Discover the new serverless architecture of Pinecone's vector database! Get ready to be blown away by keywords right from the start!

A new serverless architecture for Pinecone

For a long time, vector databases were a niche product, but because they're ideally suited to providing context and long-term memory for large language models, everyone in the database space now seems to be trying to add vector search to their existing products as quickly as possible. Meanwhile, dedicated services like Pinecone, founded by the team behind Amazon SageMaker, are leading the way, with Pinecone having raised a total of $138 million since its inception in 2019. Today, Pinecone is launching Pinecone Serverless, a new and vastly improved serverless architecture to power its service.

Pinecone Serverless: an optimized architecture

Pinecone Serverless now separates reads, writes and storage, which should reduce costs for users. Indeed, Pinecone claims that its new architecture can offer a cost reduction of 10x to 100x. The new architecture supports vector grouping in addition to binary object storage. This translates into lower latencies and Pinecone Serverless' ability to support massive data volumes. Similarly, Pinecone Serverless introduces new indexing and search algorithms to enable fast vector search on this storage of binary objects. The service also offers a multi-tenant computing layer.

A serverless solution for easy creation of GenAI applications

"Being truly serverless, it completely eliminates the need for developers to provision or manage infrastructure, making it easier for them to create GenAI applications and bring them to market much faster," the company explains in its announcement. "As a result, developers with use cases of all sizes can create reliable, efficient and impactful GenAI applications with any language model of their choice, resulting in an imminent wave of incredible GenAI applications reaching the market."

Integration with other AI services

From the outset, Pinecone Serverless will offer integrations with several other AI and back-end services, including Anthropic, Anyscale, Cohere, Confluent, LangChain, Pulumi and Vercel. "Vercel's mission is to help the world ship the best products, and in the age of GenAI, that requires Pinecone as a vector database component," said Guillermo Rauch, CEO and founder of Vercel. "That's why we're announcing that all Vercel users can now add Pinecone Serverless to their applications with just a few clicks, with even more exciting features to come."