Pinecone Blog

General updates, blog posts about all things Pinecone and vector search.

Introducing cascading retrieval: Unifying dense and sparse with reranking

New cascading retrieval capabilities make it seamless to combine dense retrieval and sparse retrieval and reranking into a unified search pipeline, delivering unparalleled precision, performance, and ease of use.

Read the Blog Post

Product

Accelerate prototyping and development with Pinecone Local

With Pinecone Local, you can now prototype, test, and develop AI applications locally while seamlessly integrating workflow testing into CI/CD pipelines.

Dec 6, 2024

Ana Wishnoff

Senior Product Manager

Product

Introducing integrated inference: Embed, rerank, and retrieve your data with a single API

Announcing expanded inference capabilities alongside our core vector database to make it even easier and faster to build high-quality, knowledgeable AI applications with Pinecone.

Dec 2, 2024

Gibbs Cullen

Staff Product Marketing Manager

Gareth Jones

Staff Product Manager

Product

Strengthening security and increasing control with CMEK and API key roles

A deep dive into how Pinecone supports two new security features, 1) Customer-managed encryption keys (CMEK) and 2) Role-Based Access Control (RBAC) with API key roles

Dec 2, 2024