#hybrid search

Infinity's AI-native database is engineered for optimal performance with large language model applications, providing fast and versatile search across multiple data types. It excels in low-latency and high QPS query performance, making it ideal for search, recommendation systems, and content generation. With an intuitive Python API and single-binary deployment, Infinity is easily accessible for AI developers. Explore embedded and client-server modes through documentation and community resources.

The package provides a question-answering system using LLMs with customizable document interactions. It offers features like document parsing enhancement, hybrid and HyDE-enabled search, and embeddings integration for improved retrieval and re-ranking. The system works with multiple document collections, allows for filtering and incremental embedding updates, and is accessible through CLI and web platforms. It also supports multi-querying, experimental APIs, and compatibility with various LLM models, offering flexibility and adaptability.