Pinecone BYOC: trusted AI knowledge in the customer cloud. Sep 23, 2026 Today, Pinecone is announcing the general availability of Pinecone Bring Your Own Cloud (BYOC) on AWS, Google Cloud, and Azure, bringing Pinecone's trusted AI knowledge platform to where enterprise data needs to live. AI becomes transformative when it works with a company's proprietary knowledge. Customer context, policies, and operational history allows its agents to make decisions and carry out work using expertise the business has built over years. Organizations have spent years controlling where sensitive knowledge lives and who can reach it. Providing access to it typically meant managing knowledge infrastructure ranging from inference, document parsing, and vector databases. Platform teams shouldered the burden of tuning and maintaining the system, including keeping retrieval quality and performance stable across a diverse set of AI workloads. With BYOC, customer data and the knowledge derived from it remain in the customer's account, while Pinecone manages the platform operations. This means teams can bring sensitive AI workloads to production without taking on the complexity of operating knowledge infrastructure themselves. The APIs and interfaces remain the same as the managed service, providing organizations with the flexibility to select the right deployment model for each workload based on its security, connectivity, and operational requirements. Keeping proprietary knowledge inside the customer cloud. Pinecone's platform architecture separates the systems that manage the service from those that store and process customer data. * Control Plane: Handles management operations such as resource lifecycle, authentication, and service health. It does not store or process customer content or request payloads. * Data Plane: Stores, processes, and serves customer data and knowledge. AI agents and applications connect directly to this for read and write operations. The only data shared with Pinecone are anonymized operational metrics and traces for monitoring and support. With BYOC, the data plane runs inside the customer's selected cloud account and region, including those beyond where Pinecone's standard service is available. Vectors, documents, metadata, and request payloads remain within the customer-controlled boundary. Zero-access BYOC model. Pinecone does not require SSH, VPN, inbound network access, or a standing cross-account IAM role to manage the service. Upgrades, scaling actions, and maintenance work are retrieved using an outbound call from the Pinecone control plane and executed locally. This pull-based mechanism allows Pinecone to manage the database without a persistent access path into the customer environment. Additionally, BYOC works alongside SSO, RBAC, SCIM + SAML, audit logging, encryption, and private-networking controls available with Pinecone's Enterprise plan so customers can have complete confidence in ensuring their proprietary knowledge is secure. Keep the managed Pinecone experience. In addition to Pinecone handling upgrades, scaling, maintenance, and service health monitoring, customers retain access to Pinecone's support and engineering teams for troubleshooting, incident response, and ongoing operational guidance. Teams use the same Pinecone APIs, SDKs, and control plane workflows across the BYOC and standard deployments. This means each workload can use the deployment model that fits its data governance and access requirements without creating a separate development path. Toyota brings manufacturing knowledge to AI within its environment. Toyota Motor North America (TMNA) was one of Pinecone's first BYOC customers. TMNA used Pinecone to ground AI applications with decades of proprietary manufacturing knowledge while keeping that knowledge secure inside Toyota's environment. "Decades of engineering expertise and R&D knowledge live across our technical documentation, specifications, test data, and research. R&D GPT, backed by Pinecone's vector database, helps bring that institutional knowledge together, giving our engineers a faster and more intuitive way to discover, connect, and apply the information they need while maintaining the security, governance, and access controls our enterprise requires. It helps our teams spend less time searching for knowledge and more time applying it to accelerate innovation." - Ravi Chandu Ummadisetti, Head of Agentic AI & Product Research, Toyota Motor North America "A vast amount of our manufacturing know-how lives in our documentation, and that institutional knowledge is one of the most valuable assets we have. It also happens to be complex - highly structured engineering data sitting alongside unstructured process documents, across a lot of formats and a lot of different access patterns. Pinecone BYOC runs inside our own environment, so that knowledge never leaves our boundary and is served only to models we've already vetted. It handles that complexity at the scale our operations demand, with the enterprise security and governance controls our teams require. A critical requirement for how our team can use AI with confidence." - Kordel France, Head of AI Engineering, Toyota Motor North America Bringing trusted AI knowledge to more environments. Its mission is to make AI knowledgeable, everywhere. BYOC extends Pinecone's trusted AI knowledge platform to customer-controlled cloud environments today, and its work continues beyond BYOC. Pinecone is developing a fully self-managed option for air-gapped and highly restricted networks where both the control plane and data plane will run inside the customer environment. Reach out if you're interested in shaping the security and deployment requirements of a self-managed Pinecone offering. Get started. Talk with your Pinecone account team to review your requirements and plan your BYOC deployment, or contact Pinecone to get connected with Pinecone.

