Elastic, the Search AI Company, today announced support for Google Cloud’s Vertex AI platform in the Elasticsearch Open Inference API  and Playground. Developers can now use Vertex AI’s text embedding and reranking models to build production applications on the Elasticsearch vector database. Also, with Elastic Playground, developers can quickly prototype and iterate on RAG applications with Vertex AI and Google Cloud’s Gemini models. 

“We’re excited to collaborate with Elastic to bring Vertex AI and Gemini models to even more developers,” said Warren Barkley, senior director of Product Management for Vertex AI at Google Cloud. “As innovation in generative AI and RAG applications continues to grow, this integration with Elasticsearch will enable the Elastic community to easily and effectively harness Vertex AI and our models to build transformative applications.”

“Our latest integration with Google Cloud’s Vertex AI platform makes a unified AI development platform accessible to Elastic developers, said Shay Banon, founder and chief technology officer at Elastic. “Vertex AI and Elasticsearch are proven at a vast scale, and we’re looking forward to seeing what developers build with their combined capabilities.”

Developers using Elasticsearch and Vertex AI can now store and use embeddings, refine retrieval to ground answers with proprietary data and more. Google Cloud’s Gemini models are available in the Elastic low-code playground experience, giving developers more choices when A/B testing LLMs, tuning retrieval and chunking. 

Support for Vertex AI is available today. Read the Open Inference API and Playground blogs to get started.  

For more information on previous integrations between Elastic and Google Gemini 1.5 models via Vertex AI, read the Elastic blog.