Redis announces two new offerings for GenAI app developers

Company introduces LangCache, a fully managed semantic caching service that integrates LLM response caching in AI apps, and vector sets, a new native data type specialized for vector similarity search

SAN FRANCISCO, April 08, 2025 (GLOBE NEWSWIRE) -- Redis, the world’s fastest data platform, today announced LangCache, a fully-managed semantic caching service for AI apps and agents, and vector sets, a new native data type

for Redis that allows developers to easily access and work with vectors and use them in more composable and scalable ways. The company also launched several other tools and features that provide the comprehensive data architecture developers need to build faster, more accurate GenAI apps and agents.

LangCache allows developers to seamlessly integrate Redis-based LLM response caching into applications. It significantly reduces costly calls to LLMs, storing and reusing prompts and responses to minimize cost, improve prompt accuracy, and deliver faster AI experiences. LangCache lets developers:

• Minimize costly calls to LLMs and speed up GenAI apps by taking user queries and returning relevant prompts that have been previously stored in Redis.
• Improve accuracy of LLM cache retrieval using custom fine-tuned model and configurable search criteria, including search algorithm and threshold distance.
• Generate embeddings through their preferred model provider, eliminating the need to separately manage models, API keys, and model-specific variables.
• Govern responses so that apps only return data that's approved for the current user, eliminating the need for separate security protocols as part of your app.

Redis also introduced vector sets, a new native data type in Redis written by Redis’ creator, Salvatore Sanfilippo. Vector sets allow developers to easily access and work with vectors and use them in more composable and scalable ways. Vector sets complement Redis’ existing vector similarity search, offering a lower-level way to work with vectors.

Vector sets take inspiration from sorted sets, one of Redis's fundamental data types known for its efficiency in handling ordered collections. The new data type extends this concept by allowing the storage and querying of high-dimensional vector embeddings, which are crucial for various AI and machine learning applications.

Vector sets also implement some exciting additional capabilities, including:

• Quantization: In a vector set, the vectors are quantized by default to 8 bit values. However, this can be modified to no quantization or binary quantization when adding the first element.
• Dimensionality reduction: The number of dimensions in a vector can be reduced by random projection by specifying the option and the number of dimensions.
• Filtering: Each element of the vector set can be associated with a set of attributes specified as a JSON blob via the VADD or VSETATTR command. This allows the ability to filter for a subset of elements using VSIM that are verified by the expression.
• Multi-threading: Vector sets speeds up vector similarity requests by splitting up the work across threads to provide even faster results.

Vector sets will be available in beta in Redis 8, coming May 1.

“LangCache and vector sets give developers a simple way to handle the complex data needs that come with building agent-based AI apps," said Rowan Trollope, CEO of Redis. “Just as traditional apps need a cache that stores frequently accessed data, agents need fast access to the data that helps them make decisions to complete their tasks. LangCache speeds up responses and provides more accurate answers, while vector sets give them a simple, elegant way to store and retrieve the data.”

Other new tools and features for AI developers include:

• Redis Agent Memory Server. An open source service that provides memory management for AI apps and agents. Users can manage short-term and long-term memory for AI conversations, with features like automatic topic extraction, entity recognition, and context summarization.
• Hybrid search. Redis now combines full-text search with vector similarity search to deliver more relevant results.
• Quantization. Redis offers quantization and supports int8 as an even more memory-efficient vector type. Quantization compresses float embeddings to 8-bit integers, enabling the int8 embeddings to reduce memory usage and cost by 75% and improve search speed by 30%, all while maintaining 99.99% of the original search accuracy.
• LangGraph integrations. A portfolio of native integrations for LangGraph specifically designed for agent architectures and agentic apps. Use Redis to build a LangGraph agent’s short-term memory via checkpointers, long-term memory via Store, vector database, LLM cache, and rate limiting.

New Redis Cloud features help ship GenAI apps fast
GenAI requires a wide array of data types, so developers need a platform that can handle it all fast, at scale, multi-cloud or hybrid. New features in Redis Cloud ensure devs can easily build and deliver real-time GenAI apps faster while optimizing total cost of ownership.

• Redis Data Integration (RDI): Now in private previewRDI on Cloud – Redis’ change data capture offering – effortlessly and automatically syncs data between cache and database to deliver data consistency in milliseconds.
• Redis Flex on Cloud Essentials: Available in public preview, Redis Flex is Redis rearchitected to natively span across both RAM and SSD, delivering the fastest speeds from the first byte to the largest of dataset sizes. Developers can store up to 5X more data in their app and database for the same price as before.
• Redis Insight on Cloud: Developers can now view, update, query, and search the data in Redis directly from their browser. Redis Insight gives access to the Redis developer environment, including the Workbench and tutorials, and new query autocompletion which pulls in and suggests schema, index, and key names from Redis data in real-time to allow developers to write queries faster and easier.
  

Get started with all these new features on Redis Cloud with a free trial on redis.io/try-free/ or reach out to your account manager.

About Redis
Redis is the world’s fastest data platform. From its open source origins in 2011 to becoming the #1 cited brand for caching solutions, Redis has helped more than 10,000 customers build, scale, and deploy the apps our world runs on. With cloud and on-prem databases for caching, vector search, and more, Redis helps digital businesses set a new standard for app speed. Located in San Francisco, Austin, London, and Tel Aviv, Redis is internationally recognized as the leader in building fast apps fast. Learn more at redis.io.