thustorage/PipeANN
A low-latency, billion-scale, and updatable graph-based vector store on SSD.
Need to quickly find similar items from an extremely large collection of data, even billions of entries, without needing massive amounts of expensive memory? This solution allows you to search through vast datasets stored on SSDs with ultra-low latency. It helps data scientists, machine learning engineers, and researchers perform lightning-fast similarity searches, taking in high-dimensional vector data and providing the closest matching vectors and their identifiers.
102 stars.
Use this if you need to perform high-throughput, low-latency similarity searches on a dataset of millions to billions of vectors that you need to be able to update regularly, all while minimizing expensive in-memory storage.
Not ideal if your dataset is very small, or if your primary concern is an absolute minimum latency where even a millisecond difference is critical and cost is no object for in-memory solutions.
Stars
102
Forks
37
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/thustorage/PipeANN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
MariaDB/server
MariaDB server is a community developed fork of MySQL server. Started by core members of the...
AlayaDB-AI/AlayaLite
AlayaLite – A Fast, Flexible Vector Database for Everyone.
infiniflow/infinity
The AI-native database built for LLM applications, providing incredibly fast hybrid search of...
nnethercott/hannoy
Production-ready KV-backed HNSW implementation in Rust using LMDB
dingodb/dingo
A multi-modal vector database that supports upserts and vector queries using unified SQL...