TBNilles/LEANN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rm useless

Browse Source
This commit is contained in:
yichuan520030910320
2025-07-06 06:47:20 +00:00
parent af0959818d
commit 95a653993a
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/main_cli_example.py
View File

@@ -23,7 +23,7 @@ file_extractor: dict[str, BaseReader] = {
".xlsx": reader, ".xlsx": reader,
} }
node_parser = DoclingNodeParser( 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...") print("Loading documents...")
documents = SimpleDirectoryReader( documents = SimpleDirectoryReader(

1
packages/leann-core/src/leann/api.py
View File

@@ -32,6 +32,7 @@ def _compute_embeddings(chunks: List[str], model_name: str) -> np.ndarray:
else: else:
from sentence_transformers import SentenceTransformer from sentence_transformers import SentenceTransformer
model = SentenceTransformer(model_name) model = SentenceTransformer(model_name)
model = model.half()
print(f"INFO: Computing embeddings for {len(chunks)} chunks using SentenceTransformer model '{model_name}'...") print(f"INFO: Computing embeddings for {len(chunks)} chunks using SentenceTransformer model '{model_name}'...")
embeddings = model.encode(chunks, show_progress_bar=True) embeddings = model.encode(chunks, show_progress_bar=True)