[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
fix some readme
yichuan5200309103206f5d5e4a77d1
diff --git a/README.md b/README.mdindex b6580d1..4683957 100755--- a/README.md+++ b/README.md@@ -33,6 +33,8 @@ LEANN achieves this through *graph-based selective recomputation* with *high-deg🪶 **Lightweight:** Graph-based recomputation eliminates heavy embedding storage, while smart graph pruning and CSR format minimize graph storage overhead. Always less storage, less memory usage!+📦 **Portable:** Transfer your entire knowledge base between devices (even with others) with minimal cost - your personal AI memory travels with you.+📈 **Scalability:** Handle messy personal data that would crash traditional vector DBs, easily managing your growing personalized data and agent generated memory!✨ **No Accuracy Loss:** Maintain the same search quality as heavyweight solutions while using 97% less storage.@@ -85,7 +87,7 @@ uv sync-## Quick Start in 30s+## Quick StartOur declarative API makes RAG as easy as writing a config file.[Try in this ipynb file →](demo.ipynb) [](https://colab.research.google.com/github/yichuan-w/LEANN/blob/main/demo.ipynb)@@ -116,7 +118,6 @@ LEANN supports RAG on various data sources including documents (.pdf, .txt, .md)> **Generation Model Setup**->> LEANN supports multiple LLM providers for text generation (OpenAI API, HuggingFace, Ollama).<details>@@ -467,10 +468,10 @@ If you find Leann useful, please cite:## ✨ [Detailed Features →](docs/features.md)-## 🤝 [Contributing →](docs/contributing.md)+## 🤝 [CONTRIBUTING →](docs/CONTRIBUTING.md)-## [FAQ →](docs/faq.md)+## ❓ [FAQ →](docs/faq.md)## 📈 [Roadmap →](docs/roadmap.md)diff --git a/docs/CONTRIBUTING.md b/docs/CONTRIBUTING.mdindex 67331bb..4a37e26 100644--- a/docs/CONTRIBUTING.md+++ b/docs/CONTRIBUTING.md@@ -26,7 +26,7 @@ We welcome contributions! Leann is built by the community, for the community.```3. **Install system dependencies**:-+**macOS:**```bashbrew install llvm libomp boost protobuf zeromq pkgconf@@ -42,7 +42,7 @@ We welcome contributions! Leann is built by the community, for the community.```bash# macOSCC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync-+# Ubuntu/Debianuv sync```@@ -182,7 +182,7 @@ Make sure your code passes these checks locally before pushing!```bashgit commit -m "feat: add new search algorithm"```-+Follow [Conventional Commits](https://www.conventionalcommits.org/):- `feat:` for new features- `fix:` for bug fixesdiff --git a/docs/normalized_embeddings.md b/docs/normalized_embeddings.mdindex d6f285e..46213e5 100644--- a/docs/normalized_embeddings.md+++ b/docs/normalized_embeddings.md@@ -72,4 +72,4 @@ Using the wrong distance metric with normalized embeddings can lead to:- **Incorrect ranking** of search results- **Suboptimal performance** compared to using the correct metric-For more details on why this happens, see our analysis of [OpenAI embeddings with MIPS](../examples/main_cli_example.py).\ No newline at end of file+For more details on why this happens, see our analysis of [OpenAI embeddings with MIPS](../examples/main_cli_example.py).