Redis for AI and search on Docs

Notebooks collection

Mon, 01 Jan 0001 00:00:00 +0000

Notebook	Category	Description
The place to start if you are brand new to Redis	Introduction	Great for Redis beginners looking for a guided Colab experience.	Open in Colab
Implementing hybrid search with Redis	Hybrid and Vector Search	Combines vector similarity with keyword filters.	Open in Colab
Vector search with Redis Python client	Hybrid and Vector Search	Demonstrates pure vector search using the Redis Python client.	Open in Colab
Vector search with Redis Vector Library	Hybrid and Vector Search	Uses RedisVL for advanced vector indexing and querying.	Open in Colab
Shows how to convert a float32 index to float16 or integer data types	Hybrid and Vector Search	Demonstrates data type optimization for vector indices.	Open in Colab
RAG from scratch with Redis Vector Library	RAG	Basic RAG implementation using RedisVL.	Open in Colab
RAG using Redis and LangChain	RAG	Shows integration between Redis and LangChain for RAG.	Open in Colab
RAG using Redis and LlamaIndex	RAG	Walkthrough of RAG with Redis and LlamaIndex.	Open in Colab
Advanced RAG with RedisVL	RAG	Advanced concepts and techniques using RedisVL.	Open in Colab
RAG using Redis and Nvidia	RAG	NVIDIA + Redis for LLM context retrieval.	Open in Colab
Utilize RAGAS framework to evaluate RAG performance	RAG	Evaluation of RAG apps using the RAGAS framework.	Open in Colab
Implement a simple RBAC policy with vector search using Redis	RAG	Role-based access control implementation for RAG systems.	Open in Colab
LangGraph and agents	Agents	Getting started with agent workflows.	Open in Colab
Movie recommendation system	Agents	Collaborative agent-based movie recommender.	Open in Colab
Full-Featured Agent Architecture	Agents	Comprehensive agent implementation with advanced features.	Open in Colab
Optimize semantic cache threshold with RedisVL	Semantic Cache	Performance optimization for semantic caching systems.	Open in Colab
Simple examples of how to build an allow/block list router in addition to a multi-topic router	Semantic Router	Basic routing patterns and access control mechanisms.	Open in Colab
Use `RouterThresholdOptimizer` from RedisVL to setup best router config	Semantic Router	Router configuration optimization using RedisVL.	Open in Colab
Facial recognition	Computer Vision	Face matching using Facenet and RedisVL.	Open in Colab
Content filtering with RedisVL	Recommendation Systems	Introduction to content-based filtering.	Open in Colab
Collaborative filtering with RedisVL	Recommendation Systems	Intro to collaborative filtering with RedisVL.	Open in Colab
Intro deep learning two tower example with RedisVL	Recommendation Systems	Deep learning approach to recommendation systems.	Open in Colab
Credit scoring system using Feast with Redis as the online store	Feature Store	Feature store implementation for ML model serving.	Open in Colab

Additional resources

Looking for more ways to learn about Redis for AI? Check out our:

Redis AI ecosystem integrations

Mon, 01 Jan 0001 00:00:00 +0000

Redis integrates with a wide range of AI frameworks, platforms, and tools to enhance your AI applications. This page highlights key ecosystem integrations that can help you build more powerful, efficient, and scalable AI solutions with Redis.


Kong AI Gateway & Redis	Unstructured & Redis	Mem0 & Redis
Combine Kong's AI Gateway with Redis for efficient AI request routing, caching, and rate limiting to optimize your AI infrastructure.	Accelerate AI workflows by using Redis to cache document processing results from Unstructured, reducing processing time and costs.	Implement smarter memory management for AI agents with Mem0's integration with Redis, providing persistent, queryable memory for LLMs.
LiteLLM & Redis	LangGraph & Redis	LangChain & Redis
Optimize LLM performance with LiteLLM's Redis caching capabilities, supporting both traditional and semantic caching to reduce costs and latency.	Build smarter AI agents with LangGraph's Redis integration for memory persistence, state management, and multi-agent coordination.	Leverage LangChain's Redis integration for vector storage, memory, and caching to create more capable AI applications with improved performance.
LlamaIndex & Redis	Amazon Bedrock & Redis	NVIDIA NIM & Redis
Use LlamaIndex with Redis as a vector store for efficient document indexing, retrieval, and querying in RAG applications.	Integrate Redis with Amazon Bedrock to enhance your generative AI applications with persistent memory and efficient vector search.	Deploy GenAI applications faster by combining NVIDIA NIM's inference optimization with Redis for vector search, caching, and data management.