Zilliz launches Milvus vector lakebase. Chris Mellor STORAGE EDITOR Blocks & Files editor Published thu 16 Jul 2026 // 18:17 UTC Zilliz has announced its v3.0 update to Milvus, its open-source vector database adding lake-native data access and a more expressive retrieval engine to developers building production AI applications. Lake-native means the data's primary home is open formats on cloud object storage (a data lake) - not loaded into a separate database. Zilliz has been talking about its Vector Lakebase technology since June, public preview start time, when CEO and founder Charles Xie said it was "one data foundation where the same vectors can serve a production query, anchor a discovery session, and power a multi-petabyte training-data pipeline - without copies, migration, or a parallel stack." Unified lake-native storage, Zilliz says, means one storage layer, on object storage, that serves both low-latency online search and large-scale analytics over the same files. James Luan, Zilliz Co-founder and CTO, said: "Milvus 3.0 brings production retrieval closer to where data already lives and gives developers a more expressive engine for modern AI applications. That same foundation powers Zilliz Vector Lakebase, where we extend it with the elasticity, operational simplicity, and enterprise capabilities required to manage AI data at scale." Vector databases store vector embeddings, the mathematically calculated numeric representations of various dimensions of a word or image. Vector databases provide vector search facilities to find similar vectors. Items with similar values on the same dimensions have vectors that are closer to the stores ones than dissimilar items. Zilliz says Milvus is the most popular open-source vector database world-wide, with more than 10,000 organizations using it for RAG, search, recommendations, and AI agents in production. It has also accumulated more than 100 million Docker pulls. Zilliz says production AI systems commonly maintain one copy of data for real-time retrieval and another for offline processing. Moving data between the two introduces additional storage overhead, lengthy exports, synchronization pipelines, and operational complexity. Milvus 3.0 enables organizations to build and serve production-grade indexes over vector data that remains in object storage and open data formats. It also moves more query and retrieval operations into the engine, expanding Milvus beyond traditional nearest-neighbor search to support richer ranking, aggregation, sparse search, and multi-vector retrieval. V3.0 features; * External Collections define Milvus collections over data stored in Lance, Iceberg, Parquet, or Vortex. Milvus builds vector, full-text, JSON, and scalar indexes over the data and exposes them through the same APIs as native collections - without copying the source data into Milvus. Incremental synchronization keeps indexes current as the underlying dataset changes. * Loon, the new manifest-based storage engine in Milvus 3.0, is designed to substantially reduce the read amplification associated with low-latency point access on object storage. It uses Vortex, an open and Arrow-compatible columnar format, as its default storage format. * Snapshots create point-in-time, read-only views of live collections at minimal incremental storage cost. Offline jobs such as evaluation, deduplication, and backfill validation can run against a stable dataset while production writes continue. * A new Spark connector exposes Milvus as a Spark DataSource V2, allowing Spark, Databricks, and EMR pipelines to read from and write to Milvus as part of standard batch workflows. Milvus 3.0 also introduces vector-native batch operators for tasks including deduplication and clustering. Top-K vector search means finding the K most conceptually similar items to a query item, using mathematical distance rather than exact keyword matching. "K" is a number such as 5, 10 or 20. Top-K searches don't scale well as they measure distances between vectors across an entire dataset. The more vectors and dimensions in the dataset the longer the search takes. Luan said: "Production applications rarely stop at returning the nearest vectors. They need to sort, group, build facets, and retrieve across multiple representations of the same entity. Milvus 3.0 moves more of that work into the engine while redesigning storage for efficient, low-latency access on object storage." Milvus 3.0 expands search retrieval beyond traditional top-K vector search to include; * Server-side sorting and aggregation, together with faceted search, allow applications to combine semantic relevance with attributes such as freshness, rating, price, category, tenant, and