🚀 Build scalable AI applications with Pathway's AI Pipelines for accurate retrieval-augmented generation and enterprise search.

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

Vector Index Benchmark for Embeddings (VIBE) is an extensible benchmark for approximate nearest neighbor search methods, or vector indexes, using modern embedding datasets.

Approximate Nearest Neighbor search using reduced-rank regression, with extremely fast queries, tiny memory usage, and rapid indexing on modern vector embeddings.

A Rust binding for the VSAG -- vector indexing and search library.

KNN Search Algorithm Comparison – This project compares the performance of different K-Nearest Neighbors (KNN) search algorithms across various dataset sizes and dimensions.

Streamlit app for a Blender Helper Bot using a pre-built TiDB vector store

Simple, High Quality, RAG application using TiDB vector store

AI-powered Dropbox search tool for private documents

A prototype for visualizing and exploring vector document indexes

Roy: A lightweight, model-agnostic framework for crafting advanced multi-agent systems using large language models.

Semantic Desktop Search - search for answers not the file names