[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
chore: apply ruff format
Aakash Suresh347e31f3b233
diff --git a/packages/leann-core/src/leann/embedding_compute.py b/packages/leann-core/src/leann/embedding_compute.pyindex d39e6b6..9e68313 100644--- a/packages/leann-core/src/leann/embedding_compute.py+++ b/packages/leann-core/src/leann/embedding_compute.py@@ -652,9 +652,7 @@ def compute_embeddings_sentence_transformers(# Optional compile on supported devicesif device in ["cuda", "mps"]:try:- hf_model = torch.compile(- hf_model, mode="reduce-overhead", dynamic=True- )+ hf_model = torch.compile(hf_model, mode="reduce-overhead", dynamic=True)logger.info(f"Applied torch.compile to HF model for {model_name} "f"(device={device}, dtype={torch_dtype})"