DevRel newsletter — June 2026

Elastic acquired Jina AI in late 2025, and jina-embeddings-v5-omni is now available on the Elastic Inference Service in both small and nano variants. The model handles text, images, audio, and video in a single shared embedding space, so you can query across all media types with one index and one query.

You know this situation: Something exists somewhere, like a PDF attachment, a meeting recording, or one of 120 files all named “weekly stakeholder presentation”, but your search engine can only work with text and can’t find it. 

Today, building multimodal search means accepting one of two compromises. The first is using a separate embedding model and index per modality, then somehow ranking and merging results at query time. The second is a single large multimodal model, but those tend to run to seven billion parameters or more, are slow and expensive, and the frontier ones are closed-weight, so you cannot run them locally or inspect what is inside.

jina-embeddings-v5-omni takes a different path: a compact model family that maps all four modalities into the same vector space, so a text query can directly retrieve a relevant video frame, audio clip, or scanned document with no cross-index merging needed.

Because the text backbone in v5-omni is completely unchanged from v5-text, the model produces bit-identical text embeddings. If you already have a text index built on jina-embeddings-v5-text, you can add images, audio, and video to it without rebuilding the index or re-embedding any existing documents.

v5-omni also inherits both of Elasticsearch's major storage optimizations:

• Better Binary Quantization (BBQ): Binarizes vectors to achieve 93% storage reduction with less than 3% accuracy loss. See the BBQ documentation for configuration details.

• Matryoshka representation learning: Embeddings can be truncated to as few as 32 dimensions. Truncation sensitivity varies by modality; video is more sensitive than text or images, so check the tradeoff charts before picking a dimension budget.

Truncating to 256 dimensions and applying binary quantization together cut the index footprint substantially while retaining most retrieval quality.

On the Elastic Inference Service, inference endpoints and Kibana connectors for both jina-embeddings-v5-omni-small and jina-embeddings-v5-omni-nano are created automatically with no manual configuration required. The Elastic documentation covers local deployment via Hugging Face as well. Both models are also available on the Jina API and Hugging Face (CC-BY-NC-4.0).

The full technical write-up, including architecture details and benchmark breakdowns, is on the Elasticsearch Labs blog and the GELATO paper on arXiv. The original video walkthrough is on YouTube.

• Credits: Subscribe to Elastic Cloud via AWS Marketplace or Microsoft Marketplace to receive $1,000 in credits.

• Persistent agent memory: Join Jeff Vestal as he explains how to provide AI agent persistent cross-session memory using Elasticsearch in Claude Code.

• Vector search: Jeffrey Rengifo shares six vector search tips for building AI search applications on Elasticsearch.

• OGX with Elasticsearch: Learn how to configure Elasticsearch as an OGX vector store, ingest PDFs, and build a Python RAG agent with Enrico Zimuel.

• Network Topology: Explore the Network Topology plugin for Kibana with Connor Pierce, which provides a ready-to-deploy Logstash pipeline, a structured schema, and a topology view.

• Streams: Edward Lewis showcases how to configure downsampling in Elastic Streams alongside retention and tiers with a live preview and validation.

• Security: Jamie Hynds and Mia LaVada explain how Elastic Security ingests Google Threat Intelligence. Monitor Claude activity in Elastic Security with Jamie Hynds and Sumana Mannem.

Check out these videos:

• Your AI coding agent got dumber and you didn't notice by JP Hwang 

• Search algorithms explained in 12 levels (BM25, vectors, RAG & more) by Jon Avezbaki

• Elasticsearch's new default embedding model: Explained by JD Armada

Featured blogs from the community:

• TLS certificate monitoring made simple with Elastic Stack by Raihan Iqbal

• Implementing a virtual filesystem over Elasticsearch by Leonie Monigatti

Learn Elastic at no cost: Explore self-paced modules to build your Elastic skills.

Find Elastic at these upcoming conferences:

• San Francisco, CA, USA: AI Engineer World’s Fair — June 29–July 2 (booth + workshop)

• Bengaluru, India: AWS Community Day — July 11 (booth + talk)

• London, UK: Typescript AI Conference  — July 23 (talk)

• Berkeley, CA, USA: Agentic AI Summit — August 1–2 (booth)

Join your local Elastic User Group chapter for the latest news on upcoming events! You can also find us on meetup.com. If you’re interested in presenting at a meetup, send an email to meetups@elastic.co.