How do you handle the freshness problem in RAG (docs change constantly)?

medium

Answer

$(1) Incremental indexing: streaming ingest, upsert on change, tombstone on delete.$
$\mathrm{last}_{\mathrm{updated}}$
$(3) Time-aware retrieval: for queries about recent events, prefer docs from the last N days.$
$(4) Version tags in prompts: 'as of 2026-07-30'.$
$(5) Web search fallback: when retrieval returns stale docs, fall through to a live web search.$
$Critical for news, financial, product-docs RAG.$

Check yourself — multiple choice

Only static indexes
Incremental upsert, freshness metadata, time-aware retrieval, version tags, web-search fallback — freshness is a first-class concern
Random re-index
Not solvable

Fresh RAG: incremental upsert + freshness metadata + time filters + web fallback.

#rag#production

214 interview questions in this topic.