CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/maven-dev-langchain4j--langchain4j-qdrant

LangChain4j Qdrant integration providing a vector store embedding implementation for Qdrant database with metadata filtering support

—

Pending

Quality

Pending

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Overview
Eval results
Files

index.mddocs/

LangChain4j Qdrant Integration

A vector store embedding implementation for Qdrant database that integrates with the LangChain4j framework.

Quick Reference

Package: dev.langchain4j:langchain4j-qdrant:1.11.0 Java: 17+ Main Class: QdrantEmbeddingStore Interface: EmbeddingStore<TextSegment>

Installation

Maven:

<dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-qdrant</artifactId>
    <version>1.11.0</version>
</dependency>

Gradle:

implementation 'dev.langchain4j:langchain4j-qdrant:1.11.0'

Core Import

import dev.langchain4j.store.embedding.qdrant.QdrantEmbeddingStore;

Minimal Example

import dev.langchain4j.store.embedding.qdrant.QdrantEmbeddingStore;
import dev.langchain4j.data.embedding.Embedding;
import dev.langchain4j.data.segment.TextSegment;
import dev.langchain4j.store.embedding.EmbeddingSearchRequest;
import dev.langchain4j.store.embedding.EmbeddingSearchResult;

// Create store
QdrantEmbeddingStore store = QdrantEmbeddingStore.builder()
    .collectionName("my-collection")
    .build();

// Add embedding
Embedding embedding = Embedding.from(new float[]{0.1f, 0.2f, 0.3f});
TextSegment segment = TextSegment.from("Sample text");
String id = store.add(embedding, segment);

// Search
Embedding query = Embedding.from(new float[]{0.11f, 0.21f, 0.31f});
EmbeddingSearchRequest request = EmbeddingSearchRequest.builder()
    .queryEmbedding(query)
    .maxResults(5)
    .minScore(0.7)
    .build();
EmbeddingSearchResult<TextSegment> results = store.search(request);

// Clean up
store.close();

Key Capabilities

  • Add embeddings: With or without IDs, text segments, and metadata
  • Search embeddings: Cosine similarity search with optional metadata filtering
  • Remove embeddings: By ID, multiple IDs, filter, or clear all
  • Metadata support: String, Integer, Long, Double, Float, UUID
  • Filter operations: Equality, comparison, range, logical (AND/OR/NOT)

API Quick Reference

Store Creation

// Builder pattern (recommended)
QdrantEmbeddingStore.builder()
    .collectionName(String)    // REQUIRED
    .host(String)              // Default: "localhost"
    .port(int)                 // Default: 6334
    .useTls(boolean)           // Default: false
    .apiKey(String)            // Optional
    .payloadTextKey(String)    // Default: "text_segment"
    .client(QdrantClient)      // Optional custom client
    .build()

Add Operations

String add(Embedding embedding)
void add(String id, Embedding embedding)
String add(Embedding embedding, TextSegment textSegment)
List<String> addAll(List<Embedding> embeddings)
void addAll(List<String> ids, List<Embedding> embeddings, List<TextSegment> textSegments)

Search Operations

EmbeddingSearchResult<TextSegment> search(EmbeddingSearchRequest request)

Remove Operations

void remove(String id)
void removeAll(Collection<String> ids)
void removeAll(Filter filter)
void removeAll()

Lifecycle

void clearStore()
void close()

Documentation Structure

For detailed information, see:

  • API Reference - Complete API signatures and constructors
  • Examples - Common usage patterns and code examples
  • Filters - Metadata filtering syntax and operations
  • Setup - Prerequisites, Qdrant configuration, connection options
  • Error Handling - Exception types and handling patterns

Common Imports

// Core classes
import dev.langchain4j.store.embedding.qdrant.QdrantEmbeddingStore;
import dev.langchain4j.data.embedding.Embedding;
import dev.langchain4j.data.segment.TextSegment;
import dev.langchain4j.data.document.Metadata;

// Search
import dev.langchain4j.store.embedding.EmbeddingSearchRequest;
import dev.langchain4j.store.embedding.EmbeddingSearchResult;
import dev.langchain4j.store.embedding.EmbeddingMatch;

// Filters
import dev.langchain4j.store.embedding.filter.Filter;
import static dev.langchain4j.store.embedding.filter.MetadataFilterBuilder.*;

// Qdrant client (optional)
import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;

Quick Decision Tree

Need to initialize store? → See Setup for configuration options

Need to add embeddings?

