Definition
An inverted file index (IVF) is a partitioning scheme that makes vector search scale to billions of items. At build time, a coarse quantizer, usually k-means, groups all vectors into a fixed number of clusters or cells (the count is called nlist). Each cell holds an inverted list: the IDs of every vector assigned to that centroid. Rather than comparing a query against every vector, IVF compares it only against vectors in the handful of cells whose centroids are closest.
The nprobe trade-off
At search time you set nprobe, the number of nearest cells to actually scan. Probe one cell and the search is blazing fast but may miss neighbours that landed just across a cell boundary; probe more cells and recall climbs at the cost of latency. A common rule of thumb is to probe enough cells to cover a few percent of the dataset, which typically recovers high recall while still skipping the vast majority of vectors. Tuning nprobe is the main recall-versus-speed dial for a self-hosted index.
IVF plus product quantization
IVF only narrows which vectors to examine; it does not shrink them. In practice it is combined with compression: the popular IVF-PQ index uses IVF to pick candidate cells and product quantization to store the vectors inside those cells compactly. This pairing is how libraries like Faiss fit large corpora into modest RAM on hardware you own.
To go deeper on the compression half of that pairing, see our product quantization entry, and compare IVF's cell-based pruning with the graph-based approach described under vector quantization for choosing the right index for your own retrieval stack.
In Simple Terms
An inverted file index (IVF) is a partitioning scheme that makes vector search scale to billions of items. At build time, a coarse quantizer, usually…