Langchain4j Vector Stores Configuration

This handles LangChain4J vector store setup for RAG applications across PostgreSQL/pgvector, Pinecone, MongoDB Atlas, Milvus, and Neo4j. You get builder-based configuration patterns, connection pooling with HikariCP, metadata filtering with multiple field types, and health check implementations. The validation workflow is smart: it walks you through connection testing, dimension validation, and test queries before you ingest production data. Most useful when you're wiring up semantic search or need to switch between vector databases without rewriting your embedding logic. The examples cover everything from basic in-memory stores for development to production setups with monitoring and connection pools. Good reference if you're tired of reading vendor-specific documentation for each database.

skills.sh installs: 3.8K
GitHub stars: 369
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-vector-stores-configuration --agent claude-code

Installs into .claude/skills of the current project.

Files

LangChain4J Vector Stores Configuration

Configure vector stores for Retrieval-Augmented Generation applications with LangChain4J.

Overview

LangChain4J provides a unified abstraction for vector stores (PostgreSQL/pgvector, Pinecone, MongoDB Atlas, Milvus, Neo4j) with builder-based configuration, metadata filtering, and hybrid search support.

When to Use

Configuring vector stores for semantic search and RAG applications
Setting up embedding storage with metadata filtering and hybrid search
Optimizing vector database performance for production AI workloads

Instructions

Set Up Basic Vector Store

Configure an embedding store for vector operations:

@Bean
public EmbeddingStore<TextSegment> embeddingStore() {
    return PgVectorEmbeddingStore.builder()
        .host("localhost")
        .port(5432)
        .database("vectordb")
        .user("username")
        .password("password")
        .table("embeddings")
        .dimension(1536) // OpenAI embedding dimension
        .createTable(true)
        .useIndex(true)
        .build();
}