From 95a653993a9a98c2d527c16627e5c4b83ace43e7 Mon Sep 17 00:00:00 2001 From: yichuan520030910320 Date: Sun, 6 Jul 2025 06:47:20 +0000 Subject: [PATCH] rm useless --- examples/main_cli_example.py | 2 +- packages/leann-core/src/leann/api.py | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/examples/main_cli_example.py b/examples/main_cli_example.py index 262fa94..e89e1ee 100644 --- a/examples/main_cli_example.py +++ b/examples/main_cli_example.py @@ -23,7 +23,7 @@ file_extractor: dict[str, BaseReader] = { ".xlsx": reader, } node_parser = DoclingNodeParser( - chunker=HybridChunker(tokenizer="Qwen/Qwen3-Embedding-4B", max_tokens=64) + chunker=HybridChunker(tokenizer="Qwen/Qwen3-Embedding-4B", max_tokens=128) ) print("Loading documents...") documents = SimpleDirectoryReader( diff --git a/packages/leann-core/src/leann/api.py b/packages/leann-core/src/leann/api.py index ed6af41..48478bf 100644 --- a/packages/leann-core/src/leann/api.py +++ b/packages/leann-core/src/leann/api.py @@ -32,6 +32,7 @@ def _compute_embeddings(chunks: List[str], model_name: str) -> np.ndarray: else: from sentence_transformers import SentenceTransformer model = SentenceTransformer(model_name) + model = model.half() print(f"INFO: Computing embeddings for {len(chunks)} chunks using SentenceTransformer model '{model_name}'...") embeddings = model.encode(chunks, show_progress_bar=True)