[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
change workflow
yichuan5200309103200692bbf7a25e
diff --git a/.github/workflows/release-manual.yml b/.github/workflows/release-manual.ymlindex 21dfc64..e52d5c0 100644--- a/.github/workflows/release-manual.yml+++ b/.github/workflows/release-manual.yml@@ -57,7 +57,7 @@ jobs:needs: update-versionuses: ./.github/workflows/build-reusable.ymlwith:- ref: ${{ needs.update-version.outputs.commit-sha }}+ ref: 'main'publish:name: Publish and Release@@ -70,7 +70,7 @@ jobs:steps:- uses: actions/checkout@v4with:- ref: ${{ needs.update-version.outputs.commit-sha }}+ ref: 'main'- name: Download all artifactsuses: actions/download-artifact@v4diff --git a/README.md b/README.mdindex 4e05e62..aced200 100755--- a/README.md+++ b/README.md@@ -195,7 +195,7 @@ Once the index is built, you can ask questions like:- "Show me emails about travel expenses"</details>-### 🔍 Time Machine for the Web: RAG Your Entire Google Browser History!+### 🔍 Time Machine for the Web: RAG Your Entire Chrome Browser History!<p align="center"><img src="videos/google_clear.gif" alt="LEANN Browser History Search Demo" width="600">diff --git a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.pyindex a61a169..68fc8f8 100644--- a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py+++ b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py@@ -48,6 +48,10 @@ class HNSWBuilder(LeannBackendBuilderInterface):self.efConstruction = self.build_params.setdefault("efConstruction", 200)self.distance_metric = self.build_params.setdefault("distance_metric", "mips")self.dimensions = self.build_params.get("dimensions")+ if not self.is_recompute:+ if self.is_compact:+ # TODO: support this case @andy+ raise ValueError("is_recompute is False, but is_compact is True. This is not compatible now. change is compact to False and you can use the original HNSW index.")def build(self, data: np.ndarray, ids: List[str], index_path: str, **kwargs):from . import faiss # type: ignore