Additional integrations

Microsoft Semantic Kernel: Use Redis as a vector store connector with Microsoft's Semantic Kernel framework.
DocArray: Leverage Redis as a document store and vector database with Jina AI's DocArray.
Redis Cloud on Vercel: Deploy and manage Redis databases directly from your Vercel dashboard with the Redis Cloud integration. Refer to the setup guide for more details.
Spring AI & Redis: Build powerful RAG applications by combining Spring AI's framework with Redis for vector storage and retrieval.
Kernel Memory & Redis: Create memory-enabled LLM applications using Microsoft's Kernel Memory with Redis for efficient storage and retrieval.

Getting started

To learn more about using Redis with AI frameworks and tools, check out our:

Redis video tutorial collection

Mon, 01 Jan 0001 00:00:00 +0000

Explore our collection of video tutorials and demonstrations showcasing how Redis powers AI applications. From vector search fundamentals to advanced RAG implementations, these videos provide practical insights and hands-on examples.


Long-Term Memory with LangGraph	Short-Term Memory with LangGraph	What is semantic search?
Learn how to implement long-term memory capabilities in AI agents using LangGraph. This video shows you how to build AI systems that can retain and recall information across extended interactions.	Want your AI agents to remember what users tell them? Short-term memory is the key to natural conversations, and in this tutorial, you'll learn how to implement it with LangGraph.	Traditional search matches words — but what if your AI app could match meaning instead? This video explains how semantic search works and why it's essential for modern AI applications.
What is a semantic cache?	Building a RAG Pipeline from Scratch with RedisVL	What is a vector database?
What if you could skip redundant LLM calls and make your AI app faster, cheaper, and smarter? This video breaks down semantic caching and shows how it can transform your AI applications.	Unlock the Power of Retrieval-Augmented Generation (RAG) with RedisVL. This tutorial will show you how to build a complete RAG pipeline from scratch using Redis as your vector database.	Vector databases have been trending recently as they power modern search, recommendations, and AI-driven applications. Learn what vector databases are and how they work.
Building the future Architecting AI Agents with AWS, LlamaIndex and Redis	Building AI Apps using LangChain	Resources to Learn AI with Redis
The ins and outs of AI agents: understand their role in breaking down tasks into manageable components for better performance. Learn how to architect AI agents using AWS, LlamaIndex, and Redis.	This series of videos dives into the integration between LangChain and Redis to power AI applications that need runtime speed, scalability, and intelligent data management.	This video shows which resources you can use to learn AI with Redis and build powerful AI applications.
What Is RAG? Retrieval-Augmented Generation Explained Simply	Chunking Strategies Explained	What is an embedding model?
Retrieval-Augmented Generation (RAG) is one of the most powerful architectural patterns in GenAI today—combining the strengths of large language models (LLMs) with real-time, external context from your own data. In this session, learn why it matters and how each component—from query rewriting to dense retrieval to semantic chunking—works behind the scenes to power more accurate, grounded, and up-to-date responses.	Are you interested in building LLM applications that actually work? Your chunking strategy makes all the difference. In this video, get a break down of the science of text chunking so your embeddings can start answering the right questions to your users.	Everyone’s talking about embedding models lately—but what do they actually do, and why does it matter? This video breaks it down in simple terms and shows how embeddings power search, recommendations, and AI features behind the scenes.

Additional Resources


LLM Session Management with Redis	A Semantic Cache using LangChain	Similarity Search using Vector Store
Developers building AI applications require a way to store the conversation history between an LLM and a user. This is important to provide context and maintain coherent conversations across sessions.	One common concern of developers building AI applications is how quickly answers from LLMs will be served to their end users, as well as how much it will cost. Learn how to implement semantic caching using LangChain and Redis.	Similarity search is one of the most popular use cases for developers building AI applications. It allows users to perform searches that can find semantically similar content using vector embeddings.
Create a New Database on Redis Cloud	Redis Insight: A Developer's Deep Dive	Redis + Amazon SageMaker for real-time fraud detection demo
Learn how to create a new database on Redis Cloud in this step-by-step tutorial. Perfect for developers getting started with Redis Cloud for their AI and data applications.	This video breaks down Redis Insight and shows developers how to use this powerful tool for database management and development.	See how Redis integrates with Amazon SageMaker to build real-time fraud detection systems. This demo shows practical applications of Redis in machine learning and AI-powered fraud prevention.
Redis + Amazon Bedrock in two minutes
AWS has announced Redis Cloud as one of the few supported vector databases supported for Amazon Bedrock. Learn how to integrate Redis with Amazon Bedrock for your generative AI applications.

Getting Started

Ready to start building AI applications with Redis? Check out our: