Lightweight Nearest Neighbors with Flexible Backends
-
Updated
Oct 5, 2025 - Python
Lightweight Nearest Neighbors with Flexible Backends
The Python package of differential nearest neighbors regression (DNNR): Raising KNN-regression to levels of gradient boosting method. Build on-top of Numpy, Scikit-Learn, and Annoy.
Advertisement search interface based on image similarity.
sends roblox friend requests
Semnet efficiently constructs graph structures from embeddings, enabling graph-based analysis and operations over large collections embedded texts, images, and more.
🏞 A content-based image retrieval (CBIR) system
Image Recommendation via similarity retrieval through deep learning
A Flask app with a search engine for GoodReads books, featuring simple and neural search capabilities using Whoosh, Annoy and HuggingFace transformers.
query server for approximate nearest neighbors
A unified interface for vector databases
A simple tool to retrieve relevant Wikipedia passages
Project purpose is to index as much as possible fake faces datasets and allow people easily search for similar faces by providing source face image.
Recommendation algorithms
Multi-Modal Search over fashion datasets. Information Retrieval Tasks optimised using Spotify's Annoy, using text embeddings over captions and words generated from image via classifiers. Experimentation and Optimisation of hyper-parameters
🎵 Utilized the Spark engine to build and evaluate a music recommender system and accelerated query search from utilizing spatial data structure by using the Annoy
Lex Fridman Podcast Guests Q&A: You’re answered by different opinions using Large Language Models 🎙️🔍💡
Official Indra Python Client
Implementation and analysis of various algorithms, libraries and systems, distributed and not, for Approximate Nearest Neighbors searches
Moteur de recherche intelligent
Add a description, image, and links to the annoy topic page so that developers can more easily learn about it.
To associate your repository with the annoy topic, visit your repo's landing page and select "manage topics."