# Perplexity — pplx-embed-v2-late

> AI lab announcements, news reports and podcasts.

forck.live follows what companies announce about their own products. Press may
corroborate an official story; it never leads and never appears as an item of its
own. A missing date stays missing. A title is the publisher's words — where a
company does not publish in English, an English rendering is listed separately
as `Title in English` and named as this site's translation, never as theirs.

This file is the record of one model version: what the model registry states
about it, Perplexity's launch post, the first-party posts this record
holds about it, the outlets that reported on those posts, and other companies'
announcements that it runs on their platforms. A model ranks nothing here and
nothing is composed: each date names whose it is, and a field nothing states is
`not stated` rather than missing.

- This model's page: https://forck.live/models/pplx-embed-v2-late
- Perplexity's page: https://forck.live/company/perplexity
- Every model: https://forck.live/models
- Catalogue: https://forck.live/llms.txt

## Model

- Name: pplx-embed-v2-late
- Company: Perplexity (perplexity.ai)
- Launch post: Multimodal embeddings beyond a single vector — https://forck.live/items/16412-multimodal-embeddings-beyond-a-single-vector
- Announced: 2026-10-07
- Launch source: https://www.perplexity.ai/hub/blog/multimodal-embeddings-beyond-a-single-vector
- Launch chosen by: a person, pinned in the model registry
- Released (per models.dev): 2026-10-07
- Listed (per OpenRouter): not stated
- Open weights: not stated
- Posts about it: 1
- Outlets named under its posts: 0

## Posts about it

_Perplexity's own posts whose title names pplx-embed-v2-late, and its launch post, in the record's order: dated newest first, undated last. The record reads the newest 50 first-party posts mentioning the model, every company's together, so a model mentioned more often than that lists the newest of them._

Every entry is one first-party announcement, and carries the same eight fields
in this order before any others:

    Company · Announced · Category · Coverage · Announcement · Group · Source · Record

`Source` is the company's own page the announcement was traced to and `Record`
is this site's page for it. Both are safe to cite.

`Coverage` is a number of outlets, or `not counted` — which means this record
reached no count of its own, never that nobody wrote about it.

`Category` is this tracker's own analysis, and is authoritative wherever it is
stated. `not stated` means either that nothing has analysed the post yet or
that the analysis placed it outside this taxonomy; neither is a verdict about
the announcement.

`Announcement` is whether the post is news of something the company did, rather
than a how-to, a customer story, a changelog listing or a staffing note.

`Group` is which of this record's groups the entry falls in, carried on the
entry itself so it holds where the groups are headings and where they are not.
One of: `models`, `covered`, `announcements`, `routine`.

Anything after `Record` is held detail that only some announcements carry.

### Perplexity — Multimodal embeddings beyond a single vector

- Company: Perplexity (perplexity.ai)
- Announced: 2026-10-07
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.perplexity.ai/hub/blog/multimodal-embeddings-beyond-a-single-vector
- Record: https://forck.live/items/16412-multimodal-embeddings-beyond-a-single-vector
- Subject: Perplexity

Perplexity released pplx-embed-v2-late, a family of late-interaction embedding models that retain token-level vectors instead of compressing each input into a single vector, improving multimodal retrieval. The models handle both text and image modalities, allowing direct search of rendered PDF pages without OCR or parsed text. Perplexity says the 0.6B model matches models with five times as many active parameters on the ViDoRe (V3) visual document retrieval benchmark. Both model sizes, 0.6B and 9B, are publicly available on Hugging Face and share an embedding space so the smaller model can query an index built with the larger one.

## Who reported on it

_This record names no outlet that reported on these posts._

---

Record: https://forck.live/models/pplx-embed-v2-late
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md