Latest

Every published item, in order · 4 items

10月15日

Qdrant TurboQuant shrinks Perplexity pplx-embed-v2-late vectors 21×

The result makes late-interaction embeddings practical for large-scale retrieval, since storage costs were the main barrier to adoption. Teams running vector search can cut memory and infrastructure spend dramatically while keeping near-baseline accuracy, provided their pipeline can retain originals for rescoring. Engineers comparing against Matryoshka-style truncation or binary quantization now have a concrete 21× datapoint.

#Qdrant #Perplexity #TurboQuant #embeddings

Qdrant@qdrant_engineSource

10月8日

Products US vs ChinaMulti-source16:17

Chinese content10月8日AI简报：Claude Haiku 5.5发布、GPT-6推送、Copilot深度整合Windows

一天里的关键更新都在这：Claude Haiku 5.5 带百万上下文还降价，GPT-6 全面推送交互式界面，GitHub Copilot CLI 能直接用本地 Ollama 模型。

#Claude #GPT-6 #GitHub Copilot #NVIDIA

Event

TestingCatalog@testingcatalog11 sourcesSource

Models BuildersSelected01:22

Perplexity Open-Sources pplx-embed-v2-late Multimodal Embedding Models

The 9B-index-plus-0.6B-query split lets teams build multimodal retrieval where only the small model runs on-device, cutting serving costs for RAG pipelines. Late-interaction over PDF pages without OCR is a concrete alternative to pipeline-heavy document search stacks. Developers building search or RAG systems can pull the weights directly from Hugging Face and compare against ColBERT-style retrieval setups.

#Perplexity #pplx-embed-v2-late #multimodal #RAG

Event

Aravind Srinivas@AravSrinivas2 sourcesSource

Models BuildersSelected01:17

Perplexity releases pplx-embed-v2-late late-interaction embedding models

Late-interaction embeddings like these score higher on retrieval quality than single-vector models because token-level matching is preserved, at the cost of larger index size. Teams building RAG pipelines that mix text and image sources can evaluate the open weights on Hugging Face directly. Perplexity's open release contrasts with most frontier labs keeping embedding stacks proprietary.

#pplx-embed-v2-late #Perplexity #embeddings #open-source models