Features
Portable deployment: edge, on-prem, hybrid, cloud
Sub-15ms local vector search with ANN indexing
99% recall at 10M vectors
Offline operation with sync-on-connect
CRUD operations for vector embeddings
Metadata filtering on vector search
Deploy on Raspberry Pi, NVIDIA Jetson
HIPAA/GDPR-compliant on-premises deployment
Consistent architecture from prototype to production
Integration with Actian Data Intelligence Platform
MCP (Model Context Protocol) server support
Python, JavaScript, Go client libraries
No environment-specific rewrites
Supports disconnected and air-gapped deployments
Fully managed vector database
Automatic index tuning and upgrades
Writes acknowledged in under 100ms
Consistent p99 latency at any scale
Metadata filtering during queries
Namespace-per-agent isolation
Dense, sparse, and full-text indexes
Hybrid search (vector + BM25) via Pinecone Nexus public preview
Integrated embedding and reranking (Cohere Rerank 4.0 Fast GA)
Customer Managed Encryption Keys (CMEK)
Open-source monitoring stack (June 2026)
Multi-region and multi-cloud support (AWS, GCP, Azure) on Builder+
