読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニューストピック · Qdrant重大3 分で読めるDisconfirmAI 編集部

Vector Database Company Qdrant: Asymmetric Quantization Reduces Single-Vector PDF Retrieval Memory to 64 Bytes per Page, Retaining 99.2% Quality

Qdrant blog author Evgeniya Sukhodolskaya tested the single dense vector retrieval capability of Cohere Embed 5 Pro across five public English corpora in ViDoRe V3, finding its ranking quality exceeded that of several late-interaction models. The team further stacked Matryoshka dimension truncation, 1-bit document quantization, and 8-bit asymmetric query quantization, combined with top-20 full-vector re-ranking, achieving 99.2% retained ranking quality at a RAM cost of only 64 bytes per page.

2026-10-23 08:00 GMT+8

When searching PDF page images, the Qdrant team previously typically recommended using late-interaction visual models (such as ColPali or ColQwen), retaining one vector for each image patch to avoid losing relationships between words in the layout during OCR extraction. However, late-interaction methods generate approximately one thousand vectors per page, and their MaxSim similarity metric cannot directly utilize HNSW indexing, making scaling difficult on datasets with billions of points. Out of curiosity, the team tested Cohere Embed 5 Pro—a model that represents an entire PDF page image with a single dense vector—on five public English corpora from ViDoRe V3 (computer science textbooks, financial reports, EU labor reports, US Air Force technical manuals, and US FDA pharmaceutical documents, comprising 12,969 page images and 1,489 English questions). The results showed that its nDCG@10 score surpassed that of several late-interaction models.

The team then explored how to turn this finding into a scalable solution for production environments. Embed 5 outputs default 2048-dimensional vectors, which consume 8 KB per page when stored as float32. Qdrant’s approach involves stacking three compression techniques: first, leveraging Matryoshka Representation Learning (MRL) supported by Embed 5 to retain only the first 512 dimensions of the vector rather than all 2048; second, applying 1-bit binary quantization to document vectors, keeping only the sign (whether each dimension is greater than zero); and crucially, asymmetric quantization—where query vectors maintain 8-bit precision while document vectors use only 1 bit. The intuition is that when dimensions are truncated to 512, the equal-weight sign count of 1-bit quantization becomes coarse, giving the same weight to a dimension just barely above zero and one with a large positive value; retaining magnitude information on the query side allows important dimensions to carry more weight during scoring. During retrieval, compressed vectors are used to find the top 20 candidates, which are then re-ranked using the complete float32 vectors stored on disk.

ログイン / 新規登録
読書リサーチレーダー投資フレームワーク

The final recipe consists of 512 dimensions, 1-bit documents, 8-bit queries, plus top-20 re-ranking, occupying only 64 bytes in RAM per page—1/128th of the 8 KB required for a complete float32 vector, while retaining 99.2% of the ranking quality. The team performed some napkin math: for 10 million PDF pages, ColPali’s float32 vectors would require approximately 4.8 TB, complete Embed 5 vectors would need 76 GB, and this recipe requires only 610 MB of RAM. However, the team also noted boundaries: Embed 5’s training data is not public, and they wrote,

"We might have accidentally tested on the training set, but if not, wow!"

. Additionally, 610 MB is the starting RAM usage; the complete vectors read from disk during re-ranking will gradually fill the OS page cache. The recipe still retains approximately 95 GB of complete and truncated float vectors on disk.

The team also tested the gain provided by Cohere Rerank 5 for OCR text retrieval pipelines: after embedding ViDoRe V3’s OCR text search using Embed 5 Pro, they re-ranked the top 20 pages using Rerank 5 Pro, raising the average nDCG@10 across the five corpora from 66.8 to 73.2; when the text search used the 64-byte recipe, it similarly rose from 66.2 to 71.7.

ソース

  • qdrant.tech↗
トピック

Qdrant

向量数据库公司Qdrant于2026年10月23日发布博客,展示了如何利用Cohere Embed 5 Pro模型结合非对称量化技术,实现大规模PDF页面图像的高效检索。测试显示,Embed 5 Pro在ViDoRe V3基准测试中的单de…

2 ステップ1 件更新日 2026-11-02 09:01

経緯

  1. 2026-10-23Qdrant发布博客《Scalable PDF Retrieval with Cohere Embed 5 and Qdrant Asymmetric Quantization》,作者Evgeniya Sukhodolskaya报告称Cohere Embed 5 Pro在五个公开英文语料库上的单向量检索性能优于部分late-interaction模型。qdrant.tech ↗
  2. 2026-10-23博客详细阐述了优化方案:利用Matryoshka表示学习将2048维向量截断至512维,采用1-bit二进制量化存储文档向量,8-bit非对称量化处理查询向量,并对前20个结果进行全精度重排序,实现每页64字节的RAM占用。qdrant.tech ↗

未解決の問題

  • Cohere Embed 5的训练数据未公开,Qdrant指出可能存在测试集与训练集重叠的风险,需等待第三方独立复现验证其泛化能力。
  • 该方案依赖Qdrant特有的非对称量化与重排序功能,其他主流向量数据库是否支持同等效率的混合量化策略尚不明确。
トピック全文を読む →
リサーチを続ける →