Retrieval
5 pieces on Retrieval, including 1 step-by-step guide.
Guides
News & Analysis
Long Context or Retrieval? Compare Cost, Quality and Update Work
A worked long-context versus retrieval comparison that includes indexing, repeated queries, cache behavior and answer quality.
Read more →
Sentence Transformers v6.0 Adds ColBERT Training in 14.5 Hours on One GPU
Sentence Transformers v6.0 adds MultiVectorEncoder with full ColBERT-style training. A single RTX 3090 run beats every zero-shot retriever by 0.06 NDCG@10.
Read more →
Row-Level RAG Chunks Cut Table Context by 7.7x
Serialising each table row as its own chunk returns 122 chars instead of 943 on a targeted lookup — a 7.7x context reduction with no parser changes.
Read more →
ColBERT Late Interaction Lands in Sentence Transformers v6.0
Sentence Transformers v6.0 adds MultiVectorEncoder, bringing ColBERT-style late interaction retrieval—42× larger indexes, 26-point MLDR gains—into one pip install.
Read more →