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/sequence2txt_model.py

@@ -198,8 +198,8 @@ class GPUStackSeq2txt(Base):
     def __init__(self, key, model_name, base_url):
         if not base_url:
             raise ValueError("url cannot be None")
-        if base_url.split("/")[-1] != "v1-openai":
-            base_url = os.path.join(base_url, "v1-openai")
+        if base_url.split("/")[-1] != "v1":
+            base_url = os.path.join(base_url, "v1")
         self.base_url = base_url
         self.model_name = model_name
         self.key = key