PulseAugur
EN
LIVE 23:43:29

Perplexity AI releases dual-size multimodal embedding models

By PulseAugur Editorial · [3 sources] ·

Perplexity AI has launched pplx-embed-v2-late, a set of two ColBERT-style multimodal embedding models. The models are available in a 0.6B parameter version designed for edge devices and a larger 9B parameter version optimized for quality. Both models can process text, images, and rendered PDFs, sharing a unified embedding space, and are released under an MIT license for self-hosting. AI

IMPACT Enables efficient multimodal search and retrieval, particularly for documents and on edge devices.

RANK_REASON Model release from Perplexity AI, a notable AI company, with details on model sizes and performance.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

Perplexity AI releases dual-size multimodal embedding models

How we ranked this

Signal score
6 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Frontier Release
Model release from Perplexity AI, a notable AI company, with details on model sizes and performance.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [3]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Perplexity AI Releases pplx-embed-v2-late: A 0.6B Edge Model and a 9B Model Scoring 92.4% on MADQA

    <p>Perplexity's pplx-embed-v2-late comes in 2 sizes: a 0.6B model built to run on edge devices, and a 9B model for building high-quality indexes. Its best score is 92.4% on MADQA, and its weakest is 61.2% on ViDoRe v3 Markdown. Both are MIT-licensed and ready to self-host.</p> <p…

  2. Mastodon — mastodon.social TIER_1 Polski(PL) · aisight ·

    Perplexity released pplx-embed-v2-late models in 0.6B and 9B sizes. With a shared embedding space, a lightweight query encoder can search the index

    Perplexity udostępniło modele pplx-embed-v2-late o rozmiarach 0,6B i 9B. Dzięki wspólnej przestrzeni osadzeń lekki enkoder zapytań może przeszukiwać indeks przygotowany przez znacznie większy model. # si # ai # sztucznainteligencja # wiadomości # informacje # technologia https://…

    LINKS aisight.pl/…/perplexity-podziel-wyszukiwa… aisight.pl/…/generatory-obrazow-ai-stereo…
  3. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Perplexity AI has released pplx-embed-v2-late, a pair of ColBERT-style multimodal embedding models. The 0.6B edge model runs on devices while the 9B model score

    Perplexity AI has released pplx-embed-v2-late, a pair of ColBERT-style multimodal embedding models. The 0.6B edge model runs on devices while the 9B model scores 92.4% on MADQA for high-quality indexes. Both are MIT-licensed and ready to self-host. https://www. marktechpost.com/2…

    LINKS marktechpost.com/…/perplexity-ai-releases…

RELATED ENTITIES

RELATED TOPICS