New proprietary reranking and embedding models, as well as the addition of third-party models like Cohere's Rerank 3.5 model, further provide customers quick, easy access to high-quality retrieval and significantly streamline the development of grounded AI applications."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," said 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."Pinecone's composable platform now includes the following updates:pinecone-rerank-v0 proprietary reranking modelproprietary reranking model pinecone-sparse-english-v0 proprietary sparse embedding modelproprietary sparse embedding model New sparse vector index typeIntegration of Cohere's Rerank 3.5 modelNew security features, including role-based access controls (RBAC), audit logs, customer-managed encryption keys (CMEK), and the general availability (GA) of Private Endpoints for AWS PrivateLinkAdvancing the state of the art for retrievalHigh-quality retrieval is key to delivering the best user experience in AI search and retrieval-augmented generation (RAG) applications. Pinecone's research shows that state-of-the-art performance requires combining three key components:Dense vector retrieval to capture deep semantic similaritiesto capture deep semantic similarities Fast and precise sparse retrieval for keyword and entity search using a proprietary sparse indexing algorithmfor keyword and entity search using a proprietary sparse indexing algorithm Best-in-class reranking models to combine dense and sparse results and maximize relevanceBy combining the sparse retrieval, dense retrieval, and reranking capabilities within Pinecone, developers will be able to create end-to-end retrieval systems that deliver up to 48% and on average 24% better performance than dense or sparse retrieval alone."With the advent of GenAI, we knew we could challenge the status quo in talent acquisition by building an experience focused on the job seeker rather than the hiring company," said Alex Bowcut, CTO of Hyperleap. "With Pinecone, we've seen 40% better click-through rates for the job matches we deliver with search results using their semantic retrieval as opposed to traditional full-text search. Now, with the addition of sparse vector retrieval to Pinecone's proven natural language search capabilities, we're excited to explore how we can bring deeper personalization to people looking for work."Pinecone proprietary modelsWith the introduction of its first proprietary models, Pinecone is making it easier for developers to build knowledgeable AI.Natively integrated into Pinecone's platform, these models simplify the development of production-ready AI applications.AI search simplified with integrated inferenceWith the release of Pinecone's integrated inference capability, engineers can now develop state-of-the-art applications without the burden of managing model hosting, integration, or infrastructure. By offering these capabilities behind a single API, developers can seamlessly access top embedding and reranking models hosted on Pinecone's infrastructure, eliminating the need to worry about vectors or data being routed through multiple providers

Pinecone has also announced the general availability of Private Endpoints for AWS PrivateLink.

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More. Pinecone has made a name for itself in recent years as being one of the leading native vector database platforms. Pinecone is continuing to differentiate in an increasingly competitive market with new capabilities to help solve enterprise AI challengesToday Pinecone announced a series of updates to its namesake vector database platform. The updates include a new cascading retrieval approach that combines the benefits of dense and sparse vector retrieval. Pinecone is also deploying a new set of reranking technologies designed to help improve accuracy and efficiency for vector embeddings