Rust client for Qdrant vector search engine.
cargo add qdrant-clientPackage is available in crates.io
The client uses gRPC via the Tonic library.
In order to build tonic >= 0.8.0, 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/qdrantOr by updating the configuration file:
service:
grpc_port: 6334More info about gRPC in documentation.
Add necessary dependencies:
cargo add qdrant-client anyhow tonic tokio --features tokio/rt-multi-threadAdd search example from examples/search.rs to your src/main.rs:
use anyhow::Result;
use qdrant_client::prelude::*;
use qdrant_client::qdrant::vectors_config::Config;
use qdrant_client::qdrant::{CreateCollection, SearchPoints, VectorParams, VectorsConfig};
use std::collections::HashMap;
#[tokio::main]
async fn main() -> Result<()> {
// Example of top level client
// You may also use tonic-generated client from `src/qdrant.rs`
let config = QdrantClientConfig::from_url("http://localhost:6334");
let client = QdrantClient::new(Some(config)).await?;
let collections_list = client.list_collections().await?;
dbg!(collections_list);
// collections_list = ListCollectionsResponse {
// collections: [
// CollectionDescription {
// name: "test",
// },
// ],
// time: 1.78e-6,
// }
let collection_name = "test";
client.delete_collection(collection_name).await?;
client
.create_collection(&CreateCollection {
collection_name: collection_name.into(),
vectors_config: Some(VectorsConfig {
config: Some(Config::Params(VectorParams {
size: 10,
distance: Distance::Cosine.into(),
})),
}),
..Default::default()
})
.await?;
let collection_info = client.collection_info(collection_name).await?;
dbg!(collection_info);
let payload: Payload = vec![("foo", "Bar".into()), ("bar", 12.into())]
.into_iter()
.collect::<HashMap<_, Value>>()
.into();
let points = vec![PointStruct::new(0, vec![12.; 10], payload)];
client
.upsert_points_blocking(collection_name, points, None)
.await?;
let search_result = client
.search_points(&SearchPoints {
collection_name: collection_name.into(),
vector: vec![11.; 10],
filter: None,
limit: 10,
with_vectors: None,
with_payload: None,
params: None,
score_threshold: None,
offset: None,
..Default::default()
})
.await?;
dbg!(search_result);
// search_result = SearchResponse {
// result: [
// ScoredPoint {
// id: Some(
// PointId {
// point_id_options: Some(
// Num(
// 0,
// ),
// ),
// },
// ),
// payload: {},
// score: 1.0000001,
// version: 0,
// vectors: None,
// },
// ],
// time: 5.312e-5,
// }
Ok(())
}Or run the example from this project directly:
cargo run --example searchQdrant Cloud is a managed service for Qdrant.
The client needs to be configured properly to access the service.
- make sure to use the correct port (6334)
- make sure to pass your API KEY
async fn make_client() -> Result<QdrantClient> {
let config = QdrantClientConfig::from_url("http://xxxxxxxxxx.eu-central.aws.cloud.qdrant.io:6334");
// using an env variable for the API KEY for example
let api_key = std::env::var("QDRANT_API_KEY").ok();
if let Some(api_key) = api_key {
config.set_api_key(&api_key);
}
let client = QdrantClient::new(Some(config)).await?;
Ok(client)
}