What Matters in Production RAG
The article discusses the challenges of moving Retrieval-Augmented Generation (RAG) systems from demo to production. It highlights the importance of maintaining a fresh and accurate index and building an observability layer to diagnose issues. Key aspects include the indexing and query pipelines, chunking strategies, and the implications of embedding model choices.
- ▪RAG systems retrieve relevant documents at query time to provide context for language models.
- ▪The indexing pipeline ingests documents and stores vector embeddings in a database, while the query pipeline retrieves these embeddings based on user queries.
- ▪Effective chunking strategies are crucial, as naive approaches often lead to poor retrieval results.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Arpit Bhayani |
| Canonical URL | https://arpitbhayani.me/blogs/rag-production/ |
| Publication time | Sun, 17 May 2026 20:54:13 +0000 |
| Retrieval time | 2026-05-17T21:03:21.008Z |
| Last seen | 2026-05-17T21:03:21.008Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | raoQeVp1kzgX |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Most of us build RAG the same way: follow a tutorial that embeds a handful of PDFs, stores the vectors in a local Chroma instance, and chains everything together with LangChain (if that’s still a thing). The demo works. The answer looks reasonable. Then you take it to production and it falls apart in quiet, hard-to-diagnose ways. This article is about what comes after the demo. It covers the fundamentals of how RAG actually works under the hood, the engineering challenges of keeping an index fresh and correct over time, and how to build the observability layer that lets you answer “why did the system retrieve that?” when things go wrong. None of these topics are exotic. All of them are consistently underbuilt in practice.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Arpit Bhayani.
Discussion
0 commentsMore from Arpit Bhayani
-Wireless-Earbuds.jpg&w=320)