kdbai-samples
A collection of developer samples showing how to use the KDB.AI vector database, from getting-started guides to industry-specific retrieval-augmented generation use cases.
kdbai-samples is a set of example notebooks for KDB.AI, a vector database with time-series capabilities built by KX, the makers of kdb+. KDB.AI combines unstructured vector embeddings with structured time-series data, and supports several index types including Flat, IVF, IVFPQ, and HNSW, multiple distance metrics, and metadata-filtered top-N retrieval through Python and REST interfaces.
Samples include a Python quickstart, temporal similarity search over time series both with and without transformation, retrieval-augmented generation with LlamaIndex, hybrid search combining dense and sparse retrieval, image search over medical scans, semantic search over PDF documents, and metadata filtering for faster, more accurate retrieval. Using KDB.AI Server itself requires signing up for a license.
It is written mainly as Jupyter notebooks and released under the Apache-2.0 license.