---
id: redisvl
version: "0.25.1"
license: MIT
license_treatment: permissive
maintenance: active
---

# redisvl — Python client library and CLI for using Redis as a vector database

License: permissive · Maintenance: active · Downloads: 2.8M/mo

## What it is and what it does

RedisVL is a production-ready Python client that turns Redis into a vector database for AI applications. It provides schema-driven index management, vector search with metadata filtering, and hybrid search combining semantic and full-text signals. The package handles the boilerplate of defining indexes, loading embeddings, and executing queries—all backed by Redis's native vector search engine.

Typical workflows include building RAG pipelines with real-time retrieval, implementing AI agent memory systems, and creating recommendation engines. It ships with async support, CLI tools for index management, and integrations with multiple embedding providers. The eight runtime dependencies (numpy, pydantic, redis, tenacity, jsonpath-ng, ml-dtypes, python-ulid, pyyaml) are all well-maintained libraries, keeping installation friction low.

Use it for:

- Build RAG systems that retrieve relevant documents from Redis based on semantic similarity to user queries.
- Implement AI agent memory by storing and retrieving conversation context as embeddings with semantic routing.
- Create recommendation engines that search for similar items using vector similarity with metadata filtering.
- Cache embeddings to reduce LLM API costs while maintaining fast semantic search performance.
- Perform hybrid search combining vector similarity with full-text keyword matching on the same dataset.
- Manage multiple vector indexes from a CLI without writing Python, using schema files and batch operations.

## Worth the install?

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

RedisVL is a Python client for building AI applications with Redis vector search, enabling semantic search, RAG pipelines, and vector-backed retrieval with metadata filtering and hybrid search capabilities.

Yes. RedisVL is actively maintained, has no known vulnerabilities, uses a permissive MIT license, and solves a real problem—bridging Python and Redis for vector-backed AI workloads. Install friction is low and it supports modern Python versions (3.10–3.14). Best for teams already using or planning to adopt Redis, or those seeking a lightweight vector search layer without a separate database.

## Install

pip install redisvl
uv add redisvl
poetry add redisvl

## Installing redisvl

Before you install: Low friction: pure Python wheel with eight runtime dependencies (numpy, pydantic, redis, tenacity, and others). Active maintenance with a commit from 2026-08-14 and release from 2026-08-07; supports Python 3.10–3.14.

License in practice: MIT license (permissive) means you can use, modify, and distribute RedisVL freely in commercial and private projects with minimal restrictions.

Quickstart:

pip install redisvl

from redisvl.schema import IndexSchema
from redisvl.index import SearchIndex

schema = IndexSchema.from_dict({
    "index": {"name": "idx", "prefix": "doc"},
    "fields": [{"name": "embedding", "type": "vector", "attrs": {"dims": 4, "distance_metric": "cosine"}}]
})
index = SearchIndex(schema, redis_url="redis://localhost:6379")
index.create()

Requires a running Redis instance (>=8+ for vector search); local Docker setup or Redis Cloud connection needed.

Verify before relying:

- Performance characteristics (latency, throughput) for large-scale vector indexes not specified in fact sheet.
- Whether all 8+ embedding provider integrations mentioned in description are included in base package or require separate dependencies.
- Specific reranker implementations and their availability in version 0.25.1.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 2.8M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

redis vector search python, vector database client, semantic search with redis, rag pipeline vector retrieval, embedding similarity search, redis ai applications, vector indexing and search, vector-search, rag-pipeline, redis-client

[View on SkillFed](https://skillfed.io/packages/redisvl) · [View on PyPI](https://pypi.org/project/redisvl/)