gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix batch size error for qianwen embedding (#2431)

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

#2402

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu 2024-09-14 14:40:57 +08:00 • committed by GitHub
parent d3262ca378
commit 3044cb85fd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
rag/llm/embedding_model.py
View file

@ -155,6 +155,7 @@ class QWenEmbed(Base):
def encode(self, texts: list, batch_size=10): def encode(self, texts: list, batch_size=10):
import dashscope import dashscope
batch_size = min(batch_size, 4)
try: try:
res = [] res = []
token_count = 0 token_count = 0