ivf

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

A tiny approximate K-Nearest Neighbour library in Python based on Fast Product Quantization and IVF

Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization

Open Fertility is an open-source project dedicated to advancing fertility analysis and prediction through machine learning.

A fully dynamic approximate nearest neighbor index built on Inverted File Index

A web application for predicting the chance of an IVF/ICSI cycle yielding a D5 embryo suitable for transfer or freezing.

Software-as-a-Medical-Device research prototype for AI-assisted intracytoplasmic sperm injection (ICSI). Two-stage YOLOv8 pipeline (multi-class detection plus polygon segmentation) to support sperm selection, immobilization, and injection. Django web app with live and recorded video annotation.

Research code for PloidyNet, a multimodal neural network for non-invasive embryo ploidy prediction.

Hybrid retrieval from first principles: BM25, exact and IVF vector indexes, and reciprocal rank fusion, with ANN recall measured against exact search. 57 tests.

🔥 VectorForge - Lightweight High-Performance Vector Index Engine | Pure Python, Zero Dependencies, HNSW/IVF/LSH/BruteForce, TUI Dashboard, Multi-Format I/O, Cross-Platform

Search large vector datasets with high speed and low memory usage using the TurboQuant algorithm.