All articles

Today we are releasing pplx-embed-v1 and pplx-embed-context-v1, two state-of-the-art text embedding models built for real-world, web-scale retrieval.

DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity

Defense architecture, benchmark, and detection model for securing AI agents in open-world web environments.

Elegant tool to address emerging LLM communication patterns

Make trillion-parameter models available with cloud platform portability

Building a scalable Search API that handles 200 million daily queries using hybrid retrieval and intelligent context curation for AI models

Ultra-fast cross-GPU model sync

Day‑0 support for GPT‑OSS on H200 by adapting ROSE with FP8, sink attention, and MoE optimizations

Separating prefill and decode across devices speeds up LLM inference and improves performance