# Redis Vl Python > Redis Vector Library (RedisVL) -- the AI-native Python client for Redis. - **Type:** MCP server - **Install:** `agentstack add mcp-redis-redis-vl-python` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [redis](https://agentstack.voostack.com/s/redis) - **Installs:** 0 - **Category:** [Databases](https://agentstack.voostack.com/c/databases) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [redis](https://github.com/redis) - **Source:** https://github.com/redis/redis-vl-python - **Website:** https://docs.redisvl.com ## Install ```sh agentstack add mcp-redis-redis-vl-python ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About Redis Vector Library The AI-native Redis Python client [](https://opensource.org/licenses/MIT) [](https://pypi.org/project/redisvl/) [](https://github.com/redis/redis-vl-python/stargazers) [](https://github.com/psf/black) **[Documentation](https://docs.redisvl.com)** • **[Recipes](https://github.com/redis-developer/redis-ai-resources)** • **[GitHub](https://github.com/redis/redis-vl-python)** --- ## Introduction Redis Vector Library (RedisVL) is the production-ready Python client for AI applications built on Redis. **Lightning-fast vector search meets enterprise-grade reliability.** Perfect for building **RAG pipelines** with real-time retrieval, **AI agents** with memory and semantic routing, and **recommendation systems** with fast search and reranking. | **🎯 Core Capabilities** | **🚀 AI Extensions** | **🛠️ Dev Utilities** | |:---:|:---:|:---:| | **[Index Management](#index-management)***Schema design, data loading, CRUD ops* | **[Semantic Caching](#semantic-caching)***Reduce LLM costs & boost throughput* | **[CLI](#command-line-interface)***Index management from terminal* | | **[Vector Search](#retrieval)***Similarity search with metadata filters* | **[LLM Memory](#llm-memory)***Agentic AI context management* | **Async Support***Async indexing and search for improved performance* | | **[Complex Filtering](#retrieval)***Combine multiple filter types* | **[Semantic Routing](#semantic-routing)***Intelligent query classification* | **[Vectorizers](#vectorizers)***8+ embedding provider integrations* | | **[Hybrid Search](#retrieval)***Combine semantic & full-text signals* | **[Embedding Caching](#embedding-caching)***Cache embeddings for efficiency* | **[Rerankers](#rerankers)***Improve search result relevancy* | | | | **[MCP Server](#mcp-server)***Expose an existing Redis index to MCP clients* | # 💪 Getting Started ## Installation Install `redisvl` into your Python (>=3.10) environment using `pip`: ```bash pip install redisvl ``` Install the MCP server extra when you want to expose an existing Redis index through MCP: ```bash pip install redisvl[mcp] ``` > For more detailed instructions, visit the [installation guide](https://docs.redisvl.com/en/latest/user_guide/installation.html). > 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). ## Redis Choose from multiple Redis deployment options: Redis Cloud - Managed cloud database (free tier available) [Redis Cloud](https://redis.io/try-free) offers a fully managed Redis service with a free tier, perfect for getting started quickly. Docker - Local development Run Redis locally using Docker: ```bash docker run -d --name redis -p 6379:6379 redis:latest ``` This runs Redis 8+ with built-in vector search capabilities. Redis Enterprise - Commercial, self-hosted database [Redis Enterprise](https://redis.io/enterprise/) provides enterprise-grade features for production deployments. Redis Sentinel - High availability with automatic failover Configure Redis Sentinel for high availability: ```python # Connect via Sentinel redis_url="redis+sentinel://sentinel1:26379,sentinel2:26379/mymaster" ``` Azure Managed Redis - Fully managed Redis Enterprise on Azure [Azure Managed Redis](https://azure.microsoft.com/en-us/products/managed-redis) provides fully managed Redis Enterprise on Microsoft Azure. > 💡 **Tip**: Enhance your experience and observability with the free [Redis Insight GUI](https://redis.io/insight/). # Overview ## Index Management 1. **Design a schema** for your use case that models your dataset with built-in Redis indexable fields (*e.g. text, tags, numerics, geo, and vectors*). Load schema from YAML file ```yaml index: name: user-idx prefix: user storage_type: json fields: - name: user type: tag - name: credit_score type: tag - name: job_title type: text attrs: sortable: true no_index: false # Index for search (default) unf: false # Normalize case for sorting (default) - name: embedding type: vector attrs: algorithm: flat dims: 4 distance_metric: cosine datatype: float32 ``` ```python from redisvl.schema import IndexSchema schema = IndexSchema.from_yaml("schemas/schema.yaml") ``` Load schema from Python dictionary ```python from redisvl.schema import IndexSchema schema = IndexSchema.from_dict({ "index": { "name": "user-idx", "prefix": "user", "storage_type": "json" }, "fields": [ {"name": "user", "type": "tag"}, {"name": "credit_score", "type": "tag"}, { "name": "job_title", "type": "text", "attrs": { "sortable": True, "no_index": False, # Index for search "unf": False # Normalize case for sorting } }, { "name": "embedding", "type": "vector", "attrs": { "algorithm": "flat", "datatype": "float32", "dims": 4, "distance_metric": "cosine" } } ] }) ``` > 📚 Learn more about [schema design](https://docs.redisvl.com/en/stable/user_guide/01_getting_started.html#define-an-indexschema) and [schema creation](https://docs.redisvl.com/en/stable/user_guide/01_getting_started.html#example-schema-creation). 