Download
LEANN is an open source system designed to enable retrieval-augmented generation (RAG) and semantic search across personal data while running entirely on local devices. It focuses on dramatically reducing the storage overhead typically required for vector search and embedding indexes, enabling efficient large-scale knowledge retrieval on consumer hardware. LEANN introduces a storage-efficient approximate nearest neighbor index combined with on-the-fly embedding recomputation to avoid storing large embedding vectors. By recomputing embeddings during queries and using compact graph-based indexing structures, LEANN can maintain high search accuracy while minimizing disk usage. It aims to act as a unified personal knowledge layer that connects different types of data such as documents, code, images, and other local files into a searchable context for language models.
Features
- Storage-efficient approximate nearest neighbor index for semantic search
- On-the-fly embedding recomputation to minimize vector storage overhead
- Graph pruning techniques that reduce index size while preserving accuracy
- Two-level coarse-to-fine search for faster query processing
- Support for indexing many file types including code, documents, and data formats
- Pluggable backends such as DiskANN and HNSW/FAISS with a unified interface
Project Samples
