Weaviate Launches Flexible Embedding Service for AI Development
AMSTERDAM, Dec. 3, 2024 -- Weaviate’s latest SaaS service is bringing freedom and flexibility to a crucial area of AI development: data vectorization. Launched today, Weaviate Embeddings combines the flexibility of open source with the convenience and scalability of a managed service and pay-as-you-go pricing.
Data in an AI application is represented by a unique set of coordinates called a vector embedding, stored in a vector database. The first step in processing any data input or user query is to convert it to embeddings. Embedding services perform this essential task.
While indispensable to AI development, embedding services all too often become a bottleneck for developers. They impose restrictive rate limits that slow down operations. They require remote API calls that hinder performance. They use proprietary models to lock developers into their ecosystem.
Weaviate takes a different approach. Weaviate Embeddings provides access to open-source or proprietary models fully hosted in Weaviate Cloud, eliminating the need to connect to an external embedding provider or bear the burden of self-hosting. Users maintain full control of their embeddings and can easily switch between models.
With Weaviate, choice doesn’t mean sacrificing speed or scalability. Weaviate Embeddings runs on GPUs and brings ML models closer to where data is stored to minimize latency. Unlike other commercial model providers, Weaviate imposes no rate limits or caps on embeddings per second in production environments. And simple pricing reduces the cost of model inference.
“Our goal is to equip developers with the tools and operational support to bring their models closer to their data,” said Weaviate CEO Bob van Luijt. “Weaviate Embeddings makes it simpler for developers to build and manage AI-native applications. For those who prefer a custom approach, our open-source database supports any way they want to work. It’s all about giving developers the freedom to choose what’s best for them.”
Currently available in preview on Weaviate Cloud, Weaviate Embeddings launches with Snowflake’s Arctic-Embed, an open-source text embedding model known for high quality and efficient retrieval. Weaviate plans to add new models and modalities to the service on an ongoing basis starting in early 2025.
Weaviate Embeddings is the latest in a series of projected services to help AI developers move from prototypes to production. Earlier this year Weaviate launched a developer “workbench” of tools and apps for common AI use cases, including a Recommender and tools for queries, collections and data exploration. Weaviate also launched a range of hot, warm and cold storage tiers to reduce the cost of AI-native apps in production.
For more on Weaviate Embeddings, visit the Weaviate website here.
About Weaviate
Weaviate is an open-source AI-native vector database that makes it easier for developers to build and scale AI applications. With powerful hybrid search out of the box, seamless connection to machine learning models and a purpose-built architecture that scales to billions of vectors and millions of tenants, Weaviate is a foundation for modern, AI-native software development. Customers and open-source users, including Instabase, NetApp and Red Hat power search and generative AI applications with Weaviate while maintaining control over their own data. Weaviate was founded in 2019 and is funded by Battery Ventures, Cortical Ventures, Index Ventures, ING Ventures, NEA and Zetta Venture Partners.
Source: Weaviate
