Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Pinecone's vector database gets a new serverless architecture | TechCrunch

Jan 16, 2024 - news.bensbites.co
Pinecone, a dedicated vector database service, is launching Pinecone Serverless, a significantly enhanced serverless architecture for its service. The new architecture separates reads, writes, and storage, potentially reducing costs for users by 10x to 100x. It supports vector clustering on top of blob storage, resulting in lower latencies and the ability to support massive data sizes. New indexing and retrieval algorithms have also been introduced for fast vector search across blob storage, and a multi-tenant compute layer is now offered.

The company claims that the serverless nature of the service eliminates the need for developers to manage infrastructure, making it easier to build and market GenAI applications. Pinecone Serverless will offer integrations with several other AI and backend services, including Anthropic, Anyscale, Cohere, Confluent, Langchain, Pulumi, and Vercel. Vercel users can now add Pinecone Serverless to their applications in just a few clicks.

Key takeaways:

  • Pinecone is launching Pinecone Serverless, a new and significantly enhanced serverless architecture to power its service, which separates reads, writes, and storage, potentially reducing costs for users.
  • The new architecture supports vector clustering on top of blob storage, resulting in lower latencies and the ability to support massive data sizes.
  • Pinecone Serverless introduces new indexing and retrieval algorithms for fast vector search across blob storage and offers a multi-tenant compute layer.
  • Pinecone Serverless will offer integrations with several other AI and backend services, including Anthropic, Anyscale, Cohere, Confluent, Langchain, Pulumi, and Vercel.
View Full Article

Comments (0)

Be the first to comment!