Kinetica Delivers Real-Time Vector Similarity Search
Retrieved on:
Wednesday, March 20, 2024
Cloud, Synthetic media, ANN, OLAP, Gen, Algorithm, GPU, SQL, General partnership, RAG, SAN, Motion, Anomaly, LLM, Architecture, RAFT, Acceleration, Index, Language, NVIDIA, ANSI, Generative, Weather, Cryptocurrency
SAN JOSE, Calif., March 20, 2024 (GLOBE NEWSWIRE) -- Kinetica, the real-time GPU-accelerated database for analytics and generative AI, today unveiled at NVIDIA GTC the industry’s only real-time vector similarity search engine that can ingest vector embeddings 5X faster than the previous market leader, based on the popular VectorDBBench benchmark. Under the hood Kinetica uses NVIDIA RAPIDS RAFT to harness the power of the GPU for vector similarity search. With Kinetica’s best-in-class combined data and query latency for vector embedding pipelines, large language models (LLM) can immediately augment their results with new information via embeddings as soon as they are generated, without delays at scale.
Key Points:
- Under the hood Kinetica uses NVIDIA RAPIDS RAFT to harness the power of the GPU for vector similarity search.
- High performance vector similarity search at speed and scale - Kinetica vectorization enables vector similarity search (exact nearest neighbor) at speed and scale even without an index.
- Hybrid vector search combines similarity search with time-series, spatial, graph & OLAP through SQL - Build more powerful Generative AI applications by combining vector similarity search with filters, joins, aggregations, etc.
- “By taking advantage of NVIDIA RAPIDS vector search, Kinetica can offer higher throughput, lower latency and faster index builds for Gen AI applications.”
Kinetica’s vector similarity search is now available in Kinetica 7.2 for users of Kinetica Cloud Dedicated, Developer Edition, and Kinetica Enterprise.