Fix:wrong describe_with_prompt() in ollama (#10963)

### What problem does this PR solve?

change:
wrong describe_with_prompt() in ollama

### Type of change

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

rag/llm/cv_model.py

@@ -539,7 +539,7 @@ class OllamaCV(Base):
         try:
             response = self.client.generate(
                 model=self.model_name,
-                prompt=vision_prompt[0]["content"][0]["text"],
+                prompt=vision_prompt[0]["content"],
                 images=[image],
             )
             ans = response["response"].strip()