New platform lets developers build more accurate AI apps faster
High-quality retrieval is key to delivering the best user experience in AI search and retrieval-augmented generation (RAG) applications.
Knowledge platform Pinecone has announced new vector database capabilities combined with proprietary AI models to help developers build more accurate AI applications, faster and more easily.
"Our goal at Pinecone has always been to make it as easy as possible for developers to build production-ready knowledgeable AI applications quickly and at scale," says Edo Liberty, founder and CEO of Pinecone. "By adding built-in and fully-managed inference capabilities directly into our vector database, as well as new retrieval functionality, we're not only simplifying the development process but also dramatically improving the performance and accuracy of AI-powered solutions."
By combining sparse retrieval, dense retrieval, and re-ranking capabilities within Pinecone, developers will be able to create end-to-end retrieval systems that deliver up to 48 percent and on average 24 percent better performance than dense or sparse retrieval alone.
It uses two proprietary models, pinecone-rerank-v0 which improves search accuracy by up to 60 percent, and on average nine percent, over industry-leading models on the Benchmarking-IR (BEIR) benchmark. In addition pinecone-sparse-english-v0 boosts performance for keyword-based queries.
A single API means engineers can now develop state-of-the-art applications without the burden of managing model hosting, integration, or infrastructure. Pinecone has also collaborated with Cohere to host cohere-rerank-v3.5 natively within the platform. This allows customers to easily select and use cohere-rerank-v3.5 directly from the Pinecone API to enhance the relevance of their search results.
Security is built in too, role-based access controls let users set API key roles for control and data plane operations, while customer-managed encryption keys enable users to control their own data encryption.
Pinecone is available through the AWS marketplace and developers can get started for free on the Pinecone console.
Image credit: BiancoBlue/depositphotos.com