# RediSearch

> Redis Stack with vector search via RediSearch module, HNSW/Flat indexes on in-memory store. Features: Hybrid BM25+vector, real-time cache, multi-tenancy. Use cases: Caching LLM responses, high-throughput RAG. Comparisons: Faster than disk DBs for hot data; vs Memgraph: simpler key-value.

- **URL:** https://github.com/RediSearch/RediSearch
- **Category:** In Memory Hybrid Vector Stores
- **Tags:** In Memory Vector Search, Hybrid BM25, High Throughput, Redis Stack
- **Updated:** 2026-04-28 11:38
- **Canonical page:** https://vectordb.ever.works/it/items/redisearch

## Details

## Overview

Redis module for full-text, secondary indexing, vector similarity (KNN/filtered/range).

## Features

- Vector similarity: KNN, filtered KNN
- Full-text with tf-idf, phonetic, stemming
- Aggregations, geospatial
- Cluster scaling (Enterprise)

## License

RSALv2/SSPLv1

## Pricing

Open-source; Enterprise for clusters.

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/it/items/redisearch._