pgvector LangChain
The langchain-postgres package provides a PGVector vector store for LangChain using pgvector as the backend.
Ecosystem
pgvector ecosystem
Because pgvector works through ordinary SQL, it is usable from any language with a PostgreSQL client. The project maintains official bindings for many languages, and a wider set of frameworks, extensions, and tools build on it. Everything here links to its own source; none of these are affiliations unless stated.
Client libraries
Official language bindings
These bindings live under the pgvector GitHub organization. You can also use any PostgreSQL driver directly, or generate vectors in one language and query them in another.
| Language | Repository |
|---|---|
| Ada | pgvector-ada |
| Algol | pgvector-algol |
| C | pgvector-c |
| C++ | pgvector-cpp |
| C#, F#, Visual Basic | pgvector-dotnet |
| COBOL | pgvector-cobol |
| Crystal | pgvector-crystal |
| D | pgvector-d |
| Dart | pgvector-dart |
| Elixir | pgvector-elixir |
| Erlang | pgvector-erlang |
| Fortran | pgvector-fortran |
| Gleam | pgvector-gleam |
| Go | pgvector-go |
| Haskell | pgvector-haskell |
| Java, Kotlin, Groovy, Scala | pgvector-java |
| JavaScript, TypeScript | pgvector-node |
| Julia | Pgvector.jl |
| Lisp | pgvector-lisp |
| Lua | pgvector-lua |
| Nim | pgvector-nim |
| OCaml | pgvector-ocaml |
| Pascal | pgvector-pascal |
| Perl | pgvector-perl |
| PHP | pgvector-php |
| Prolog | pgvector-prolog |
| Python | pgvector-python |
| R | pgvector-r |
| Racket | pgvector-racket |
| Raku | pgvector-raku |
| Ruby | pgvector-ruby, Neighbor |
| Rust | pgvector-rust |
| Swift | pgvector-swift |
| Tcl | pgvector-tcl |
| Zig | pgvector-zig |
No bindings match your search.
Frameworks
Framework & ORM integrations
Popular application frameworks provide first-class pgvector support. These are third-party integrations that use pgvector; they are not maintained by the pgvector project.
LlamaIndex
The llama-index-vector-stores-postgres package adds a Postgres vector store backed by pgvector for LlamaIndex.
Django
The official pgvector-python binding includes Django support, so you can use vector fields and lookups in your models.
Ruby on Rails
The Neighbor gem adds nearest-neighbor search to Rails on top of pgvector, for Active Record models.
Related extensions
Related PostgreSQL extensions
These open-source PostgreSQL extensions build on or complement pgvector. Confirm licensing and operational fit for your own use before adopting one.
pgvectorscale
Adds a diskann index (StreamingDiskANN, inspired by Microsoft's DiskANN research), statistical binary quantization, and label-based filtered search. Written in Rust with PGRX; requires pgvector. From Timescale.
VectorChord
Adds the vchordrq index using RaBitQ compression with autonomous re-ranking, plus low-bit vector types. Requires pgvector. Dual-licensed AGPL-3.0 / Elastic License v2. From TensorChord.
Lantern
Provides a lantern_hnsw index built on the usearch HNSW implementation, interoperable with pgvector's data type, with embedding helpers and parallel index creation.
pgvecto.rs
An earlier Rust-based vector extension from the VectorChord team, now superseded by VectorChord. Relevant mainly for existing deployments.
See the comparison page for how these fit against pgvector and dedicated vector databases.
Operations
Operations & tooling
Tools that help you run, tune, and scale pgvector in production. These are general PostgreSQL tools that pgvector's own documentation points to.
PgHero
A performance dashboard for PostgreSQL that surfaces slow queries and index usage — useful for finding vector queries that need tuning. ankane/pghero →
PgTune
Generates starting values for PostgreSQL server configuration based on your hardware, which pgvector recommends before tuning vector indexes. pgtune.leopard.in.ua →
pg_stat_statements
The PostgreSQL extension for tracking query execution statistics, useful for monitoring vector query latency. PostgreSQL docs →
Citus
Distributes PostgreSQL across nodes for horizontal scaling. The upstream pgvector examples include a Citus sharding example. citusdata/citus →
PgDog
A PostgreSQL proxy for sharding, connection pooling, and load balancing, referenced by pgvector for scaling out. pgdogdev/pgdog →
setup-pgvector (CI)
A GitHub Action that installs pgvector in a workflow, maintained by the pgvector organization. pgvector/setup-pgvector →
Managed
Hosted providers
Many hosted PostgreSQL providers ship pgvector, so you can enable the extension without installing anything. Check each provider's documentation for the pgvector version it offers. The upstream project also maintains a community list in issue #54.
Supabase
Offers pgvector for vector columns and AI features.
Neon
Ships the pgvector extension on its serverless Postgres.
Timescale
Provides pgvector, plus the pgvectorscale extension.
Amazon RDS for PostgreSQL
Lists pgvector among its supported extensions.
Google Cloud SQL
Supports pgvector in Cloud SQL for PostgreSQL.
Azure Database for PostgreSQL
Includes pgvector in its supported extensions.
Get involved
Contributing
The pgvector project welcomes contributions through its contributing guide: report bugs, submit pull requests, improve documentation, and suggest features. Language bindings in the pgvector organization accept contributions too.
New to pgvector? Read the documentation and the install guide, then generate your first index with the index planner.