Implementation of various string similarity and distance algorithms: Levenshtein, Jaro-winkler, n-Gram, Q-Gram, Jaccard index, Longest Common Subsequence edit distance, cosine similarity ...

FAst Lookups of Cosine and Other Nearest Neighbors (based on fast locality-sensitive hashing)

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

Blazing fast framework for fine-tuning similarity learning models

Music recommender using deep learning with Keras and TensorFlow

Generating multiple choice questions from text using Machine Learning.

A .NET port of java-string-similarity

Python package to accelerate the sparse matrix multiplication and top-n similarity selection

Score documents using embedding-vectors dot-product or cosine-similarity with ES Lucene engine

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.

📈This repo contains detailed notes and multiple projects implemented in Python related to AI and Finance. Follow the blog here: https://purvasingh.medium.com

Spark library for generalized K-Means clustering. Supports general Bregman divergences. Suitable for clustering probabilistic data, time series data, high dimensional data, and very large data.

A python project for checking plagiarism of documents based on cosine similarity

A blazing-fast semantic search React component. Match by meaning, not just by letters. Search as you type without waiting (no debounce needed). Rank by cosine similarity.

Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to convert documents into vectors and allows searching for similar documents based on cosine similarity.

Real-Time Face Recognition use SCRFD, ArcFace, ByteTrack and Similarity Measure

Information Retrieval algorithms developed in python. To follow the blog posts, click on the link:

Machine learning based text classification in JavaScript using n-grams and cosine similarity

NNV(No-Named.V) is a vector database that supports Multi-Vector Search, high-performance HNSW, FLAT and quantization, and enables fast searches through sophisticated internal data shard design.

Fast similarity search using DuckDB