Elastic recently announced that Jina Embeddings v3 is now available as a self-deployable partner model in the Gemini Enterprise Agent Platform Model Garden. This is the first Jina model to join the platform. It allows organizations to deploy high-performance retrieval models directly within their own cloud environments. Enterprises can now run these models inside their Google Cloud projects and Virtual Private Clouds (VPCs).
Data Sovereignty and Predictable Pricing
This deployment model keeps sensitive data within the customer’s security perimeter. It is ideal for regulated industries that need to avoid external API calls. Enterprises maintain full control over their data at all times. Furthermore, the platform offers total data sovereignty for all processed information. Users pay a flat hourly rate for compute rather than traditional per-token metering. This structure rewards scale and high-volume traffic.
The integration connects seamlessly with existing Google Cloud services. This includes BigQuery, Cloud Storage, and IAM for security and billing.
“We’re bringing Jina models into Model Garden to make high-performance retrieval easier to deploy inside enterprise environments,” said Ken Exner, chief product officer at Elastic. “Organizations are no longer forced to choose between performance and control. They can now run production-ready embeddings directly within their Google Cloud VPC, with full ownership of their data and predictable costs.”
Jina Embeddings v3 supports various multilingual semantic search and retrieval use cases. It is widely used in production across the Elasticsearch ecosystem.
Explore IT Tech News for the latest advancements in Information Technology & insightful updates from industry experts!
News Source: Businesswire.com
