#late-interaction

2 posts

ai deep-dive RAG 技法大全 Sep 3, 2026

ColPali: Skip OCR, Retrieve Documents Directly from Images

ColPali renders each PDF page as an image, generates patch-level multi-vector embeddings with a vision-language model, and retrieves via MaxSim late interaction. On table-heavy financial PDFs, recall jumps from 62% to 84% — no OCR, no chunking. The tradeoff: ~100× storage, GPU required, no BM25.

#colpali #visual-rag #late-interaction #document-retrieval #multi-vector #rag

ai guide The RAG Techniques Compendium Mar 12, 2026

ColBERT: The Third Way in Vector Search

Bi-Encoders are too coarse, Cross-Encoders are too slow — ColBERT's Late Interaction finds the sweet spot: token-level comparison between query and document, but with document vectors that can be precomputed.

#rag #colbert #late-interaction #retrieval #reranking #colpali #visual-rag