Elastic announced that Jina AI models are available for on-premises and air-gapped environments through Jina On-Prem.
Designed for regulated industries, air-gapped environments, or organizations that want full control over data, cost, and performance, Jina On-Prem delivers enterprise-grade data extraction and semantic search with no internet connection or third-party AI services required.
Many organizations need AI systems that don't depend on a live connection to a third-party service. While self-hosted alternatives exist, they come with tradeoffs. Supporting multiple media types and languages typically requires assembling separate models, and licensed platforms cleared for air-gapped deployments are largely constrained to text and images. The most accurate open-source models also carry substantial compute requirements, meaning comprehensive coverage often demands running several large models simultaneously.
Jina On-Prem packages Jina AI's family of models that cover text, images, audio, and video in a single embedding space so they can now run entirely within a customer's own environment, making no calls to the outside once deployed. Data stays on-premises, and teams retain full control over cost, model access, and performance. Small Jina models run on a single 8GB GPU, at a fraction of the cost, while matching the accuracy of far larger models that need many times more GPU memory.
"Historically, teams running search and retrieval in regulated or disconnected environments have had to choose between capability and control," said Ajay Nair, general manager, Elasticsearch and Platform, Elastic. "The ability to run Jina models fully on-premises removes that compromise by giving them Jina AI’s high-performance reader, embedding and reranking models directly in their own environments, allowing them to build AI applications without depending on external AI services.”
Jina On-Prem installs with a single command and makes no outbound network calls once deployed: no license server, no telemetry or logging endpoint, and no connection to a model registry. The suite includes all 28 Jina AI models, including the jina-embeddings-v5-omni multimodal embedding model and jina-reranker-v3, and supports both CPU and GPU hardware with automatic GPU detection. Applications can reach it through standard API schemas so existing integrations work without rewriting code.
Jina On-Prem also serves as a drop-in replacement for models served through Elastic Inference Service (EIS), so air-gapped Elastic deployments can integrate it directly without changing how applications call their embedding and reranking models.
Jina On-Prem is available now for download via GitHub through an access token. Installation instructions are available on the Jina On-Prem Quick Start page, with a separate bundling guide for teams composing their own Docker container. To license Jina On-Prem, please contact Elastic Sales.
The Latest
For decades, enterprise networks were designed around a simple assumption: work happened inside the office. Applications lived in centralized data centers, employees connected through internal infrastructure, and security focused on protecting the perimeter that surrounded everything ... But the way organizations operate today bears little resemblance to that environment. Cloud platforms host critical applications, employees connect from homes and airports as often as they do from offices, and partners collaborate through shared systems that exist far beyond corporate walls. In short, the corporate network no longer resembles the environment it was designed to protect ...
As an analyst who researches how IT organizations design, build, and operate their networks, I find that network data is a constant source of pain. Network teams struggle with data quality, fragmentation, authority, access, and trust. And these issues undermine everything they try to do. Here are the numbers: Only 45% of network teams are completely confident in the accuracy of their network source of truth, which documents the intent of their network ...
The 2026 Global Data Center Survey from Uptime Institute reveals an industry navigating workforce constraints, escalating outage expenses, even as rising costs remain the top concern for management teams ...
The next observability gap may not be in the code. It may be under the rack. That sounds strange until you think about how AI incidents actually feel in the middle of an investigation ... The application dashboard may be accurate. It may also be stopping at the wrong boundary. AI systems depend on software, but they also depend on a dense physical stack: racks, power paths, thermal margin, maintenance activity and, in many environments, liquid cooling. Those physical dependencies can change slowly before they look like a software incident ...
Certificate expiration is the rare outage you can see coming. Every TLS certificate carries the date it stops working, so the moment it will begin breaking connections is knowable in advance. That's what makes an expired certificate such a frustrating way to lose a service. What's changing now is how often that date comes around ...
Enterprises operate different combinations of workloads across cloud, hybrid and multicloud environments. For business-critical workloads, teams need to consider monitoring and observability early so they can detect health issues, investigate failures, and understand operational impact. Organizations place workloads on cloud platforms based on a combination of technical requirements, economics, existing dependencies, organizational standards, and business priorities. Their monitoring priorities therefore depend on what they operate and where those systems run. Those priorities will not look the same for every organization ...
Top-performing businesses prioritize data-driven decision making, enabling leaders to move from intuition and gut feel towards evidence-based judgment. But that judgment is only sound when the data underpinning decisions is accurate. With incident management, data accuracy is particularly important. Long-term revenue, customer trust, and operational stability depend on high-quality data that enables teams to quickly identify and address the root cause of major incidents. Against this backdrop, governance becomes a critical endeavor to ensure the right data drives the right action ...
In MEAN TIME TO INSIGHT Episode 26, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network compliance ...
Most production autonomous agents do not run in a vacuum. They run inside cloud infrastructure: virtual machines, containers, pods, managed clusters or private servers. That is where most operations teams start monitoring. Is the VM alive? Is the container running? Did the pod restart? Is memory stable? Is CPU too high? Did the health check pass? Those signals are useful. They tell you whether the shell around the agent is alive. They do not tell you whether the agent inside is actually operational ...
Enterprise IT environments have never been more observable ... Yet many organizations still grapple with outages, lengthy incident resolution cycles, and increasing complexity. Most teams do not suffer from a shortage of data. They struggle to determine what deserves attention and what action to take next ... Enterprise IT operations must move beyond monitoring and visibility. The next stage of maturity is decision operations, an approach that helps teams make faster, better-informed decisions ...