pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 12:32:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update embedding_model.py (#8836)

Browse Source 
### What problem does this PR solve?

Remove useless covert for bge encode_queries

### Type of change

- [x] Performance Improvement
This commit is contained in:
Stephen Hu
2025-07-15 14:04:58 +08:00
committed by GitHub
parent 51a8604dcb
commit 5fa6f2f151
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rag/llm/embedding_model.py
View File

@ -114,7 +114,7 @@ class DefaultEmbedding(Base):
def encode_queries(self, text: str):
token_count = num_tokens_from_string(text)
return self._model.encode_queries([text]).tolist()[0], token_count
return self._model.encode_queries([text], convert_to_numpy=False)[0][0].cpu().numpy(), token_count
class OpenAIEmbed(Base):