Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

The Virtual Feature Store. Turn your existing data infrastructure into a feature store.

Epsilla is a high performance Vector Database Management System

A tiny embedding database in pure Rust.

Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.

A ChatGPT integration library for .NET, supporting both OpenAI and Azure OpenAI Service

A curated list of awesome works related to high dimensional structure/vector search & database

Vectory provides a collection of tools to track and compare embedding versions.

High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡

Vector Database implemented in Golang with support for full-text and vector search as well as fault tolerance via Raft.

Using embeddings to create memory.

AI song recommendations based on the feel of a song

A command-line tool to index and perform hybrid semantic & lexical search over text files

Building representation in the vector space

LegalAI is a passion project which explores and simplifies the complexities of obtaining legal information using LLMs.

The repository is aimed at providing practical examples and resources for developers and researchers interested in applying LM and GPT models to real-world NLP problems.

A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts.

The Real Time Social Media Content Retrieval System fetches real-time LinkedIn posts based on user queries, offering multiple post retrieval and customization options. Although initially focused on LinkedIn, it can be expanded to incorporate other social media platforms, facilitating cross-channel post similarity searches.

A simple python tool for embedding comparison

RoleRadar turns free-form requests like “Data Analyst roles in New York with SQL experience.” into structured filters and semantic-vector queries, delivering spot-on matches in seconds.