fix batch size error for qianwen embedding (#2431)

### What problem does this PR solve?

#2402

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

rag/llm/embedding_model.py

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