Build real-time apps that exceed expectations for responsiveness and include complex processing with low latency.
The faster the app, the better the user experience. Happy users means increased revenue. The speed and unparalleled flexibility of Redis allows businesses to adapt to constantly shifting technology needs, especially in the AI space. Redis Vector Search provides a foundation for AI applications ranging from recommendation systems to document chat.
Ground chatbots in your data using Retrieval Augmented Generation (RAG) to enhance the quality of LLM responses.
Semantic caching
Identify and retrieve cached LLM outputs to reduce response times and the number of requests to your LLM provider, which saves time and money.
Recommendation systems
Power recommendation engines with fresh, relevant suggestions at low-latency, and point your users to the products they’re most likely to buy.
Document Search
Make it easier to discover and retrieve information across documents and knowledge bases, using natural language and semantic search.
Why Redis Vector Search?
Fast
Redis’s superior speed and throughput improves the user experience and ROI, allowing for additional enrichments within the required response window.
Flexible
Tech stacks constantly evolve as Gen AI advances. Rich support for integrations and diverse data structures allows devs to bring apps to production quickly across multi-cloud and hybrid deployments.
Trusted
Reliable, secure systems reduce risk, accelerating adoption and innovation for companies and enabling production scale and high availability across regions.
Simple
Get started with easy-to-use code that gets you up and running quickly. See for yourself why Redis is the “Most Loved Database”.
Popular resources
Webinar
Apr.24.2024
Agentic RAG: Semantic caching with Redis and LlamaIndex
With Redis and LlamaIndex, customers can build faster, more accurate chatbots at scale while optimizing cost. Join this session to learn the latest best practices.
The Future of RAG: Exploring Advanced LLM Architectures with LangChain and Redis
See LangChain’s role in facilitating RAG-based applications, advanced agent orchestration techniques, and the critical role of Redis Enterprise in real-time applications.
Introducing the Redis Vector Library for Enhancing GenAI Development
Redis Vector Library simplifies the developer experience of our vector offering by providing a streamlined client experience that enhances Generative AI application development.
We’re using Redis Cloud for everything persistent in OpenGPTs, including as a vector store for retrieval and a database to store messages and agent configurations. The fact that you can do all of those in one database from Redis is really appealing.
Harrison Chase Co-Founder and CEO
The best of VS
Vector indexing algorithms
We manage vectors in an index data structure with intelligent similarity search that balances search speed and quality. Choose from two popular techniques, FLAT (a brute force approach) and HNSW (a faster approximate approach).
Powerful hybrid filtering
You get the best of both worlds and enhance your workflows by combining the power of vector search with more traditional numeric, text, and tag filters. Incorporate more business logic into queries and simplify client app codes.
Vector range queries
While traditional vector search finds the “top K” most similar vectors, we extend the relevant data discovered through a predefined similarity range that provides a more flexible search experience.
Vector search distance metrics
We use a distance metric to measure the similarity between two vectors. Choose from three popular metrics – Euclidean, Inner Product, and Cosine Similarity – used to calculate how “close” or “far apart” two vectors are.
Real-time updates
We can keep your search and recommendation systems fresh, relevant, and cost effective with updates, insertions, deletions in your search index as your dataset changes over time.
FAQs
What are vector databases?
Vector databases store unstructured data in the form of vectors that capture the meaning and context of natural language processing and computer vision. They are designed to efficiently handle the storage and retrieval of these dense numerical vectors through specialized data structures and indexing techniques, such as hierarchical navigable small world (HNSW) and product quantization. These databases enable users to find vectors that are most similar to a given query vector based on a chosen distance metric, such as Euclidean distance, cosine similarity, or dot product.
What are vector embeddings?
Vector embeddings are numerical representations of unstructured data, such as text, images, or audio, in the form of vectors. These embeddings capture the semantic similarity of objects by mapping them to points in a vector space, where similar objects are represented by vectors that are close to each other.
What is vector indexing?
Vector indexing is a technique used to organize and retrieve data based on vector representations. Instead of storing data in traditional tabular or document formats, vector indices represent data objects as vectors in a multi-dimensional space.
What are distance metrics?
In the context of a vector database, a distance metric refers to a mathematical function that takes two vectors as input and calculates a distance value representing their similarity or dissimilarity. We use three distance measures to gauge the similarity of vectors. Selecting an effective distance measure improves classification and clustering performance.
What are Large Language Models (LLMs)?
Large language models (LLMs) are advanced deep-learning models that have been developed to process and analyze human languages. An LLM operates as a highly potent deep-learning model with the capability to comprehend and generate text similar to humans. At its core, this model utilizes a large-scale transformer model to achieve its impressive performance across fields and apps.
