# Updates, Deletes and Freshness — Embeddings & Vector Search

Source: https://www.geekswithgeeks.com/en/embeddings/p-fresh

> Keep the index in step with changing documents.

## Stale vectors give stale answers

Documents change, so the index must too. Give each chunk a stable **ID** and a **source document ID** and **content hash**; on a change, re-chunk and re-embed only changed documents and **replace** their old chunks (delete by source ID, then insert). Handle **deletions** and **permission changes** promptly, since a removed or restricted document must stop being retrievable. Some ANN structures handle deletes lazily (marking entries as deleted and cleaning up during maintenance), and heavy churn may require periodic **rebuilds** or **compaction**. Keep **version and effective-date metadata** to prefer current content, and monitor **index lag** (how long a change takes to become searchable). For large batch updates, build a fresh index and switch atomically.

## Monitor index lag

Measure how long it takes for a new or deleted document to appear or disappear in results, and alert if it grows.

**Quiz:** How should a changed document be updated in the index?

- [ ] Add the new chunks and keep the old ones
- [x] Re-embed it and replace its old chunks by source document ID
- [ ] Rebuild nothing and hope
- [ ] Edit the vector numbers by hand

*Answer:* Re-embed it and replace its old chunks by source document ID. Leaving old chunks behind returns outdated, contradictory results.