# context

> Browse 1 item tagged with context.

## Items

- [Contextual Retrieval](https://vectordb.ever.works/tr/items/contextual-retrieval) — Anthropic's RAG technique that prepends chunk-specific explanatory context before embedding, reducing failed retrievals by 49% (67% with reranking). Uses Contextual Embeddings and Contextual BM25.

---

_Canonical page: https://vectordb.ever.works/tr/tags/context_