txtai supports a number of approximate nearest neighbor (ANN) libraries for vector storage. This includes Faiss, Hnswlib, Annoy, NumPy and PyTorch. Custom implementations can also be added.

The default ANN for txtai is Faiss. Faiss has by far the largest array of configurable options in building an ANN index. This article will cover quantization and different approaches that are possible along with the tradeoffs.

Install dependencies

Install txtai and all dependencies.

# Install txtai
pip install …

ann approximate nearest neighbor array article building faiss index libraries machinelearning nlp numpy python pytorch quantization storage vector