Pinecone AI Search

Pinecone serverless vector DB RAG-optimized.

Definition

Pinecone Serverless decoupled compute / storage architecture, pay-per-query, auto-scaling. Distance metrics: cosine, dot-product, euclidean. Metadata filtering. Hybrid search (sparse-dense). Managed embeddings (Pinecone Inference). SDK Python, Node.js, Java, Go. 2GB storage free tier. 5000+ enterprise customers including Shopify, Notion, Gong, You.com.

Origin

Pinecone Systems Inc., founded 2019 in New York, Series A $28M 2021, Series B $100M 2023 $750M valuation.

Usage

Dominant SaaS vector DB. Competes with Weaviate, Qdrant, ChromaDB (OSS), Milvus (Zilliz Cloud), Vespa.

Related terms

• Vector database — catégorie.
• RAG — cas usage central.
• Embeddings — inputs natifs.