[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
polish readme
yichuan52003091032091a026f38b8d
diff --git a/README.md b/README.mdindex f7a4e4d..f8881bc 100755--- a/README.md+++ b/README.md@@ -199,7 +199,7 @@ This ensures the generated files are compatible with your system's protobuf libr- **DiskANN**: Microsoft's billion-scale ANN algorithm- **HNSW**: Hierarchical Navigable Small World graphs-- **Coming soon**: ScaNN, Faiss-IVF, NGT+- **Coming soon**: ScaNN, Faiss-IVF, NSG### 📏 Distance Functions@@ -314,24 +314,22 @@ export NCCL_SOCKET_IFNAME=ens5## 📈 Roadmap-### 🎯 Q1 2024+### 🎯 Q2 2025- [X] DiskANN backend with MIPS/L2/Cosine support- [X] HNSW backend integration- [X] Real-time embedding pipeline- [X] Memory-efficient graph pruning-### 🚀 Q2 2024+### 🚀 Q3 2025+-- [ ] Distributed search across multiple nodes-- [ ] ScaNN backend support- [ ] Advanced caching strategies-- [ ] Kubernetes deployment guides+- [ ] GPU-accelerated embedding computation-### 🌟 Q3 2024-- [ ] GPU-accelerated embedding computation-- [ ] Approximate distance functions+### 🌟 Q4 2025+- [ ] Integration with LangChain/LlamaIndex- [ ] Visual similarity search