Pinecone is a managed vector database for semantic, full-text (BM25) and hybrid search. It offers hosted embedding and reranking models, namespaces and metadata filtering, with Python and JavaScript SDKs and a REST API.
Java SDK 6.3.1 stops whitespace-padded API keys being echoed into errors and logs, and stops close() dropping async writes.
pg_pinecone 0.12.1 embeds a text column with a hosted model, so no vector column is needed. Starter and Builder embedding tokens doubled.
Pinecone Java SDK 6.3.0 fixes cross-key connection sharing and 33 dependency advisories. Close every Index you open after upgrading.
Pinecone now hosts gemini-embedding-2, text-embedding-3-small and text-embedding-3-large for integrated embedding on document indexes.
pg_pinecone is an open-source Postgres extension that runs Pinecone's vector search in your database, with no changes to pgvector queries.
Wirestack