Feat: support vision llm for gpustack (#6636)

### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/6138

This PR is going to support vision llm for gpustack, modify url path
from `/v1-openai` to `/v1`

### Type of change

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

rag/llm/tts_model.py

@@ -378,7 +378,7 @@ class GPUStackTTS:
         }
 
         response = requests.post(
-            f"{self.base_url}/v1-openai/audio/speech",
+            f"{self.base_url}/v1/audio/speech",
             headers=self.headers,
             json=payload,
             stream=stream