cuVS - a library for vector search and clustering on the GPU
-
Updated
Oct 2, 2024 - Cuda
cuVS - a library for vector search and clustering on the GPU
Timescale Vector Cookbook. A collection of recipes to build applications with LLMs using PostgreSQL and Timescale Vector.
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
A cloud-native vector database, storage for next generation AI applications
Shotit is a screenshot-to-video search engine tailored for TV & Film, blazing-fast and compute-efficient.
The ultimate brain of Shotit, in charge of task coordination.
The frontend of shotit, with full documentation.
Scripts for reading, extracting, and organizing data from either HTML or PDF documents and prepare them to be converted into embeddings for use in context-augmented LLM queries.
Vector Hub - Library for easy discovery, and consumption of State-of-the-art models to turn data into vectors. (text2vec, image2vec, video2vec, graph2vec, bert, inception, etc)
The README profile of Shotit.
VQLite - Simple and Lightweight Vector Search Engine based on Google ScaNN
vasco: Discover hidden patterns in your Postgres data
Siam-Vector Search uses Siamese networks to improve vector similarity searches, making retrieval-augmented generation (RAG) systems more accurate.
implemented vector similarity algorithms to understand their inner workings, used local embeddding models
Apziva AI Residency Program 2024 -- Project 3
Vector Embedding Server in under 100 lines of code
Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.
AI Github assistant for your repo. Your proactive GitHub bot that auto-detects duplicates using OpenAI embeddings and Supabase magic!
Implementation and analysis of various algorithms, libraries and systems, distributed and not, for Approximate Nearest Neighbors searches
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.
Add a description, image, and links to the vector-similarity topic page so that developers can more easily learn about it.
To associate your repository with the vector-similarity topic, visit your repo's landing page and select "manage topics."