The Qdrant - High-Performance Vector Search at Scale - client for Rust.
Documentation:
cargo add qdrant-client
Package is available in crates.io
A list of example snippets can be found here
More examples can be found in the examples folder
The client uses gRPC via the Tonic library.
To change anything in the protocol buffer definitions, you need the protoc
Protocol Buffers compiler, along with Protocol Buffers resource files.
Refer to the Tonic installation guide for more details.
Run Qdrant with enabled gRPC interface:
# With env variable
docker run -p 6333:6333 -p 6334:6334 \
-e QDRANT__SERVICE__GRPC_PORT="6334" \
qdrant/qdrant
Or by updating the configuration file:
service:
grpc_port: 6334
More info about gRPC in documentation.
Add necessary dependencies:
cargo add qdrant-client anyhow tonic tokio serde-json --features tokio/rt-multi-thread
Add search example from examples/search.rs
to your src/main.rs
:
use qdrant_client::qdrant::{
Condition, CreateCollectionBuilder, Distance, Filter, PointStruct, ScalarQuantizationBuilder,
SearchParamsBuilder, SearchPointsBuilder, UpsertPointsBuilder, VectorParamsBuilder,
};
use qdrant_client::{Payload, Qdrant, QdrantError};
#[tokio::main]
async fn main() -> Result<(), QdrantError> {
// Example of top level client
// You may also use tonic-generated client from `src/qdrant.rs`
let client = Qdrant::from_url("http://localhost:6334").build()?;
let collections_list = client.list_collections().await?;
dbg!(collections_list);
// collections_list = {
// "collections": [
// {
// "name": "test"
// }
// ]
// }
let collection_name = "test";
client.delete_collection(collection_name).await?;
client
.create_collection(
CreateCollectionBuilder::new(collection_name)
.vectors_config(VectorParamsBuilder::new(10, Distance::Cosine))
.quantization_config(ScalarQuantizationBuilder::default()),
)
.await?;
let collection_info = client.collection_info(collection_name).await?;
dbg!(collection_info);
let payload: Payload = serde_json::json!(
{
"foo": "Bar",
"bar": 12,
"baz": {
"qux": "quux"
}
}
)
.try_into()
.unwrap();
let points = vec![PointStruct::new(0, vec![12.; 10], payload)];
client
.upsert_points(UpsertPointsBuilder::new(collection_name, points))
.await?;
let search_result = client
.search_points(
SearchPointsBuilder::new(collection_name, [11.; 10], 10)
.filter(Filter::all([Condition::matches("bar", 12)]))
.with_payload(true)
.params(SearchParamsBuilder::default().exact(true)),
)
.await?;
dbg!(&search_result);
// search_result = [
// {
// "id": 0,
// "version": 0,
// "score": 1.0000001,
// "payload": {
// "bar": 12,
// "baz": {
// "qux": "quux"
// },
// "foo": "Bar"
// }
// }
// ]
let found_point = search_result.result.into_iter().next().unwrap();
let mut payload = found_point.payload;
let baz_payload = payload.remove("baz").unwrap().into_json();
println!("baz: {}", baz_payload);
// baz: {"qux":"quux"}
Ok(())
}
Or run the example from this project directly:
cargo run --example search
Qdrant Cloud is a managed service for Qdrant.
The client needs to be configured properly to access the service.
use qdrant_client::Qdrant;
let client = Qdrant::from_url("http://xxxxxxxxxx.eu-central.aws.cloud.qdrant.io:6334")
// Use an environment variable for the API KEY for example
.api_key(std::env::var("QDRANT_API_KEY"))
.build()?;