pg_pinecone 0.13.0

This Release
pg_pinecone 0.13.0
Date
Status
Stable
Abstract
Pinecone vector search inside PostgreSQL
Description
pg_pinecone brings Pinecone vector search into PostgreSQL. Index a vector column with the native engine, pgvector, or a remote Pinecone serverless index, and keep a Pinecone full-text index in sync with a table.
Released By
pinecone
License
Apache 2.0
Resources
Special Files
Tags

Extensions

pg_pinecone 0.13.0
Pinecone vector search inside PostgreSQL

Documentation

CONTRIBUTING
Contributing to pg_pinecone
REPORT-halfvec-filtered
Vector benchmark: pgvector halfvec (FP16) in the filtered cells, against FP32 hnsw and pg_pinecone 0.10.0 (2026-10-22)
CLAUDE
CLAUDE.md
README
pg_pinecone/pgvector ANN benchmark harness
REPORT-wikidpr-10m
Vector benchmark: pg_pinecone 0.11.0 against pgvector HNSW on wiki_dpr 10M (2026-10-27)
conclusion
Installation Complete
BOX-2026-10-16-halfvec
Box 2026-10-16: resolved facts of the halfvec session
README
Box for the vector benchmark (pg_pinecone 0.10.0)
CODE_OF_CONDUCT
Contributor Covenant Code of Conduct
README
Benchmarks
reference
Reference
README
upgrade scripts pg_pinecone––.sql live here (docs/contributing.md)
CHANGELOG
Changelog
welcome
Welcome
disaster-recovery
Disaster recovery: restore -> repoint -> recover
REPORT-halfvec
Vector benchmark: pgvector halfvec (FP16) against FP32 hnsw and pg_pinecone native from main (2026-10-16)
SECURITY
Security Policy
contributing
Contributing
runbook
Operator runbook
requirements
requirements
REPORT-overram
Vector benchmark: search under a 4 GB memory cap, pgvector hnsw (FP32, FP16) and pg_pinecone 0.10.0 (2026-10-23)
BOX-2026-10-22-hvfilt
Box 2026-10-22: resolved facts of the filtered halfvec session
tutorial-gemini-document-search
Semantic search over a Postgres table with Gemini — in SQL
RUNBOOK
Over-RAM workload: Docker variant + runbook
BOX-2026-10-27-10m
Box 2026-10-27: resolved facts of the wiki_dpr 10M session
BOX-2026-10-22-overram
Box 2026-10-22: resolved facts of the over-RAM session
REPORT-residual-filter
Residual-filter benchmark: pg_pinecone iterative scan vs pgvector hnsw (2026-10-07)
README-residual
Residual-filter benchmark (iterative scan): residual-c1.yaml, residual-c2.yaml
pull_request_template
pull_request_template

README

pg_pinecone

CI License

An open-source PostgreSQL extension that brings Pinecone’s vector search into the Postgres database you already run. Keep your tables and your pgvector queries, and choose an engine per table.

  • Three engines behind one index: pgvector, native (the default), and remote. Switch a table between them without changing a query.
  • Filtered search inside Postgres: the native engine applies a filter such as a tenant ID during the search, with no account or network access.
  • Scale out when you need to: the remote engine moves a table’s search to a Pinecone serverless index, and Postgres keeps every row.
  • Full-text search: keep a Pinecone index for full-text search in sync with a table and run BM25, vector, or hybrid searches from SQL.
  • pgvector compatible: index existing vector columns as they are.

How it works

An application sends pgvector SQL to Postgres, which keeps the rows and their vector column. pg_pinecone searches them with the native engine (the default), the pgvector engine, or the remote engine, which syncs to a Pinecone serverless index and returns the results.

Engines

Engine Where the search runs Use it for
pgvector pgvector’s own HNSW or IVFFlat index, in Postgres Tables that already have a pgvector index and don’t filter
native (default) The search engine Pinecone uses at scale, in Postgres Filtered and unfiltered search, with a small index and no network calls
remote A Pinecone serverless index A table that has outgrown one Postgres server

Every switch can be reversed. The pg_pinecone docs cover how the engines compare and how to switch between them.

Quickstart

Requirements: PostgreSQL 17 or 18, superuser access, and pgvector installed on the server.

Install it one of two ways:

  • Prebuilt release: download the archive for your platform and Postgres version from the releases page and copy its files into your Postgres installation, as step 1 of the quickstart shows.
  • Docker: pineconeteam/pg_pinecone is the pgvector/pgvector image with pg_pinecone added, one tag per Postgres major: docker run -d -e POSTGRES_PASSWORD=secret pineconeteam/pg_pinecone:0.11.0-pg17 (add -c shared_preload_libraries=pg_pinecone for the remote engine).

Then create the extensions and index a vector column:

CREATE EXTENSION vector;
CREATE EXTENSION pg_pinecone;

CREATE TABLE items (id bigint PRIMARY KEY, embedding vector(3));
INSERT INTO items VALUES (1, '[1,2,3]'), (2, '[4,5,6]'), (3, '[7,8,9]');

-- Builds a native index. No API key or network access needed.
SELECT pinecone.create_index('items', 'embedding');

SELECT id FROM items ORDER BY embedding <=> '[1,2,4]' LIMIT 2;

For a full walkthrough on a sample table, including semantic search with embeddings, see the quickstart in the pg_pinecone docs.

Deploy

One-click Postgres 18 with pg_pinecone already installed:

  • Railway: a database and a connection URL.
  • Render: a private service. Other services in the same workspace and region connect over the private network.

Build from source

pg_pinecone is built with pgrx. You need a Rust toolchain and the headers of the Postgres you’re building for (pg_config on your PATH, or pass its path to --pg-config).

git clone https://github.com/pinecone-io/pg_pinecone.git
cd pg_pinecone/pg_pinecone
cargo install cargo-pgrx --version 0.19.2 --locked
cargo pgrx init --pg17 "$(which pg_config)"   # use --pg18 for PostgreSQL 18
cargo pgrx install --release                  # builds and installs into that Postgres

cargo pgrx install writes the extension into the Postgres pg_config points at; then CREATE EXTENSION vector; CREATE EXTENSION pg_pinecone; as above. On x86_64 the build targets your own CPU, so it runs anywhere you build it. For running the tests, see CONTRIBUTING.md.

Verifying releases

Release tarballs, the source zip, the Postgres.app package, and the SBOM (pg_pinecone-<version>.cdx.json) carry GitHub build-provenance attestations. The Docker images are also signed with keyless cosign. Pin the signer to this repo’s release workflows on main or a v* tag; a run from any other branch is not a release.

ID='^https://github\.com/pinecone-io/pg_pinecone/\.github/workflows/(release|docker-publish)\.yml@refs/(heads/main|tags/v.+)$'

gh attestation verify pg_pinecone-<version>-pg18-linux-x86_64.tar.gz \
  --repo pinecone-io/pg_pinecone --cert-identity-regex "$ID"
gh attestation verify oci://pineconeteam/pg_pinecone:<version>-pg18 \
  --repo pinecone-io/pg_pinecone --cert-identity-regex "$ID"

cosign verify pineconeteam/pg_pinecone:<version>-pg18 \
  --certificate-oidc-issuer https://token.actions.githubusercontent.com \
  --certificate-identity-regexp "$ID"

Documentation

The pg_pinecone docs on docs.pinecone.io cover installation, the storage engines, switching engines, and full-text search.

In this repository:

Support

Contributing

Start with an issue. See CONTRIBUTING.md for how proposals and pull requests work.

License

Apache License 2.0