Qdrant Embedding Store

Qdrant is an open-source vector database for embedding-based search. The quarkus-langchain4j-qdrant extension allows you to use Qdrant as an embedding store for Retrieval-Augmented Generation (RAG) with Quarkus LangChain4j.

Dependency

To enable Qdrant integration, add the following dependency to your Quarkus project:

<dependency>
  <groupId>io.quarkiverse.langchain4j</groupId>
  <artifactId>quarkus-langchain4j-qdrant</artifactId>
  <version>1.12.0</version>
</dependency>

Even better, if you use the Quarkus platform BOM (default for projects generated), add the Quarkus Langchain4J BOM and all dependency versions will align:

    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>${quarkus.platform.group-id}</groupId>
                <artifactId>${quarkus.platform.artifact-id}</artifactId>
                <version>${quarkus.platform.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
            <dependency>
                <groupId>${quarkus.platform.group-id}</groupId>
                <artifactId>quarkus-langchain4j-bom</artifactId> (1)
                <version>${quarkus.platform.version}</version> (2)
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>

    <dependencies>
      <dependency>
        <groupId>io.quarkiverse.langchain4j</groupId>
        <artifactId>quarkus-langchain4j-qdrant</artifactId>
        (3)
      </dependency>
    </dependencies>
1 In your dependencyManagement section, add the quarkus-langchain4j-bom
2 Inherit the version from your platform version
3 Voilà, no need for version alignment anymore

Dev Services Support

Dev Services for Qdrant are provided by the quarkus-qdrant extension, which is pulled in transitively. In dev and test modes, a containerized Qdrant instance is automatically started.

You can pre-create collections at startup via dev services configuration:

# Pre-create a collection (name is the map key)
quarkus.qdrant.devservices.collections.my-collection.vector-size=384
quarkus.qdrant.devservices.collections.my-collection.distance=Cosine
The vector size must match the output dimension of your embedding model (e.g., 384 for all-MiniLM-L6-v2, 1536 for OpenAI text-embedding-ada-002).

Migrating from 1.12.x and earlier

Prior to 1.13.x, this extension used the langchain4j gRPC client and exposed connection settings under the quarkus.langchain4j.qdrant.* namespace. These properties no longer exist. Connection to Qdrant is now handled by the quarkus-qdrant extension using its own namespace.

Old property Replacement

quarkus.langchain4j.qdrant.host

quarkus.qdrant.host

quarkus.langchain4j.qdrant.port

quarkus.qdrant.port

quarkus.langchain4j.qdrant.api-key

quarkus.qdrant.api-key

quarkus.langchain4j.qdrant.use-tls

quarkus.qdrant.use-tls

quarkus.langchain4j.qdrant.collection.name

quarkus.langchain4j.qdrant.collection-name

quarkus.langchain4j.qdrant.devservices.enabled

quarkus.qdrant.devservices.enabled

quarkus.langchain4j.qdrant.devservices.qdrant-image-name

quarkus.qdrant.devservices.image-name

quarkus.langchain4j.qdrant.devservices.port

quarkus.qdrant.devservices.port

quarkus.langchain4j.qdrant.devservices.shared

quarkus.qdrant.devservices.shared

quarkus.langchain4j.qdrant.devservices.service-name

quarkus.qdrant.devservices.service-name

quarkus.langchain4j.qdrant.devservices.collection.vector-params.size

quarkus.qdrant.devservices.collections.<name>.vector-size

quarkus.langchain4j.qdrant.devservices.collection.vector-params.distance

quarkus.qdrant.devservices.collections.<name>.distance
The default port changed from 6334 (gRPC) to 6333 (REST). Update or remove any explicit port configuration.
Per-store connection settings (host, port, api-key) are now handled by the quarkus-qdrant extension via the client-name property (see Per-store Qdrant client).

Named Stores

You can configure multiple named Qdrant stores, each using a different collection. This is useful when your application needs to manage embeddings for different domains or tenants in separate collections.

To configure a named store:

quarkus.langchain4j.qdrant.products.collection-name=product_embeddings

To inject a named store, use the @EmbeddingStoreName qualifier:

@Inject
@EmbeddingStoreName("products")
EmbeddingStore<TextSegment> productsStore;

The default store and named stores can coexist. If you only need named stores, disable the default store:

quarkus.langchain4j.qdrant.default-store-enabled=false

Per-store Qdrant client

Individual stores can point to different Qdrant instances via the client-name property, which references a named client from the quarkus-qdrant extension:

# Default Qdrant client
quarkus.qdrant.host=qdrant-primary
quarkus.qdrant.port=6333

# A second Qdrant client named "secondary"
quarkus.qdrant."secondary".host=qdrant-secondary
quarkus.qdrant."secondary".port=6333

# Default store uses the default client (no client-name needed)
quarkus.langchain4j.qdrant.collection-name=documents

# Named store uses the secondary client
quarkus.langchain4j.qdrant.products.collection-name=product_embeddings
quarkus.langchain4j.qdrant.products.client-name=secondary
Only distance=Cosine collections produce correct relevance scores. Other distance metrics are not supported.

Configuration

The Qdrant extension can be configured using the following options:

Configuration property fixed at build time - All other configuration properties are overridable at runtime

Configuration property

Type

Default

quarkus.langchain4j.qdrant.default-store-enabled

Whether the default (unnamed) Qdrant embedding store should be enabled. Set to false when you only want to use named stores.

Environment variable: QUARKUS_LANGCHAIN4J_QDRANT_DEFAULT_STORE_ENABLED

boolean

true

quarkus.langchain4j.qdrant.client-name

The name of the Qdrant client to use. These clients are configured by means of the quarkus-qdrant extension. If not set, the default Qdrant client will be used.

Environment variable: QUARKUS_LANGCHAIN4J_QDRANT_CLIENT_NAME

string

quarkus.langchain4j.qdrant.collection-name

The name of the Qdrant collection to use.

Environment variable: QUARKUS_LANGCHAIN4J_QDRANT_COLLECTION_NAME

string

quarkus.langchain4j.qdrant.payload-text-key

The field name of the text segment in the payload.

Environment variable: QUARKUS_LANGCHAIN4J_QDRANT_PAYLOAD_TEXT_KEY

string

text_segment

Named store configurations

Type

Default

quarkus.langchain4j.qdrant."store-name".client-name

The name of the Qdrant client to use. These clients are configured by means of the quarkus-qdrant extension. If not set, the default Qdrant client will be used.

Environment variable: QUARKUS_LANGCHAIN4J_QDRANT__STORE_NAME__CLIENT_NAME

string

quarkus.langchain4j.qdrant."store-name".collection-name

The name of the Qdrant collection to use.

Environment variable: QUARKUS_LANGCHAIN4J_QDRANT__STORE_NAME__COLLECTION_NAME

string

quarkus.langchain4j.qdrant."store-name".payload-text-key

The field name of the text segment in the payload.

Environment variable: QUARKUS_LANGCHAIN4J_QDRANT__STORE_NAME__PAYLOAD_TEXT_KEY

string

text_segment

Summary

To use Qdrant with Quarkus LangChain4j:

  1. Add the quarkus-langchain4j-qdrant extension

  2. Use Dev Services (automatic) or configure an external Qdrant instance via quarkus.qdrant.*

  3. Set the collection name via quarkus.langchain4j.qdrant.collection-name

  4. Inject EmbeddingStore<TextSegment> and start ingesting and retrieving documents