.NET client for Qdrant vector database
$ dotnet add package Qdrant.Client.NET SDK for Qdrant vector database.
dotnet add package Qdrant.Client
A client can be instantiated with
var client = new QdrantClient("localhost");
which creates a client that will connect to Qdrant on http://localhost:6334.
Internally, the high level client uses a low level gRPC client to interact with Qdrant. Additional constructor overloads provide more control over how the gRPC client is configured. The following example configures a client to use TLS, validating the certificate using its thumbprint, and also configures API key authentication:
var channel = QdrantChannel.ForAddress("https://localhost:6334", new ClientConfiguration
{
ApiKey = "<api key>",
CertificateThumbprint = "<certificate thumbprint>"
});
var grpcClient = new QdrantGrpcClient(channel);
var client = new QdrantClient(grpcClient);
[!IMPORTANT] IMPORTANT NOTICE for .NET Framework
.NET Framework has limited supported for gRPC over HTTP/2, but it can be enabled by
- Configuring qdrant to use TLS, and you must use HTTPS, so you will need to set up server certificate validation
System.Net.Http.WinHttpHandler 6.0.1 or later, and configuring
WinHttpHandler as the inner handler for GrpcChannelOptionsThe following example configures a client for .NET Framework to use TLS, validating the certificate using its thumbprint, and also configures API key authentication:
var channel = GrpcChannel.ForAddress($"https://localhost:6334", new GrpcChannelOptions
{
HttpHandler = new WinHttpHandler
{
ServerCertificateValidationCallback =
CertificateValidation.Thumbprint("<certificate thumbprint>")
}
});
var callInvoker = channel.Intercept(metadata =>
{
metadata.Add("api-key", "<api key>");
return metadata;
});
var grpcClient = new QdrantGrpcClient(callInvoker);
var client = new QdrantClient(grpcClient);Once a client has been created, create a new collection
await client.CreateCollectionAsync("my_collection",
new VectorParams { Size = 100, Distance = Distance.Cosine });Insert vectors into a collection
// generate some vectors
var random = new Random();
var points = Enumerable.Range(1, 100).Select(i => new PointStruct
{
Id = (ulong)i,
Vectors = Enumerable.Range(1, 100).Select(_ => (float)random.NextDouble()).ToArray(),
Payload =
{
["color"] = "red",
["rand_number"] = i % 10
}
}).ToList();
var updateResult = await client.UpsertAsync("my_collection", points);Search for similar vectors
var queryVector = Enumerable.Range(1, 100).Select(_ => (float)random.NextDouble()).ToArray();
// return the 5 closest points
var points = await client.SearchAsync(
"my_collection",
queryVector,
limit: 5);Search for similar vectors with filtering condition
// static import Conditions to easily build filtering
using static Qdrant.Client.Grpc.Conditions;
// return the 5 closest points where rand_number >= 3
var points = await _client.SearchAsync(
"my_collection",
queryVector,
filter: Range("rand_number", new Range { Gte = 3 }),
limit: 5);