pgvector support for Rust
Supports Rust-Postgres, SQLx, and Diesel
Follow the instructions for your database library:
Or check out some examples:
- Embeddings with OpenAI
- Recommendations with Disco
Add this line to your application’s Cargo.toml
under [dependencies]
:
pgvector = { version = "0.2", features = ["postgres"] }
Enable the extension
client.execute("CREATE EXTENSION IF NOT EXISTS vector", &[])?;
Create a table
client.execute("CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))", &[])?;
Create a vector from a Vec<f32>
let embedding = pgvector::Vector::from(vec![1.0, 2.0, 3.0]);
Insert a vector
client.execute("INSERT INTO items (embedding) VALUES ($1)", &[&embedding])?;
Get the nearest neighbor
let row = client.query_one("SELECT * FROM items ORDER BY embedding <-> $1 LIMIT 1", &[&embedding])?;
Retrieve a vector
let row = client.query_one("SELECT embedding FROM items LIMIT 1", &[])?;
let embedding: pgvector::Vector = row.get(0);
Use Option
if the value could be NULL
let embedding: Option<pgvector::Vector> = row.get(0);
Add this line to your application’s Cargo.toml
under [dependencies]
:
pgvector = { version = "0.2", features = ["sqlx"] }
Enable the extension
sqlx::query("CREATE EXTENSION IF NOT EXISTS vector").execute(&pool).await?;
Create a table
sqlx::query("CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3))").execute(&pool).await?;
Create a vector from a Vec<f32>
let embedding = pgvector::Vector::from(vec![1.0, 2.0, 3.0]);
Insert a vector
sqlx::query("INSERT INTO items (embedding) VALUES ($1)").bind(embedding).execute(&pool).await?;
Get the nearest neighbors
let rows = sqlx::query("SELECT * FROM items ORDER BY embedding <-> $1 LIMIT 1")
.bind(embedding).fetch_all(&pool).await?;
Retrieve a vector
let row = sqlx::query("SELECT embedding FROM items LIMIT 1").fetch_one(&pool).await?;
let embedding: pgvector::Vector = row.try_get("embedding")?;
Add this line to your application’s Cargo.toml
under [dependencies]
:
pgvector = { version = "0.2", features = ["diesel"] }
And add this line to your application’s diesel.toml
under [print_schema]
:
import_types = ["diesel::sql_types::*", "pgvector::sql_types::*"]
Create a migration
diesel migration generate create_vector_extension
with up.sql
:
CREATE EXTENSION vector
and down.sql
:
DROP EXTENSION vector
Run the migration
diesel migration run
You can now use the vector
type in future migrations
CREATE TABLE items (
embedding VECTOR(3)
)
For models, use:
pub struct Item {
pub embedding: Option<pgvector::Vector>
}
Create a vector from a Vec<f32>
let embedding = pgvector::Vector::from(vec![1.0, 2.0, 3.0]);
Insert a vector
let new_item = Item {
embedding: Some(embedding)
};
diesel::insert_into(items::table)
.values(&new_item)
.get_result::<Item>(&mut conn)?;
Get the nearest neighbors
use pgvector::VectorExpressionMethods;
let neighbors = items::table
.order(items::embedding.l2_distance(embedding))
.limit(5)
.load::<Item>(&mut conn)?;
Also supports max_inner_product
and cosine_distance
Get the distances
let distances = items::table
.select(items::embedding.l2_distance(embedding))
.load::<Option<f64>>(&mut conn)?;
Add an approximate index in a migration
CREATE INDEX my_index ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)
-- or
CREATE INDEX my_index ON items USING hnsw (embedding vector_l2_ops)
Use vector_ip_ops
for inner product and vector_cosine_ops
for cosine distance
Convert a vector to a Vec<f32>
let f32_vec: Vec<f32> = vec.into();
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-rust.git
cd pgvector-rust
createdb pgvector_rust_test
cargo test --all-features