QdrantStore

Qdrant vector database store implementation.

This class provides an interface for storing and searching vectors using Qdrant, a production-ready vector database. It implements the VDBStoreBase interface to provide a unified API for vector storage operations.

In Qdrant, we use the payload field to store the metadata, including the document ID, chunk ID, and original content.

This implementation uses the Qdrant Java SDK (io.qdrant:client). To use this class, add the following dependency:

`<dependency>
<groupId>io.qdrant</groupId>
<artifactId>client</artifactId>
<version>1.15.0</version>
<scope>provided</scope>
</dependency>
`

Example usage:

`// Using builder with TLS and compatibility options (recommended)
try (QdrantStore store = QdrantStore.builder()
.location("http://localhost:6333")
.collectionName("my_collection")
.dimensions(1024)
.apiKey("my-api-key")
.useTransportLayerSecurity(true)
.checkCompatibility(false)
.build()) {
store.add(document).block();
List<Document> results = store.search(queryEmbedding, 5).block();
// Store is automatically closed here
}

// Using static factory method (simpler, uses defaults)
try (QdrantStore store = QdrantStore.create("http://localhost:6333", "my_collection", 1024)) {
store.add(document).block();
List<Document> results = store.search(queryEmbedding, 5).block();
}
`

Note: The location parameter can be:

• HTTP URL: "http://localhost:6333" - will use gRPC on port 6334

• gRPC URL: "localhost:6334" - direct gRPC connection

• Local path: "file:///path/to/qdrant" - local Qdrant instance

• Memory mode: ":memory:" - in-memory Qdrant (requires local Qdrant)