한국어EN
Embeddings & Vector SearchVoyage AI (MongoDB)Voyage AI

Voyage AI releases voyage-context-3

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

voyage-context-3 released — processes the whole document in one pass, injecting global context into chunk embeddings. 20.54% better than contextual retrieval; binary/512 cuts storage costs by 99.48% compared with float/3072 (company-reported)

Why it matters

Absorbs chunking, a fundamental flaw of RAG, into the model itself

Source — Primary sources first; secondary reports are labelled “Press”

Officialmongodb.comhttps://www.mongodb.com/company/blog/product-release-announcements/voyage-context-3-focused-chunk-level-details-global-document-context

Added in Week 35, 2026 · See that week

On the map — ⑰ Embeddings line

  1. Previous stopEmbed v4
  2. This recordvoyage-context-3
  3. Next stopAmazon makes Nova Multimodal Embeddings generally available on Bedrock
See it on the map

Same week

GEPA publishedPaperSK Telecom open-sources A.X 3.1OfficialAlibaba releases Qwen3-CoderOfficialGemini Deep Think reaches IMO 2025 gold-medal standard (5 of 6 problems, 35/42)Official

Nearby on the same axis

Elasticsearch 9.1 makes BBQ default for dense vectors of 384+ dims, adds ACORN-1OfficialGoogle makes gemini-embedding-001 generally available (GA)OfficialVoyage AI launches rerank-2.5 and rerank-2.5-liteOfficialJina AI releases jina-embeddings-v4 (3.8B)Paper