Weaviate on Google Cloud
Powerful AI-native vector database. Simple, secure deployment on GCP.
End-to-end vector search and
generative AI apps, faster
Weaviate is an open source vector database that's purpose-built for AI. Weaviate cloud service is natively built on Google Cloud and scales using Google Kubernetes Engine. Integrations with Google AI Workbench and Vertex AI, including the latest Foundation Models like Gemini Pro and Ultra LLMs, help developers build and deploy production-ready generative AI applications with less hassle.
AI-native architecture
Sub-second semantic search performance and ability to scale to handle billions of vectors and millions of tenants.
Modular integration framework
Natively integrate with Gemini Pro and Ultra, PaLM, Vertex AI, and model providers like Cohere, OpenAI, Hugging Face, and more. Or, use custom models.
Secure deployment on GCP
Weaviate is available in the GCP marketplace and allows one-click container based scalable deployment inside the customers’ tenant.
Weaviate and Google Cloud integrations
Whether you’re part of a traditional enterprise with an on-prem data footprint or a digital native, Weaviate can meet you where you are in your cloud journey.
Build scalable enterprise infrastructure for Weaviate using Google Cloud’s Virtual Machines (VMs), enabling horizontal scaling and High Availability (HA) for clusters. Load data into Weaviate from any one of Google’s managed databases or cloud storage services, keeping your data contained within your Virtual Private Cloud (VPC).
Take advantage of Google’s generative AI stack with Weaviate to build next-generation AI applications.
Features and Pricing
Contact gcp-marketplace@weaviate.io to receive details about your critical response SLA, the setup of support channels (Slack, email, and phone), and to receive optional complimentary training from experts at Weaviate.