redis/redis-vl-python

Redis Vector Library (RedisVL) -- the AI-native Python client for Redis.

What it solves

Redis Vector Library (RedisVL) is a production-ready Python client designed to simplify the building of AI applications using Redis as a vector database. It streamlines the process of managing indices, performing complex vector and hybrid searches, and implementing common AI design patterns like semantic caching and LLM memory.

How it works

RedisVL provides a high-level API to interact with Redis, allowing developers to define schemas (via YAML or Python dictionaries) and create search indices. It supports multiple query types, including semantic similarity search (VectorQuery), full-text search (TextQuery), and hybrid search (combining both). The library also includes built-in integrations with various embedding providers (vectorizers) and rerankers to improve search result relevancy.

Who it’s for

It is intended for developers building RAG (Retrieval-Augmented Generation) pipelines, AI agents with long-term memory, and recommendation systems that require fast, real-time retrieval and enterprise-grade reliability.

Highlights

  • Comprehensive Search: Supports vector, range, filter, text, and hybrid search (combining semantic and full-text signals).
  • AI Extensions: Includes production-ready modules for semantic caching (to reduce LLM costs), embedding caching, LLM memory (semantic message history), and semantic routing.
  • Integrated Vectorizers: Out-of-the-box support for 8+ embedding providers including OpenAI, Cohere, HuggingFace, and Mistral.
  • Index Management: Simplifies schema design and data loading with a dedicated Python API and a command-line interface (CLI).
  • MCP Server: Ability to expose Redis indices to Model Context Protocol (MCP) clients.

Related

  • Project
    redis/redis

    Redis is a high-performance in-memory data structure server used as a cache, NoSQL database, and vector store to enable sub-millisecond latency for real-time applications.

  • Project
    RediSearch/RediSearch

    A Redis module that adds full-text search, secondary indexing, and vector similarity search to Redis, enabling high-performance querying of database records.

  • Project
    qdrant/qdrant-client

    A Python client library and SDK for the Qdrant vector search engine, enabling efficient storage and retrieval of vector embeddings.

  • Project
    infiniflow/infinity

    An AI-native database designed for LLM applications that provides high-speed hybrid search across dense and sparse embeddings, tensors, and full-text data.

  • Project
    Bessouat40/RAGLight

    A lightweight and modular Python library for implementing Retrieval-Augmented Generation (RAG), allowing users to easily integrate various LLMs and vector stores to chat with their documents.