Baike.dev
All toolsOnline toolsAI codingTrendingOpen sourceNewsSubmit
Log in
< Back to tools
P

pgvector-go

> 编程语言
Open source

pgvector support for Go

347 stars0 likes1 views
WebsiteGitHub

About

pgvector support for Go

pgvector-go

pgvector support for Go

Supports pgx, pg, Bun, Ent, GORM, and sqlx

pgvector-go 0.4.0 was recently released - see how to upgrade

Getting Started

Follow the instructions for your database library:

  • pgx
  • pg
  • Bun
  • Ent
  • GORM
  • sqlx

Or check out some examples:

  • Embeddings with OpenAI
  • Binary embeddings with Cohere
  • Hybrid search with Ollama (Reciprocal Rank Fusion)
  • Sparse search with Text Embeddings Inference
  • Recommendations with Disco
  • Horizontal scaling with Citus
  • Bulk loading with COPY

pgx

Run:

bash
go get github.com/pgvector/pgvector-go
go get github.com/pgvector/pgvector-go/pgx

Import the packages

go
import (
    "github.com/pgvector/pgvector-go"
    pgxvec "github.com/pgvector/pgvector-go/pgx"
)

Enable the extension

go
_, err := conn.Exec(ctx, "CREATE EXTENSION IF NOT EXISTS vector")

Register the types with the connection

go
err := pgxvec.RegisterTypes(ctx, conn)

or the pool

go
config.AfterConnect = func(ctx context.Context, conn *pgx.Conn) error {
    return pgxvec.RegisterTypes(ctx, conn)
}

Create a table

go
_, err := conn.Exec(ctx, "CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))")

Insert a vector

go
_, err := conn.Exec(ctx, "INSERT INTO items (embedding) VALUES ($1)", pgvector.NewVector([]float32{1, 2, 3}))

Get the nearest neighbors to a vector

go
rows, err := conn.Query(ctx, "SELECT id FROM items ORDER BY embedding  $1 LIMIT 5", pgvector.NewVector([]float32{1, 2, 3}))

Add an approximate index

go
_, err := conn.Exec(ctx, "CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)")
// or
_, err := conn.Exec(ctx, "CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)")

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

See a full example

pg

Run:

bash
go get github.com/pgvector/pgvector-go

Import the package

go
import "github.com/pgvector/pgvector-go"

Enable the extension

go
_, err := db.Exec("CREATE EXTENSION IF NOT EXISTS vector")

Add a vector column

go
type Item struct {
    Embedding pgvector.Vector `pg:"type:vector(3)"`
}

Insert a vector

go
item := Item{
    Embedding: pgvector.NewVector([]float32{1, 2, 3}),
}
_, err := db.Model(&item).Insert()

Get the nearest neighbors to a vector

go
var items []Item
err := db.Model(&items).
    OrderExpr("embedding  ?", pgvector.NewVector([]float32{1, 2, 3})).
    Limit(5).
    Select()

Add an approximate index

go
_, err := conn.Exec(ctx, "CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)")
// or
_, err := conn.Exec(ctx, "CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)")

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

See a full example

Bun

Run:

bash
go get github.com/pgvector/pgvector-go

Import the package

go
import "github.com/pgvector/pgvector-go"

Enable the extension

go
_, err := db.Exec("CREATE EXTENSION IF NOT EXISTS vector")

Add a vector column

go
type Item struct {
    Embedding pgvector.Vector `bun:"type:vector(3)"`
}

Insert a vector

go
item := Item{
    Embedding: pgvector.NewVector([]float32{1, 2, 3}),
}
_, err := db.NewInsert().Model(&item).Exec(ctx)

Get the nearest neighbors to a vector

go
var items []Item
err := db.NewSelect().
    Model(&items).
    OrderExpr("embedding  ?", pgvector.NewVector([]float32{1, 2, 3})).
    Limit(5).
    Scan(ctx)

Add an approximate index

go
var _ bun.AfterCreateTableHook = (*Item)(nil)

func (*Item) AfterCreateTable(ctx context.Context, query *bun.CreateTableQuery) error {
    _, err := query.DB().NewCreateIndex().
        Model((*Item)(nil)).
        Index("items_embedding_idx").
        ColumnExpr("embedding vector_l2_ops").
        Using("hnsw").
        Exec(ctx)
    return err
}

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

See a full example

Ent

Run:

bash
go get github.com/pgvector/pgvector-go
go get github.com/pgvector/pgvector-go/ent

Import the package

go
import (
    "github.com/pgvector/pgvector-go"
    entvec "github.com/pgvector/pgvector-go/ent"
)

Enable the extension (requires the sql/execquery feature)

go
_, err := client.ExecContext(ctx, "CREATE EXTENSION IF NOT EXISTS vector")

Add a vector column

go
func (Item) Fields() []ent.Field {
    return []ent.Field{
        field.Other("embedding", pgvector.Vector{}).
            SchemaType(map[string]string{
                dialect.Postgres: "vector(3)",
            }),
    }
}

