redisvl

Redis Vector Library

The AI-native Redis Python client

Documentation • Recipes • GitHub

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.

🎯 Core Capabilities	🚀 AI Extensions	🛠️ Dev Utilities
Index Management Schema design, data loading, CRUD ops	Semantic Caching Reduce LLM costs & boost throughput	CLI Index management from terminal
Vector Search Similarity search with metadata filters	LLM Memory Agentic AI context management	Async Support Async indexing and search for improved performance
Hybrid Queries Vector + text + metadata combined	Semantic Routing Intelligent query classification	Vectorizers 8+ embedding provider integrations
Multi-Query Types Vector, Range, Filter, Count queries	Embedding Caching Cache embeddings for efficiency	Rerankers Improve search result relevancy

Built for Modern AI Workloads

• RAG Pipelines → Real-time retrieval with hybrid search capabilities
• AI Agents → Short term & long term memory and semantic routing for intent-based decisions
• Recommendation Systems → Fast retrieval and reranking

💪 Getting Started

Installation

Install redisvl into your Python (>=3.9) environment using pip:

pip install redisvl

For more detailed instructions, visit the installation guide.

Redis

Choose from multiple Redis deployment options:

• Redis Cloud: Managed cloud database (free tier available)

• Redis Stack: Docker image for development

  docker run -d --name redis-stack -p 6379:6379 -p 8001:8001 redis/redis-stack:latest
  

• Redis Enterprise: Commercial, self-hosted database

• Redis Sentinel: High availability with automatic failover

  # Connect via Sentinel
  redis_url="redis+sentinel://sentinel1:26379,sentinel2:26379/mymaster"
  

• Azure Managed Redis: Fully managed Redis Enterprise on Azure

Enhance your experience and observability with the free Redis Insight GUI.

Overview

Index Management

• Design a schema for your use case that models your dataset with built-in Redis and indexable fields (e.g. text, tags, numerics, geo, and vectors). Load a schema from a YAML file:

  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
  

  from redisvl.schema import IndexSchema
  
  schema = IndexSchema.from_yaml("schemas/schema.yaml")
  

  Or load directly from a Python dictionary:

  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"
              }
          }
      ]
  })
  

• Create a SearchIndex class with an input schema to perform admin and search operations on your index in Redis:

  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.

• Load and fetch data to/from your Redis instance:

  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 the combination of vectors, metadata filters, and more.

• VectorQuery - Flexible vector queries with customizable filters enabling semantic search:

  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)
  

  Incorporate complex metadata filters on your queries:

  from redisvl.query.filter import Tag
  
  # define a tag match filter
  tag_filter = Tag("user") == "john"
  
  # update query definition
  query.set_filter(tag_filter)
  
  # execute query
  results = index.query(query)
  

• RangeQuery - Vector search within a defined range paired with customizable filters

• FilterQuery - Standard search using filters and the full-text search

• CountQuery - Count the number of indexed records given attributes

• TextQuery - Full-text search with support for field weighting and BM25 scoring

Read more about building advanced Redis queries.

Dev Utilities

Vectorizers

Integrate with popular embedding providers to greatly simplify the process of vectorizing unstructured data for your index and queries:

• AzureOpenAI
• Cohere
• Custom
• GCP VertexAI
• HuggingFace
• Mistral
• OpenAI
• VoyageAI

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 in your embedding workflows.

Rerankers

Integrate with popular reranking providers to improve the relevancy of the initial search results from Redis

Extensions

We're excited to announce the support for RedisVL Extensions. These modules implement interfaces exposing best practices and design patterns for working with LLM memory and agents. We've taken the best from what we've learned from our users (that's you) as well as bleeding-edge customers, and packaged it up.

Have an idea for another extension? Open a PR or reach out to us at [e-mail]. 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.

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
)

# 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"])

>>> Paris

Learn more about semantic caching for LLMs.

Embedding Caching

Reduce computational costs and improve performance by caching embedding vectors with their associated text and metadata using the EmbeddingsCache.

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?")

>>> Cache hit! Retrieved from Redis in <1ms

Learn more about embedding caching 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.

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 weather going to be today?"}]

Filter messages by role:

# Get only user messages
history.get_recent(role="user")
# Or multiple roles
history.get_recent(role=["user", "system"])

Learn more about LLM memory.

Semantic Routing

Build fast decision models that run directly in Redis and route user queries to the nearest "route" or "topic".

from redisvl.extensions.router import Route, SemanticRouter

routes = [
    Route(
        name="greeting",
        references=["hello", "hi"],
        metadata={"type": "greeting"},
        distance_threshold=0.3,
    ),
    Route(
        name="farewell",
        references=["bye", "goodbye"],
        metadata={"type": "farewell"},
        distance_threshold=0.3,
    ),
]

# build semantic router from routes
router = SemanticRouter(
    name="topic-router",
    routes=routes,
    redis_url="redis://localhost:6379",
)


router("Hi, good morning")

>>> RouteMatch(name='greeting', distance=0.273891836405)

Learn more about semantic routing.

Command Line Interface

Create, destroy, and manage Redis index configurations from a purpose-built CLI interface: rvl.

$ rvl -h

usage: rvl <command> [<args>]

Commands:
        index       Index manipulation (create, delete, etc.)
        version     Obtain the version of RedisVL
        stats       Obtain statistics about an index

Read more about using the CLI.

🚀 Why RedisVL?

Redis is a proven, high-performance database that excels at real-time workloads. With RedisVL, you get a production-ready Python client that makes Redis's vector search, caching, and session management capabilities easily accessible for AI applications.

Built on the Redis Python client, RedisVL provides an intuitive interface for vector search, LLM caching, and conversational AI memory - all the core components needed for modern AI workloads.

😁 Helpful Links

For additional help, check out the following resources:

• Getting Started Guide
• API Reference
• Redis AI Recipes

🫱🏼‍🫲🏽 Contributing

Please help us by contributing PRs, opening GitHub issues for bugs or new feature ideas, improving documentation, or increasing test coverage. Read more about how to contribute!

🚧 Maintenance

This project is supported by Redis, Inc on a good faith effort basis. To report bugs, request features, or receive assistance, please file an issue.