[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: smaller warmup id
Andy Leebaa60b40d1bb
diff --git a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.py b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.pyindex df45be8..06a29bb 100644--- a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.py+++ b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.py@@ -465,7 +465,7 @@ def create_hnsw_embedding_server("""Perform client-side warmup"""time.sleep(2)print(f"Performing client-side warmup with model {model_name}...")- sample_ids = ["1", "2", "3", "4", "5"]+ sample_ids = ["0", "1", "2", "3", "4"]try:context = zmq.Context()