Framework for evaluating and improving agents

A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

A Skill Library for Automated Machine Learning

A library for efficient similarity search and clustering of dense vectors.

🌟 Wiki of OI / ICPC for everyone. （某大型游戏线上攻略，内含炫酷算术魔法）

🚀 Efficient implementations for emerging model architectures

Experimental Code for "Unleashing Graph Partitioning for Large-Scale Nearest Neighbor Search"

Robust tree-based learned vector index with query-aware repartitioning

Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

VLDB 2024 paper repo. RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search

Comprehensive tools and frameworks for developing foundation models tailored to recommendation systems.

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 …

Implementation of DeepDB: Learn from Data, not from Queries!

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/

Fork of PilotScope's fork. PilotScope is a middleware to bridge the gaps of deploying AI4DB (Artificial Intelligence for Databases) algorithms into actual database systems.

Header-only C++/python library for fast approximate nearest neighbors