  • Single embedding → add(Embedding)
  • With text/metadata → add(Embedding, TextSegment)
  • Multiple embeddings → addAll(List<Embedding>)
  • See Examples

Need to search?

  • Basic search → Build EmbeddingSearchRequest with query, maxResults, minScore
  • With filters → Add .filter(Filter) to request
  • See Examples and Filters

Need to remove?

  • Single → remove(String id)
  • Multiple → removeAll(Collection<String> ids)
  • By metadata → removeAll(Filter filter)
  • Everything → removeAll()

Need metadata filtering? → See Filters for complete syntax

Getting errors? → See Error Handling

Architecture Notes

The library wraps the Qdrant gRPC client and provides:

  • Vector Storage: Stores embeddings as Qdrant points with UUID-based identifiers
  • Metadata Management: Bidirectional conversion between LangChain4j Metadata and Qdrant payload
  • Filter Translation: Converts LangChain4j filter expressions to Qdrant filter format
  • Similarity Search: Cosine similarity-based vector search with optional filtering
  • Type Conversion: Handles conversion between Java types and Qdrant Value types

Prerequisites Checklist

Before using this library:

  1. ✓ Running Qdrant instance (local or cloud)
  2. ✓ Qdrant collection created with vector dimensions matching your embeddings
  3. ✓ Collection configured with cosine distance

See Setup for detailed prerequisites and configuration.

Integration with LangChain4j

This library implements the EmbeddingStore<TextSegment> interface and integrates seamlessly with:

  • Embedding Models: Any LangChain4j embedding model
  • Document Processing: TextSegment and Metadata support
  • Semantic Search: Native EmbeddingSearchRequest support
  • Retrieval Systems: Compatible with RAG and retrieval patterns

Example with embedding model:

import dev.langchain4j.model.embedding.EmbeddingModel;
import dev.langchain4j.model.embedding.AllMiniLmL6V2QuantizedEmbeddingModel;

EmbeddingModel model = new AllMiniLmL6V2QuantizedEmbeddingModel();
QdrantEmbeddingStore store = QdrantEmbeddingStore.builder()
    .collectionName("documents")
    .build();

TextSegment segment = TextSegment.from("Sample text");
Embedding embedding = model.embed(segment).content();
store.add(embedding, segment);

See Examples for complete integration patterns.

Configuration Patterns

Local Development

QdrantEmbeddingStore store = QdrantEmbeddingStore.builder()
    .collectionName("my-collection")
    .build();

Cloud Deployment

QdrantEmbeddingStore store = QdrantEmbeddingStore.builder()
    .host("your-cluster.qdrant.io")
    .port(6334)
    .collectionName("my-collection")
    .useTls(true)
    .apiKey("your-api-key")
    .build();

Custom Client

QdrantClient client = new QdrantClient(
    QdrantGrpcClient.newBuilder("localhost", 6334, false)
        .withApiKey("your-api-key")
        .build()
);
QdrantEmbeddingStore store = QdrantEmbeddingStore.builder()
    .client(client)
    .collectionName("my-collection")
    .build();

See Setup for more configuration options.

Install with Tessl CLI

npx tessl i tessl/maven-dev-langchain4j--langchain4j-qdrant@1.11.0

docs

api.md

error-handling.md

examples.md

filters.md

index.md

setup.md

tile.json