OctaneDB - Lightweight & Fast Vector Database OctaneDB is a lightweight, high-performance Python vector database library that provides 10x faster performance than existing solutions like Pinecone, ChromaDB, and Qdrant. Built with modern Python and optimized algorithms, it's perfect for AI/ML applications requiring fast similarity search. โจ Key Features ๐ Performance 10x faster than existing vector databases than existing vector databases Sub-millisecond query response times query response times 3,000+ vectors/second insertion rate insertion rate Optimized memory usage with HDF5 compression ๐ง Advanced Indexing HNSW (Hierarchical Navigable Small World) for ultra-fast approximate search for ultra-fast approximate search FlatIndex for exact similarity search for exact similarity search Configurable parameters for performance tuning for performance tuning Automatic index optimization ๐ Text Embedding Support ๐ ChromaDB-compatible API for easy migration for easy migration Automatic text-to-vector conversion using sentence-transformers using sentence-transformers Multiple embedding models (all-MiniLM-L6-v2, all-mpnet-base-v2, etc.) (all-MiniLM-L6-v2, all-mpnet-base-v2, etc.) GPU acceleration support (CUDA) support (CUDA) Batch processing for improved performance ๐พ Flexible Storage In-memory for maximum speed for maximum speed Persistent file-based storage file-based storage Hybrid mode for best of both worlds mode for best of both worlds HDF5 format for efficient compression ๐ Powerful Search Multiple distance metrics : Cosine, Euclidean, Dot Product, Manhattan, Chebyshev, Jaccard : Cosine, Euclidean, Dot Product, Manhattan, Chebyshev, Jaccard Advanced metadata filtering with logical operators with logical operators Batch search operations operations Text-based search with automatic embedding ๐ ๏ธ Developer Experience Simple, intuitive API similar to ChromaDB similar to ChromaDB Comprehensive documentation and examples and examples Type hints throughout throughout Extensive ...
First seen: 2025-08-23 08:33
Last seen: 2025-08-23 10:35