content source. Operations that previously required over-fetching data and processing it in application code can now execute directly within the Milvus engine. * StructList introduces native multi-vector retrieval for documents, images, and other entities represented by more than one vector. A document can retain vectors for multiple chunks, an image can retain vectors for multiple visual patches, and a product can retain several multimodal representations under a single entity and metadata record. StructList also supports late-interaction retrieval models such as ColBERT and ColPali. * Milvus 3.0 strengthens sparse and hybrid retrieval with an optimized sparse index that is approximately 3 times smaller while achieving comparable recall in internal testing. * Enhancements also include SINDI for learned-sparse vectors, server-side MinHash generation, nullable vector fields, custom dictionaries for full-text search, and broader support for Faiss-compatible indexes. This release develops the shared technical foundation behind both open-source Milvus and Zilliz Cloud. Developers can deploy Milvus independently, while Zilliz Cloud builds on the Milvus core to deliver a fully-managed Vector Lakebase spanning real-time serving, interactive discovery, batch analytics, and AI data operations. Zilliz has given competitors Pinecone, Qdrant and Weaviate something to think about. All four are looking to lower search times. Qdrant introduced faster indexing, 3-way clusters for instant failover, and audit logging for compliance. In April. Pinecone announced precompiled vector sets and a composable retriever in May to speed AI agent searches. They appear to be assuming that, by providing better vector-based search facilities, they can prosper while competing with multi-model databases such as Regatta, SingleStore, SurrealDB and others. The vector-only suppliers do partner upstream with analytic lakehouse suppliers such as Snowflake and Databricks, but partnering with other database suppliers might be difficult because of database core architecture and storage engine difficulties. It will be interesting to see if one or more of the vector-only database suppliers starts adding/developing support for other database model types, such as structured, graph, document and time-series data. Availability. Milvus 3.0 is available under the Apache 2.0 license and remains a graduated LF AI & Data project. It can be deployed on Kubernetes or Docker, including in air-gapped environments, and supports S3-compatible object storage, Google Cloud Storage, and Azure Blob Storage. The release is available initially through the Python, Go, and Node.js SDKs, with Java support planned shortly after release. Developers can read the release notes, follow the quickstart, and access the source code on GitHub. They can also join the Milvus community or speak with project maintainers through Milvus Office Hours. For organizations that prefer a managed platform, Zilliz Cloud incorporates Milvus 3.0 as its core indexing and retrieval engine and extends it into a fully managed Vector Lakebase. Zilliz Cloud adds elastic compute, interactive discovery, batch analytics, shared indexing, enterprise security and governance, and automated operations across a single copy of AI data. Bootnote. External Collection builds real vector, full-text, JSON, and scalar indexes over lake-resident data and Loon removes the read amplification that made object storage impractical for low-latency point lookups. External Collection does not copy data. It is read-only and zero-copy: Milvus maps fields from your existing Lance, Iceberg, Parquet, or Vortex data and builds indexes over it in place. The files stay in your lake under your governance; incremental sync picks up changes.

Database vendors are positioning themselves as a solution to escalating AI costs as major providers shift towards usage-based billing. Companies like Pinecone and Tiger Data claim they can reduce expenses by minimising calls to AI models and managing workloads from developer agents. Pinecone has launched Nexus, a knowledge engine that structures and contextualises business data in advance, preventing agents from repeatedly rediscovering information and burning through tokens. Tiger Data's Ghost platform offers instant PostgreSQL databases with usage-based pricing, charging by compute-hours rather than database count. According to IDC research, 79% of organisations are investing significantly in agentic AI. However, analysts note that established database vendors like Snowflake, Oracle and Microsoft are absorbing similar capabilities, creating uncertainty over whether specialists or platforms will dominate this emerging market.