jina-embeddings-v5-omni-nano-retrieval

by jinaai

Compact omni retrieval embeddings for low-latency agent memory

4Kdl/month

8likes

948Mparams

HuggingFace Use in Pipeline

Identifiers

Model ID

jinaai/jina-embeddings-v5-omni-nano-retrieval

Feature URI

mixpeek://image_extractor@v1/jina_embeddings_v5_omni_nano_retrieval

Overview

Jina Embeddings v5 Omni Nano Retrieval is the compact retrieval checkpoint in Jina's v5 omni family. It is designed for multimodal retrieval across text, images, audio, and video while keeping model size and serving cost low.

On Mixpeek, the nano retrieval model is useful when an agent needs broad first-stage recall over mixed media but has tight latency, budget, or edge deployment constraints. Use it as a fast candidate generator before a larger reranker or vision-language model inspects the final evidence.

Architecture

Compact multimodal embedding model exposed through the Transformers feature-extraction pipeline. The retrieval checkpoint is tuned for query-document similarity across multiple input modalities.

Mixpeek SDK Integration

import { Mixpeek } from "mixpeek";

const mx = new Mixpeek({ apiKey: "API_KEY" });

await mx.collections.ingest({
  collection_id: "agent-memory",
  source: { url: "s3://agent-observations/" },
  feature_extractors: [{
    feature: "visual_embeddings",
    model: "jinaai/jina-embeddings-v5-omni-nano-retrieval"
  }]
});