Insert a vector

go
_, err := client.Item.
    Create().
    SetEmbedding(pgvector.NewVector([]float32{1, 2, 3})).
    Save(ctx)

Get the nearest neighbors to a vector

go
items, err := client.Item.
    Query().
    Order(func(s *sql.Selector) {
        s.OrderExpr(entvec.L2Distance("embedding", pgvector.NewVector([]float32{1, 2, 3})))
    }).
    Limit(5).
    All(ctx)

Also supports MaxInnerProduct, CosineDistance, L1Distance, HammingDistance, and JaccardDistance

Add an approximate index

go
func (Item) Indexes() []ent.Index {
    return []ent.Index{
        index.Fields("embedding").
            Annotations(
                entsql.IndexType("hnsw"),
                entsql.OpClass("vector_l2_ops"),
            ),
    }
}

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

See a full example

GORM

Run:

bash
go get github.com/pgvector/pgvector-go

Import the package

go
import "github.com/pgvector/pgvector-go"

Enable the extension

go
db.Exec("CREATE EXTENSION IF NOT EXISTS vector")

Add a vector column

go
type Item struct {
    Embedding pgvector.Vector `gorm:"type:vector(3)"`
}

Insert a vector

go
item := Item{
    Embedding: pgvector.NewVector([]float32{1, 2, 3}),
}
result := db.Create(&item)

Get the nearest neighbors to a vector

go
var items []Item
db.Clauses(clause.OrderBy{
    Expression: clause.Expr{SQL: "embedding  ?", Vars: []interface{}{pgvector.NewVector([]float32{1, 1, 1})}},
}).Limit(5).Find(&items)

Add an approximate index

go
db.Exec("CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)")
// or
db.Exec("CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)")

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

See a full example

sqlx

Run:

bash
go get github.com/pgvector/pgvector-go

Import the package

go
import "github.com/pgvector/pgvector-go"

Enable the extension

go
db.MustExec("CREATE EXTENSION IF NOT EXISTS vector")

Add a vector column

go
type Item struct {
    Embedding pgvector.Vector
}

Insert a vector

go
item := Item{
    Embedding: pgvector.NewVector([]float32{1, 2, 3}),
}
_, err := db.NamedExec(`INSERT INTO items (embedding) VALUES (:embedding)`, item)

Get the nearest neighbors to a vector

go
var items []Item
db.Select(&items, "SELECT * FROM items ORDER BY embedding  $1 LIMIT 5", pgvector.NewVector([]float32{1, 1, 1}))

Add an approximate index

go
db.MustExec("CREATE INDEX ON items USING hnsw (embedding vector_l2_ops)")
// or
db.MustExec("CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)")

Use vector_ip_ops for inner product and vector_cosine_ops for cosine distance

See a full example

Reference

Vectors

Create a vector from a slice

go
vec := pgvector.NewVector([]float32{1, 2, 3})

Get a slice

go
slice := vec.Slice()

Half Vectors

Create a half vector from a slice

go
vec := pgvector.NewHalfVector([]float32{1, 2, 3})

Get a slice

go
slice := vec.Slice()

Sparse Vectors

Create a sparse vector from a slice

go
vec := pgvector.NewSparseVector([]float32{1, 0, 2, 0, 3, 0})

Or a map of non-zero elements

go
elements := map[int32]float32{0: 1, 2: 2, 4: 3}
vec := pgvector.NewSparseVectorFromMap(elements, 6)

Note: Indices start at 0

Get the number of dimensions

go
dim := vec.Dimensions()

Get the indices of non-zero elements

go
indices := vec.Indices()

Get the values of non-zero elements

go
values := vec.Values()

Get a slice

go
slice := vec.Slice()

Upgrading

0.4.0

For pgx, run:

bash
go get github.com/pgvector/pgvector-go
go get github.com/pgvector/pgvector-go/pgx

For Ent, run:

bash
go get github.com/pgvector/pgvector-go
go get github.com/pgvector/pgvector-go/ent

For other database libraries, run:

bash
go get github.com/pgvector/pgvector-go

History

View the changelog

Contributing

Everyone is encouraged to help improve this project. Here are a few ways you can help:

  • Report bugs
  • Fix bugs and submit pull requests
  • Write, clarify, or fix documentation
  • Suggest or add new features

To get started with development:

bash
git clone https://github.com/pgvector/pgvector-go.git
cd pgvector-go
go mod tidy
createdb pgvector_go_test
cd test
go mod tidy
go generate ./ent
go mod tidy
go test -v

To run an example:

bash
createdb pgvector_example
cd examples
go mod tidy
go run ./loading

Issues· 0 open

View all issuesOpen on GitHub

No open issues yet, or sync has not completed.

> Tags

Go

No comments yet. Be the first to share.

> Details

PublishedAug 1, 2026
UpdatedSep 18, 2026
Category编程语言
PricingOpen source

> Related tools

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言