Database for querying billions of vectors and embeddings in sublinear time on commodity machines.
Read the accompanying blog post for details and an accessible deep dive and in-depth technical report.
fn main() {
let db = CoreNN::create("/path/to/db", Cfg {
// Specify the dimensionality of your vectors.
dim: 3,
// All other config options are optional.
...Default::default()
});
let key = "my_entry".to_string();
let vec: Vec<f32> = vec![0.3, 0.6, 0.9];
db.insert(&key, &vec);
// For per-vector quantized int8: `db.insert_qi8(&key, &qvec_i8, scale, zero_point)`.
// Later...
let db = CoreNN::open("/path/to/db");
let query: Vec<f32> = vec![1.0, 1.3, 1.7];
// Returns Vec of (key, distance) pairs.
let k100 = db.query(&query, 100);
assert_eq!(k100[0].0.as_str(), "my_entry");
}from corenn_py import CoreNN
db = CoreNN.create("/path/to/db", {
# Specify the dimensionality of your vectors.
"dim": 3,
# All other config options are optional.
})
keys = [
"my_entry_1",
"my_entry_2",
]
vectors = np.array([
[0.3, 0.6, 0.9],
[0.4, 1.1, 0.0],
])
# Or insert_bf16, insert_f16
# Or insert_i8 (per-vector quantized int8 + scale/zero_point arrays)
db.insert_f32(keys, vectors)
# Later...
db = CoreNN.open("/path/to/db")
queries = np.array([
[1.0, 1.3, 1.7],
[7.3, 2.5, 0.0],
])
# Returns a list of (key, distance) tuples
# for each query vector
# (so returns a list of lists).
k100 = db.query_f32(queries, 100)import { CoreNN } from "@corenn/node";
const db = CoreNN.create("/path/to/db", {
// Specify the dimensionality of your vectors.
dim: 3,
// All other config options are optional.
});
db.insert([
{
key: "my_entry_1",
vector: new Float32Array([0.5, 4.1, 2.2]),
// Or per-vector quantized int8:
// vector: { data: new Int8Array([..]), scale: 0.01, zeroPoint: 0 },
},
{
key: "my_entry_2",
vector: new Float32Array([3.1, 7.7, 6.4]),
},
]);
// Later...
const db = CoreNN.open("/path/to/db");
// Array of { key, distance } objects.
const results = db.query(
new Float32Array([0.0, 1.1, 2.2]),
100,
);