$git clone https://github.com/redis/redis-vl-python[Documentation](https://docs.redisvl.com) • [Recipes](https://github.com/redis-developer/redis-ai-resources) • [GitHub](https://github.com/redis/redis-vl-python)
| 1 | <div align="center"> |
| 2 | <img width="300" src="https://raw.githubusercontent.com/redis/redis-vl-python/main/docs/_static/Redis_Logo_Red_RGB.svg" alt="Redis"> |
| 3 | <h1>Redis Vector Library</h1> |
| 4 | <p><strong>The AI-native Redis Python client</strong></p> |
| 5 | </div> |
| 6 | |
| 7 | <div align="center"> |
| 8 | |
| 9 | [](https://opensource.org/licenses/MIT) |
| 10 | [](https://pypi.org/project/redisvl/) |
| 11 |  |
| 12 | [](https://github.com/redis/redis-vl-python/stargazers) |
| 13 | |
| 14 | [](https://github.com/psf/black) |
| 15 |  |
| 16 |  |
| 17 | |
| 18 | **[Documentation](https://docs.redisvl.com)** • **[Recipes](https://github.com/redis-developer/redis-ai-resources)** • **[GitHub](https://github.com/redis/redis-vl-python)** |
| 19 | |
| 20 | </div> |
| 21 | |
| 22 | --- |
| 23 | |
| 24 | ## Introduction |
| 25 | |
| 26 | Redis Vector Library (RedisVL) is the production-ready Python client for AI applications built on Redis. **Lightning-fast vector search meets enterprise-grade reliability.** |
| 27 | |
| 28 | Perfect for building **RAG pipelines** with real-time retrieval, **AI agents** with memory and semantic routing, and **recommendation systems** with fast search and reranking. |
| 29 | |
| 30 | <div align="center"> |
| 31 | |
| 32 | | **🎯 Core Capabilities** | **🚀 AI Extensions** | **🛠️ Dev Utilities** | |
| 33 | |:---:|:---:|:---:| |
| 34 | | **[Index Management](#index-management)**<br/>*Schema design, data loading, CRUD ops* | **[Semantic Caching](#semantic-caching)**<br/>*Reduce LLM costs & boost throughput* | **[CLI](#command-line-interface)**<br/>*Index management from terminal* | |
| 35 | | **[Vector Search](#retrieval)**<br/>*Similarity search with metadata filters* | **[LLM Memory](#llm-memory)**<br/>*Agentic AI context management* | **Async Support**<br/>*Async indexing and search for improved performance* | |
| 36 | | **[Complex Filtering](#retrieval)**<br/>*Combine multiple filter types* | **[Semantic Routing](#semantic-routing)**<br/>*Intelligent query classification* | **[Vectorizers](#vectorizers)**<br/>*8+ embedding provider integrations* | |
| 37 | | **[Hybrid Search](#retrieval)**<br/>*Combine semantic & full-text signals* | **[Embedding Caching](#embedding-caching)**<br/>*Cache embeddings for efficiency* | **[Rerankers](#rerankers)**<br/>*Improve search result relevancy* | |
| 38 | | | | **[MCP Server](#mcp-server)**<br/>*Expose one or more existing Redis indexes to MCP clients* | |
| 39 | |
| 40 | </div> |
| 41 | |
| 42 | |
| 43 | |
| 44 | # 💪 Getting Started |
| 45 | |
| 46 | ## Installation |
| 47 | |
| 48 | Install `redisvl` into your Python (>=3.10) environment using `pip`: |
| 49 | |
| 50 | ```bash |
| 51 | pip install redisvl |
| 52 | ``` |
| 53 | |
| 54 | Install the MCP server extra when you want to expose one or more existing Redis indexes through MCP: |
| 55 | |
| 56 | ```bash |
| 57 | pip install redisvl[mcp] |
| 58 | ``` |
| 59 | |
| 60 | > For more detailed instructions, visit the [installation guide](https://docs.redisvl.com/en/latest/user_guide/installation.html). |
| 61 | > For MCP concepts and setup, see the [RedisVL MCP docs](https://docs.redisvl.com/en/latest/concepts/mcp.html) and the [MCP how-to guide](https://docs.redisvl.com/en/latest/user_guide/how_to_guides/mcp.html). |
| 62 | |
| 63 | ## Redis |
| 64 | |
| 65 | Choose from multiple Redis deployment options: |
| 66 | |
| 67 | <details> |
| 68 | <summary><b>Redis Cloud</b> - Managed cloud database (free tier available)</summary> |
| 69 | |
| 70 | [Redis Cloud](https://redis.io/try-free) offers a fully managed Redis service with a free tier, perfect for getting started quickly. |
| 71 | |
| 72 | </details> |
| 73 | |
| 74 | <details> |
| 75 | <summary><b>Docker</b> - Local development</summary> |
| 76 | |
| 77 | Run Redis locally using Docker: |
| 78 | |
| 79 | ```bash |
| 80 | docker run -d --name redis -p 6379:6379 redis:latest |
| 81 | ``` |
| 82 | |
| 83 | This runs Redis 8+ with built-in vector search capabilities. |
| 84 | |
| 85 | </details> |
| 86 | |
| 87 | <details> |
| 88 | <summary><b>Redis Enterprise</b> - Commercial, self-hosted database</summary> |
| 89 | |
| 90 | [Redis Enterprise](https://redis.io/enterprise/) provides enterprise-grade |