web performance, frontend architecture, AI, and security.https://harshwardhan.works/https://harshwardhan.works/blog/building-a-cited-rag-how-a-question-finds-its-answer/https://harshwardhan.works/blog/building-a-cited-rag-how-a-question-finds-its-answer/The read side of the pipeline: turn a question into a vector, find the nearest chunks with one SQL query, optionally rerank them, wrap them in a prompt that forces the model to stay honest, and stream back an answer that cites its sources.Sat, 27 Jun 2026 00:00:00 GMThttps://harshwardhan.works/blog/building-a-cited-rag-how-a-document-becomes-searchable/https://harshwardhan.works/blog/building-a-cited-rag-how-a-document-becomes-searchable/How a markdown scheme document becomes searchable rows in pgvector: paragraph-aware chunking that preserves citations, a provider-agnostic embedding layer, and the fixed vector column dimension that will bite you if you ignore it.Fri, 26 Jun 2026 00:00:00 GMThttps://harshwardhan.works/blog/building-a-cited-rag-vector-databases/https://harshwardhan.works/blog/building-a-cited-rag-vector-databases/The one idea the whole series rests on, from scratch: how text turns into coordinates, why the nearest point is the most similar in meaning, and what the index is really doing. No prior vector knowledge assumed.Thu, 25 Jun 2026 00:00:00 GMThttps://harshwardhan.works/blog/building-a-cited-rag-1-introduction/https://harshwardhan.works/blog/building-a-cited-rag-1-introduction/A build-along series on a retrieval-augmented Q&A system over Indian government schemes: what we're building, why grounding and citations matter more than the model, and the pipeline the rest of the series puts together piece by piece.Wed, 24 Jun 2026 00:00:00 GMT