Feat: dataflow supports Spreadsheet and Word processor document (#9996)

### What problem does this PR solve?

Dataflow supports Spreadsheet and Word processor document

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

rag/llm/embedding_model.py

@@ -751,6 +751,8 @@ class SILICONFLOWEmbed(Base):
         token_count = 0
         for i in range(0, len(texts), batch_size):
             texts_batch = texts[i : i + batch_size]
+            texts_batch = [" " if not text.strip() else text for text in texts_batch]
+
             payload = {
                 "model": self.model_name,
                 "input": texts_batch,
@@ -935,7 +937,7 @@ class GiteeEmbed(SILICONFLOWEmbed):
         if not base_url:
             base_url = "https://ai.gitee.com/v1/embeddings"
         super().__init__(key, model_name, base_url)
-        
+
 class DeepInfraEmbed(OpenAIEmbed):
     _FACTORY_NAME = "DeepInfra"
 
@@ -951,4 +953,4 @@ class Ai302Embed(Base):
     def __init__(self, key, model_name, base_url="https://api.302.ai/v1/embeddings"):
         if not base_url:
             base_url = "https://api.302.ai/v1/embeddings"
-        super().__init__(key, model_name, base_url)
+        super().__init__(key, model_name, base_url)