Redis for AI documentation

An overview of Redis for AI documentation

Redis stores and indexes vector embeddings that semantically represent unstructured data including text passages, images, videos, or audio. Store vectors and the associated metadata within hashes or JSON documents for indexing and querying.

Vector	RAG	RedisVL
Redis vector database quick start guide	Retrieval-Augmented Generation quick start guide	Redis vector Python client library documentation

Overview

This page organized into a few sections depending on what you’re trying to do:

• How to's - The comprehensive reference section for every feature, API, and setting. It’s your source for detailed, technical information to support any level of development.
• Concepts - Explanations of foundational ideas and core principles to help you understand the reason behind the product’s features and design.
• Quickstarts - Short, focused guides to get you started with key features or workflows in minutes.
• Tutorials - In-depth walkthroughs that dive deeper into specific use cases or processes. These step-by-step guides help you master essential tasks and workflows.
• Integrations - Guides and resources to help you connect and use the product with popular tools, frameworks, or platforms.
• Benchmarks - Performance comparisons and metrics to demonstrate how the product performs under various scenarios. This helps you understand its efficiency and capabilities.
• Best practices - Recommendations and guidelines for maximizing effectiveness and avoiding common pitfalls. This section equips you to use the product effectively and efficiently.

How to's

1. Create a vector index: Redis maintains a secondary index over your data with a defined schema (including vector fields and metadata). Redis supports FLAT and HNSW vector index types.
2. Store and update vectors: Redis stores vectors and metadata in hashes or JSON objects.
3. Search with vectors: Redis supports several advanced querying strategies with vector fields including k-nearest neighbor (KNN), vector range queries, and metadata filters.
4. Configure vector queries at runtime. Select the best filter mode to optimize query execution.

Concepts

Learn to perform vector search and use gateways and semantic caching in your AI/ML projects.

Search	LLM memory	Semantic caching	Semantic routing	AI Gateways
Vector search guide	Store memory for LLMs	Semantic caching for faster, smarter LLM apps	Semantic routing chooses the best tool	Deploy an enhanced gateway with Redis

Quickstarts

Quickstarts or recipes are useful when you are trying to build specific functionality. For example, you might want to do RAG with LangChain or set up LLM memory for your AI agent. Get started with the following Redis Python notebooks.

• The place to start if you are brand new to Redis

Hybrid and vector search

Vector search retrieves results based on the similarity of high-dimensional numerical embeddings, while hybrid search combines this with traditional keyword or metadata-based filtering for more comprehensive results.

• Implementing hybrid search with Redis
• Vector search with Redis Python client
• Vector search with Redis Vector Library
• Shows how to convert a float 32 index to float16 or integer data types

RAG

Retrieval Augmented Generation (aka RAG) is a technique to enhance the ability of an LLM to respond to user queries. The retrieval part of RAG is supported by a vector database, which can return semantically relevant results to a user’s query, serving as contextual information to augment the generative capabilities of an LLM.

• RAG from scratch with the Redis Vector Library
• RAG using Redis and LangChain
• RAG using Redis and LlamaIndex
• Advanced RAG with redisvl
• RAG using Redis and Nvidia
• Utilize RAGAS framework to evaluate RAG performance
• Vector search with Azure
• RAG with Spring AI
• RAG with Vertex AI
• Notebook for additional tips and techniques to improve RAG quality
• Implement a simple RBAC policy with vector search using Redis

Agents

AI agents can act autonomously to plan and execute tasks for the user.

• Notebook to get started with LangGraph and agents
• Build a collaborative movie recommendation system using Redis for data storage, CrewAI for agent-based task execution, and LangGraph for workflow management.
• Full-Featured Agent Architecture

LLM memory

LLMs are stateless. To maintain context within a conversation chat sessions must be stored and resent to the LLM. Redis manages the storage and retrieval of chat sessions to maintain context and conversational relevance.

• LLM session manager with semantic similarity
• Handle multiple simultaneous chats with one instance

Semantic caching

An estimated 31% of LLM queries are potentially redundant. Redis enables semantic caching to help cut down on LLM costs quickly.

• Build a semantic cache using the Doc2Cache framework and Llama3.1
• Build a semantic cache with Redis and Google Gemini
• Optimize semantic cache threshold with RedisVL

Semantic routing

Routing is a simple and effective way of preventing misuses with your AI application or for creating branching logic between data sources etc.

• Simple examples of how to build an allow/block list router in addition to a multi-topic router
• Use RouterThresholdOptimizer from redisvl to setup best router config

Computer vision

Build a facial recognition system using the Facenet embedding model and RedisVL.

• Facial recognition

Recommendation systems

• Intro content filtering example with redisvl
• Intro collaborative filtering example with redisvl
• Intro deep learning two tower example with redisvl

Feature store

• Credit scoring system using Feast with Redis as the online store

Tutorials

Need a deeper-dive through different use cases and topics?

RAG

• Agentic RAG - A tutorial focused on agentic RAG with LlamaIndex and Amazon Bedrock
• RAG on Vertex AI - A RAG tutorial featuring Redis with Vertex AI
• RAG workbench - A development playground for exploring RAG techniques with Redis
• ArXiv Chat - Streamlit demo of RAG over ArXiv documents with Redis & OpenAI

Recommendations and search

• Recommendation systems w/ NVIDIA Merlin & Redis - Three examples, each escalating in complexity, showcasing the process of building a realtime recsys with NVIDIA and Redis
• Redis product search - Build a real-time product search engine using features like full-text search, vector similarity, and real-time data updates
• ArXiv Search - Full stack implementation of Redis with React FE

Ecosystem integrations

• Amazon Bedrock setup guide
• LangChain Redis Package: Smarter AI apps with advanced vector storage and faster caching
• LlamaIndex integration for Redis as a vector store
• Redis Cloud available on Vercel
• Create a Redis Cloud database with the Vercel integration
• Building a RAG application with Redis and Spring AI
• Deploy GenAI apps faster with Redis and NVIDIA NIM
• Building LLM Applications with Kernel Memory and Redis
• DocArray integration of Redis as a vector database by Jina AI
• Semantic Kernel: A popular library by Microsoft to integrate LLMs with plugins
• LiteLLM integration

Benchmarks

See how we stack up against the competition.

• Redis vector benchmark results
• 1 billion vectors

Best practices

See how leaders in the industry are building their RAG apps.

• Advanced RAG example
• Get better RAG responses with Ragas