2. [Create a SearchIndex](https://docs.redisvl.com/en/stable/user_guide/01_getting_started.html#create-a-searchindex) class with an input schema to perform admin and search operations on your index in Redis: ```python from redis import Redis from redisvl.index import SearchIndex # Define the index index = SearchIndex(schema, redis_url="redis://localhost:6379") # Create the index in Redis index.create() ``` > An async-compatible index class also available: [AsyncSearchIndex](https://docs.redisvl.com/en/stable/api/searchindex.html#redisvl.index.AsyncSearchIndex). 3. [Load](https://docs.redisvl.com/en/stable/user_guide/01_getting_started.html#load-data-to-searchindex) and [fetch](https://docs.redisvl.com/en/stable/user_guide/01_getting_started.html#fetch-an-object-from-redis) data to/from your Redis instance: ```python data = {"user": "john", "credit_score": "high", "embedding": [0.23, 0.49, -0.18, 0.95]} # load list of dictionaries, specify the "id" field index.load([data], id_field="user") # fetch by "id" john = index.fetch("john") ``` ## Retrieval Define queries and perform advanced searches over your indices, including vector search, complex filtering, and hybrid search combining semantic and full-text signals. Quick Reference: Query Types | Query Type | Use Case | Description | |:---|:---|:---| | `VectorQuery` | Semantic similarity search | Find similar vectors with optional filters | | `RangeQuery` | Distance-based search | Vector search within a defined distance range | | `FilterQuery` | Metadata filtering | Filter and search using metadata fields | | `TextQuery` | Full-text search | BM25-based keyword search with field weighting | | `HybridQuery` | Combined search | Combine semantic + full-text signals (Redis 8.4.0+) | | `CountQuery` | Counting records | Count documents matching filter criteria | ### Vector Search - [VectorQuery](https://docs.redisvl.com/en/stable/api/query.html#vectorquery) - Flexible vector queries with customizable filters enabling semantic search: ```python from redisvl.query import VectorQuery query = VectorQuery( vector=[0.16, -0.34, 0.98, 0.23], vector_field_name="embedding", num_results=3, # Optional: tune search performance with runtime parameters ef_runtime=100 # HNSW: higher for better recall ) # run the vector search query against the embedding field results = index.query(query) ``` - [RangeQuery](https://docs.redisvl.com/en/stable/api/query.html#rangequery) - Vector search within a defined range paired with customizable filters ### Complex Filtering Build complex filtering queries by combining multiple filter types (tags, numerics, text, geo, timestamps) using logical operators: ```python from redisvl.query import VectorQuery from redisvl.query.filter import Tag, Num # Combine multiple filter types tag_filter = Tag("user") == "john" price_filter = Num("price") >= 100 # Create complex filtering query with combined filters query = VectorQuery( vector=[0.16, -0.34, 0.98, 0.23], vector_field_name="embedding", filter_expression=tag_filter & price_filter, num_results=10 ) results = index.query(query) ``` - [FilterQuery](https://docs.redisvl.com/en/stable/api/query.html#filterquery) - Standard search using filters and full-text search - [CountQuery](https://docs.redisvl.com/en/stable/api/query.html#countquery) - Count the number of indexed records given attributes - [TextQuery](https://docs.redisvl.com/en/stable/api/query.html#textquery) - Full-text search with support for field weighting and BM25 scoring > Learn more about building [complex filtering queries](https://docs.redisvl.com/en/stable/user_guide/02_complex_filtering.html). ### Hybrid Search Combine semantic (vector) search with full-text (BM25) search signals for improved search quality: - [HybridQuery](https://docs.redisvl.com/en/stable/api/query.html#hybridquery) - Native hybrid search combining text and vector similarity (Redis 8.4.0+): ```python from redisvl.query import HybridQuery hybrid_query = HybridQuery( text="running shoes", text_field_name="description", vector=[0.1, 0.2, 0.3], vector_field_name="embedding", combination_method="LINEAR", # or "RRF" num_results=10 ) results = index.query(hybrid_query) ``` - [AggregateHybridQuery](https://docs.redisvl.com/en/stable/api/query.html#aggregatehybridquery) - Hybrid search using aggregation (compatible with earlier Redis versions) > Learn more about [hybrid search](https://docs.redisvl.com/en/stable/user_guide/11_advanced_queries.html#hybrid-queries-combining-text-and-vector-search). ## Dev Utilities ### Vectorizers Integrate with popular embedding providers to greatly simplify the process of vectorizing unstructured data for your index and queries. Supported Vectorizer Providers - [AzureOpenAI](https://docs.redisvl.com/en/stable/api/vectorizer.html#azureopenaitextvectorizer) - [Cohere](https://docs.redisvl.com/en/stable/api/vectorizer.html#coheretextvectorizer) - [Custom](https://docs.redisvl.com/en/stable/api/vectorizer.html#customtextvectorizer) - [GCP