The Lindorm vector engine is used to store, index, and retrieve large amounts of vector data. It supports multiple indexing algorithms, distance functions, and a variety of integrated data retrieval methods. The Lindorm vector engine provides the capabilities to perform full-text and vector retrievals in an integrated manner, which is required in Retrieval-Augmented Generation (RAG) to improve the accuracy of large models. Therefore, the Lindorm vector engine is suitable for AI-related services such as personalized recommendation, Natural Language Processing (NLP), and intelligent Q&A.
Key features
Low cost and high performance
Offers cost-effective storage based on disk indexing algorithms and the shared storage architecture. The engine supports tens of billions of vectors for a single index and a query latency within tens of milliseconds.
Ease of use
Supports real-time data updates and access over protocols such as OpenSearch, SQL, and REST.
Multimodal capabilities
Supports fusion retrieval based on scalars, full text, and vectors and provides various data query capabilities.
One-stop solution
Integrates with built-in embedding inference capabilities provided by the AI engine and provides the basic capabilities required by RAG systems based on large models.
