We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view

pplx-announcements September 30, 2026, 8:08pm 1

pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB and turbopuffer’s new, privately held context-bench.

Topic		Replies	Views
Contextualized Embeddings endpoint (/v1/contextualizedembeddings) rate-limits per chunk instead of per request Bug Reports api , embeddings-api	1	35	September 24, 2026
Introducing pplx-embed — State-of-the-Art Embedding Models for Web-Scale Retrieval Announcements	0	103	February 26, 2026
Feature Bundle Request: Explicit Prompt Caching, Multi-Model Fusion, and Granular API Feature Requests sonar-api	0	30	June 19, 2026
On-Premise Embedding API Support for Retrieval-Augmented Generation (RAG) Workflows Feature Requests	0	239	July 24, 2025
PKM Features? Web capture to add Personal Context Feature Requests sonar-api	0	74	August 8, 2025