RedisVL

A powerful, AI-native Java client library for Redis. Leverage the speed, flexibility, and reliability of Redis for real-time data to supercharge your AI application.

What is RedisVL?

RedisVL is a comprehensive Java library for building AI-native applications with Redis. It provides a high-level interface for:

Vector similarity search with advanced filtering
Schema-based index management from YAML or programmatic configuration
Hybrid queries combining vector search with metadata filters
Semantic and embedding caching for LLM applications
Multiple vectorization options (LangChain4J, local ONNX models)
Flexible storage with both Redis Hash and JSON support

RedisVL is a port of the popular Python RedisVL library, bringing these powerful capabilities to the Java ecosystem.

Resources

Getting Started

Learn the basics and create your first vector search application.

Get Started →

Hybrid Queries

Combine vector search with powerful metadata filtering.

Learn More →

LLM Cache

Implement semantic caching to reduce costs and increase performance.

Explore Caching →

Vectorizers

Create embeddings with LangChain4J or local ONNX models.

Choose a Vectorizer →

Rerankers

Improve search quality with HuggingFace cross-encoder models.

Boost Relevance →

Features

RedisVL for Java offers powerful features for AI-native applications:

Index Management - Design search schema and indices with ease from YAML or programmatic configuration
Advanced Vector Search - Perform powerful vector search queries with complex filtering support
Embedding Creation - Use LangChain4J, local ONNX models, or any of the other supported vectorizers to create embeddings
Reranking - Improve search result quality with HuggingFace cross-encoder models via ONNX Runtime
Semantic Caching - Cache LLM responses with semantic similarity, increasing QPS and decreasing system cost
Embeddings Cache - Cache vector embeddings to avoid redundant computation
Storage Flexibility - Choose between Hash and JSON storage based on your needs
Pagination - Efficiently handle large result sets

Installation

Add RedisVL to your project:

Maven

<dependency>
    <groupId>com.redis</groupId>
    <artifactId>redisvl</artifactId>
    <version>0.13.1</version>
</dependency>

Gradle

implementation 'com.redis:redisvl:0.13.1'

Quick Example

import com.redis.vl.index.SearchIndex;
import com.redis.vl.schema.IndexSchema;
import com.redis.vl.query.VectorQuery;

// Load schema from YAML
IndexSchema schema = IndexSchema.fromYaml("schema.yaml");

// Create index
SearchIndex index = new SearchIndex(schema, jedis);
index.create(true);

// Load data
index.load(data);

// Vector search with filters
VectorQuery query = VectorQuery.builder()
    .vector(queryVector)
    .field("embedding")
    .numResults(5)
    .withPreFilter("@age:[20 35]")
    .build();

List<Map<String, Object>> results = index.query(query);

Connecting with the Community

Join the Redis community to get help, share your experiences, and contribute: