redisvl
Python client library and CLI for using Redis as a vector database
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a running Redis instance (>=8+ for vector search); local Docker setup or Redis Cloud connection needed.
- 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 · maintenance · safety
MIT (permissive) — MIT license (permissive) means you can use, modify, and distribute RedisVL freely in commercial and private projects with minimal restrictions.
last release 2026-08-07 (7 days) · last repo commit 2026-08-14 · 423 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 2,796,777 downloads/mo, #2,885 on PyPI
Alternatives
Verify before relying
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()- 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.
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 on this page. Verify before relying on it.
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
redisvl on PyPI
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.
Requires a running Redis instance (>=8+ for vector search); local Docker setup or Redis Cloud connection needed.
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()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 the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagesjsonpath-ngml-dtypesnumpypydanticpython-ulidpyyamlredistenacity |
| Maintenance | Actively maintained 7 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 2,796,777 / month, #2,885 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: redisvl-0.25.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “redis vector search python”
- redisvlRedisVL is a Python client for building AI applications with Redis…
- llama-index-vector-stores-redisIntegrates Redis as a vector store backend for LlamaIndex, enabling…
- langchain-redisIntegrates Redis with LangChain to provide vector storage, semantic…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also llama-index-vector-stores-redis · upstash-vector · walrus · turbopuffer · langchain-redis · nucliadb-utils · langchain-milvus · weaviate-client · llama-index-vector-stores-faiss · agent-framework-azure-ai-search