Skip to content

armgit / LEANN

Public Imported from GitHub
0

[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.

upd readme

yichuan5200309103202a96d05b21a7
diff --git a/README.md b/README.md
index 3624c81..8f62ca8 100755
--- a/README.md
+++ b/README.md
@@ -389,15 +389,7 @@ python examples/compare_faiss_vs_leann.py
Same dataset, same hardware, same embedding model. LEANN just works better.
-## Reproduce Our Results
-
-```bash
-uv pip install -e ".[dev]" # Install dev dependencies
-python examples/run_evaluation.py data/indices/dpr/dpr_diskann # DPR dataset
-python examples/run_evaluation.py data/indices/rpj_wiki/rpj_wiki.index # Wikipedia
-```
-The evaluation script downloads data automatically on first run.
### Storage Usage Comparison
@@ -424,6 +416,15 @@ The evaluation script downloads data automatically on first run.
*Benchmarks run on Apple M3 Pro 36 GB*
+## Reproduce Our Results
+
+```bash
+uv pip install -e ".[dev]" # Install dev dependencies
+python examples/run_evaluation.py data/indices/dpr/dpr_diskann # DPR dataset
+python examples/run_evaluation.py data/indices/rpj_wiki/rpj_wiki.index # Wikipedia
+```
+
+The evaluation script downloads data automatically on first run. The last three results were tested with partial personal data, and you can reproduce them with your own data!
## 🔬 Paper
If you find Leann useful, please cite:
diff --git a/packages/leann-backend-diskann/third_party/DiskANN b/packages/leann-backend-diskann/third_party/DiskANN
index 25339b0..af2a264 160000
--- a/packages/leann-backend-diskann/third_party/DiskANN
+++ b/packages/leann-backend-diskann/third_party/DiskANN
@@ -1 +1 @@
-Subproject commit 25339b03413b5067c25b6092ea3e0f77ef8515c8
+Subproject commit af2a26481e65232b57b82d96e68833cdee9f7635