VertexAI](https://docs.redisvl.com/en/stable/api/vectorizer.html#vertexaitextvectorizer) - [HuggingFace](https://docs.redisvl.com/en/stable/api/vectorizer.html#hftextvectorizer) - [Mistral](https://docs.redisvl.com/en/stable/api/vectorizer/html#mistralaitextvectorizer) - [OpenAI](https://docs.redisvl.com/en/stable/api/vectorizer.html#openaitextvectorizer) - [VoyageAI](https://docs.redisvl.com/en/stable/api/vectorizer/html#voyageaitextvectorizer) ```python from redisvl.utils.vectorize import CohereTextVectorizer # set COHERE_API_KEY in your environment co = CohereTextVectorizer() embedding = co.embed( text="What is the capital city of France?", input_type="search_query" ) embeddings = co.embed_many( texts=["my document chunk content", "my other document chunk content"], input_type="search_document" ) ``` > Learn more about using [vectorizers](https://docs.redisvl.com/en/stable/user_guide/04_vectorizers.html) in your embedding workflows. ### Rerankers [Integrate with popular reranking providers](https://docs.redisvl.com/en/stable/user_guide/06_rerankers.html) to improve the relevancy of the initial search results from Redis ## Extensions **RedisVL Extensions** provide production-ready modules implementing best practices and design patterns for working with LLM memory and agents. These extensions encapsulate learnings from our user community and enterprise customers. > 💡 *Have an idea for another extension? Open a PR or reach out to us at . We're always open to feedback.* ### Semantic Caching Increase application throughput and reduce the cost of using LLM models in production by leveraging previously generated knowledge with the [`SemanticCache`](https://docs.redisvl.com/en/stable/api/cache.html#semanticcache). Example: Semantic Cache Usage ```python from redisvl.extensions.cache.llm import SemanticCache # init cache with TTL and semantic distance threshold llmcache = SemanticCache( name="llmcache", ttl=360, redis_url="redis://localhost:6379", distance_threshold=0.1 # Redis COSINE distance [0-2], lower is stricter ) # store user queries and LLM responses in the semantic cache llmcache.store( prompt="What is the capital city of France?", response="Paris" ) # quickly check the cache with a slightly different prompt (before invoking an LLM) response = llmcache.check(prompt="What is France's capital city?") print(response[0]["response"]) ``` ```stdout >>> Paris ``` > Learn more about [semantic caching](https://docs.redisvl.com/en/stable/user_guide/03_llmcache.html) for LLMs. ### Embedding Caching Reduce computational costs and improve performance by caching embedding vectors with their associated text and metadata using the [`EmbeddingsCache`](https://docs.redisvl.com/en/stable/api/cache.html#embeddingscache). Example: Embedding Cache Usage ```python from redisvl.extensions.cache.embeddings import EmbeddingsCache from redisvl.utils.vectorize import HFTextVectorizer # Initialize embedding cache embed_cache = EmbeddingsCache( name="embed_cache", redis_url="redis://localhost:6379", ttl=3600 # 1 hour TTL ) # Initialize vectorizer with cache vectorizer = HFTextVectorizer( model="sentence-transformers/all-MiniLM-L6-v2", cache=embed_cache ) # First call computes and caches the embedding embedding = vectorizer.embed("What is machine learning?") # Subsequent calls retrieve from cache (much faster!) cached_embedding = vectorizer.embed("What is machine learning?") ``` ```stdout >>> Cache hit! Retrieved from Redis in > Learn more about [embedding caching](https://docs.redisvl.com/en/stable/user_guide/10_embeddings_cache.html) for improved performance. ### LLM Memory Improve personalization and accuracy of LLM responses by providing user conversation context. Manage access to memory data using recency or relevancy, *powered by vector search* with the [`MessageHistory`](https://docs.redisvl.com/en/stable/api/message_history.html). Example: Message History Usage ```python from redisvl.extensions.message_history import SemanticMessageHistory history = SemanticMessageHistory( name="my-session", redis_url="redis://localhost:6379", distance_threshold=0.7 ) # Supports roles: system, user, llm, tool # Optional metadata field for additional context history.add_messages([ {"role": "user", "content": "hello, how are you?"}, {"role": "llm", "content": "I'm doing fine, thanks."}, {"role": "user", "content": "what is the weather going to be today?"}, {"role": "llm", "content": "I don't know", "metadata": {"model": "gpt-4"}} ]) # Get recent chat history history.get_recent(top_k=1) # >>> [{"role": "llm", "content": "I don't know", "metadata": {"model": "gpt-4"}}] # Get relevant chat history (powered by vector search) history.get_relevant("weather", top_k=1) # >>> [{"role": "user", "content": "what is the weathe … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [redis](https://github.com/redis) - **Source:** [redis/redis-vl-python](https://github.com/redis/redis-vl-python) - **License:** MIT - **Homepage:** https://docs.redisvl.com Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-redis-redis-vl-python - Seller: https://agentstack.voostack.com/s/redis - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.