E

embeddings

VDB vector database bindings for Kit — store and search high-dimensional vector embeddings

Lightweight vector embeddings store for RAG applications

Multi-source RAG pipeline with hybrid vector + keyword retrieval, LLM-powered concept knowledge graph, adaptive search weighting, and evaluation framework.

Content Orchestrator is an AI-powered system that streamlines the creation, optimization, and management of content for various purposes, such as blog posts, articles, and advertisements. By leveraging advanced natural language processing techniques and machine learning algorithms, it enhances the efficiency and effectiveness of content creation and distribution. The system employs a network of specialized AI agents that collaborate to analyze, label, and optimize content for specific target audiences and objectives, with a strong emphasis on creating advertiser-friendly content.

Remin is a local-first semantic search engine for personal notes. It combines embeddings, ANN vector indexing (HNSW), and reranking models to retrieve information based on intent rather than keywords — fully running on-device for privacy.

Built with Rust, DuckDB (VSS), and modern embedding models.

Project for collecting requirements from feature teams interested in semantic search and RAG-powered features.

Terminal embedding client for Hugging Face's hosted embedding models written in Go

Euclidean Distance or Cosine Similarity using CSV files as vectors embedding DBs - written in Go

The movie-service is a Spring Boot RESTful API that allows consumers to locate a list of appropriate movies based upon a provided mood. The service performs a semantic search on a collection of movies by their plot descriptions, via the use of MongoDB Atlas.

A simple Python program to generate (lowercase) embeddings, from someone (me) who really does not have much experience using Python.

Feature extractor to build an XML file with the required features for running ReelOut with the MSCoco Imageset.