pgvector support for Go
Supports pgx, pg, Bun, Ent, GORM, and sqlx
pgvector-go 0.4.0 was recently released - see how to upgrade
Follow the instructions for your database library:
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
Run:
go get github.com/pgvector/pgvector-go go get github.com/pgvector/pgvector-go/pgx
Import the packages
import ( "github.com/pgvector/pgvector-go" pgxvec "github.com/pgvector/pgvector-go/pgx" )
Enable the extension
_, err := conn.Exec(ctx, "CREATE EXTENSION IF NOT EXISTS vector")
Register the types with the connection
err := pgxvec.RegisterTypes(ctx, conn)
or the pool
config.AfterConnect = func(ctx context.Context, conn *pgx.Conn) error { return pgxvec.RegisterTypes(ctx, conn) }
Create a table
_, err := conn.Exec(ctx, "CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))")
Insert a vector
_, err := conn.Exec(ctx, "INSERT INTO items (embedding) VALUES (1ドル)", pgvector.NewVector([]float32{1, 2, 3}))
Get the nearest neighbors to a vector
rows, err := conn.Query(ctx, "SELECT id FROM items ORDER BY embedding <-> 1ドル LIMIT 5", pgvector.NewVector([]float32{1, 2, 3}))
Add an approximate index
_, 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
Run:
go get github.com/pgvector/pgvector-go
Import the package
import "github.com/pgvector/pgvector-go"
Enable the extension
_, err := db.Exec("CREATE EXTENSION IF NOT EXISTS vector")
Add a vector column
type Item struct { Embedding pgvector.Vector `pg:"type:vector(3)"` }
Insert a vector
item := Item{ Embedding: pgvector.NewVector([]float32{1, 2, 3}), } _, err := db.Model(&item).Insert()
Get the nearest neighbors to a vector
var items []Item err := db.Model(&items). OrderExpr("embedding <-> ?", pgvector.NewVector([]float32{1, 2, 3})). Limit(5). Select()
Add an approximate index
_, 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
Run:
go get github.com/pgvector/pgvector-go
Import the package
import "github.com/pgvector/pgvector-go"
Enable the extension
_, err := db.Exec("CREATE EXTENSION IF NOT EXISTS vector")
Add a vector column
type Item struct { Embedding pgvector.Vector `bun:"type:vector(3)"` }
Insert a vector
item := Item{ Embedding: pgvector.NewVector([]float32{1, 2, 3}), } _, err := db.NewInsert().Model(&item).Exec(ctx)
Get the nearest neighbors to a vector
var items []Item err := db.NewSelect(). Model(&items). OrderExpr("embedding <-> ?", pgvector.NewVector([]float32{1, 2, 3})). Limit(5). Scan(ctx)
Add an approximate index
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
Run:
go get github.com/pgvector/pgvector-go go get github.com/pgvector/pgvector-go/ent
Import the package
import ( "github.com/pgvector/pgvector-go" entvec "github.com/pgvector/pgvector-go/ent" )
Enable the extension (requires the sql/execquery feature)
_, err := client.ExecContext(ctx, "CREATE EXTENSION IF NOT EXISTS vector")
Add a vector column
func (Item) Fields() []ent.Field { return []ent.Field{ field.Other("embedding", pgvector.Vector{}). SchemaType(map[string]string{ dialect.Postgres: "vector(3)", }), } }
Insert a vector
_, err := client.Item. Create(). SetEmbedding(pgvector.NewVector([]float32{1, 2, 3})). Save(ctx)
Get the nearest neighbors to a vector
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
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
Run:
go get github.com/pgvector/pgvector-go
Import the package
import "github.com/pgvector/pgvector-go"
Enable the extension
db.Exec("CREATE EXTENSION IF NOT EXISTS vector")
Add a vector column
type Item struct { Embedding pgvector.Vector `gorm:"type:vector(3)"` }
Insert a vector
item := Item{ Embedding: pgvector.NewVector([]float32{1, 2, 3}), } result := db.Create(&item)
Get the nearest neighbors to a vector
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
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
Run:
go get github.com/pgvector/pgvector-go
Import the package
import "github.com/pgvector/pgvector-go"
Enable the extension
db.MustExec("CREATE EXTENSION IF NOT EXISTS vector")
Add a vector column
type Item struct { Embedding pgvector.Vector }
Insert a vector
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
var items []Item db.Select(&items, "SELECT * FROM items ORDER BY embedding <-> 1ドル LIMIT 5", pgvector.NewVector([]float32{1, 1, 1}))
Add an approximate index
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
Create a vector from a slice
vec := pgvector.NewVector([]float32{1, 2, 3})
Get a slice
slice := vec.Slice()
Create a half vector from a slice
vec := pgvector.NewHalfVector([]float32{1, 2, 3})
Get a slice
slice := vec.Slice()
Create a sparse vector from a slice
vec := pgvector.NewSparseVector([]float32{1, 0, 2, 0, 3, 0})
Or a map of non-zero elements
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
dim := vec.Dimensions()
Get the indices of non-zero elements
indices := vec.Indices()
Get the values of non-zero elements
values := vec.Values()
Get a slice
slice := vec.Slice()
For pgx, run:
go get github.com/pgvector/pgvector-go go get github.com/pgvector/pgvector-go/pgx
For Ent, run:
go get github.com/pgvector/pgvector-go go get github.com/pgvector/pgvector-go/ent
For other database libraries, run:
go get github.com/pgvector/pgvector-go
View the changelog
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:
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:
createdb pgvector_example
cd examples
go mod tidy
go run ./loading