---
id: llama-index-vector-stores-redis
version: "0.8.0"
license: MIT
license_treatment: permissive
maintenance: active
---

# llama-index-vector-stores-redis — llama-index vector_stores redis integration

License: permissive · Maintenance: active · Downloads: 79.7K/mo

## What it is and what it does

This package provides a LlamaIndex integration that uses Redis as the backend storage for vector embeddings. It bridges LlamaIndex's vector store abstraction with Redis's vector capabilities through the redisvl library, allowing developers to build retrieval-augmented generation (RAG) systems and semantic search applications that persist embeddings in Redis.

The package is designed for applications that need fast, scalable vector similarity search without requiring a separate specialized vector database. It fits into the LlamaIndex ecosystem as a drop-in vector store option, handling embedding storage, indexing, and retrieval operations against a Redis instance.

Use it for:

- Build RAG pipelines that store document embeddings in Redis for fast retrieval during question-answering workflows.
- Implement semantic search over large document collections using Redis as the vector index backend.
- Integrate vector search into existing applications already using Redis for caching or session storage.
- Prototype and deploy LlamaIndex applications with Redis as a cost-effective vector store alternative.
- Scale vector search workloads by leveraging Redis's in-memory performance and clustering capabilities.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates Redis as a vector store backend for LlamaIndex, enabling storage and retrieval of vector embeddings in Redis for RAG and semantic search applications.

Yes, if you are building LlamaIndex applications and have Redis infrastructure available or planned. The package has low install friction, active maintenance, permissive licensing, and no known vulnerabilities. Install only if you intend to use Redis as your vector store backend; it is not useful standalone without LlamaIndex and a Redis instance.

## Install

pip install llama-index-vector-stores-redis
uv add llama-index-vector-stores-redis
poetry add llama-index-vector-stores-redis

## Installing llama-index-vector-stores-redis

Before you install: Low install friction with only two runtime dependencies (llama-index-core and redisvl). Package is actively maintained with a recent release cycle.

License in practice: MIT license permits use, modification, and distribution with minimal restrictions—suitable for both open-source and commercial projects.

Quickstart:

pip install llama-index-vector-stores-redis

from llama_index.vector_stores.redis import RedisVectorStore
from redisvl.index import SearchIndex

# Initialize Redis vector store with connection details
vector_store = RedisVectorStore(index_name="my_index")

Requires Python >=3.10,<3.14 and an accessible Redis server instance.

Verify before relying:

- Whether Redis server setup or configuration is required beyond installing this package
- Performance characteristics and scalability limits for large embedding datasets
- Compatibility with specific versions of llama-index-core and redisvl beyond the stated Python version range

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 79.7K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

redis vector store, llama index redis integration, vector embeddings redis, semantic search redis, rag vector database, redis embedding storage, llama index vector backend, vector-search, rag, llama-index-integration

[View on SkillFed](https://skillfed.io/packages/llama-index-vector-stores-redis) · [View on PyPI](https://pypi.org/project/llama-index-vector-stores-redis/)