jina-embeddings-omni-nano

About

What jina-embeddings-omni-nano is

jina-embeddings-v5-omni-nano: Multi-Task Omni Embedding Base (Nano) ArXiv | Blog Average score vs. parameter count across image (MIEB-Lite), video (MMEB-V), and audio (MAEB) benchmarks — jina-v5-omni-nano and jina-v5-omni-small define the open-weight frontier (Table 1 in the ArXiv report). Model Overview jina-embeddings-v5-omni-nano is a multimodal embedding model that accepts text, images, video, and audio and produces embeddings in a shared vector space aligned with the text-only jinaai/jina-embeddings-v5-text-nano — so you can index with text and query with any modality, no reindexing. For higher performance at a larger size, see jinaai/jina-embeddings-v5-omni-small. This is the base repository — it holds all task adapters (retrieval, classification, clustering, text-matching). For a single task, pre-merged task-specific variants are also available: - jinaai/jina-embeddings-v5-omni-nano-retrieval — query–document semantic search and RAG (raw-transformers users prepend Query: / Document: to text; sentence-transformers users call encodequery() / encodedocument()). - jinaai/jina-embeddings-v5-omni-nano-classification — assigning labels via embedding similarity — zero-shot and few-shot classification across modalities. - jinaai/jina-embeddings-v5-omni-nano-clustering — grouping semantically similar items — topic discovery, deduplication, exploratory analysis. - jinaai/jina-embeddings-v5-omni-nano-text-matching — symmetric pairwise similarity scoring — STS, paraphrase and near-duplicate detection. Via Elastic Inference Service The fastest way to use v5-omni in production. Elastic Inference Service (EIS) provides managed embedding inference with built-in scaling, so you can generate embeddings directly within your Elastic deployment. See the Elastic Inference Service documentation for setup details. Install For minimum versions see the Requirements section below (transformers = 4.57, torch = 2.5; vLLM path validated with vllm == 0.20.1). Quickstart For retrieval, use encodequery() for query-side embeddings and encodedocument() for document-side embeddings. A bare encode(text) call does not know which retrieval side you intended. This applies to every modality, not

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How embedding models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys jina-embeddings-omni-nano for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (jina-embeddings-omni-nano below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"jina-embeddings-omni-nano","input":"text to embed"}'

Details

Languages, data & research

Papers

Licence

Commercial licence needed

Sources

Weights & code

Explore

More embedding models