Feat:VolcEngine Model type add IMAGE2TEXT (#10629)

### What problem does this PR solve?
issue:
[#9004](https://github.com/infiniflow/ragflow/issues/9004)
change:
VolcEngine Model type add IMAGE2TEXT

### Type of change

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

conf/llm_factories.json

@@ -971,31 +971,9 @@
         {
             "name": "VolcEngine",
             "logo": "",
-            "tags": "LLM, TEXT EMBEDDING",
+            "tags": "LLM, TEXT EMBEDDING, IMAGE2TEXT",
             "status": "1",
-            "llm": [
-                {
-                    "llm_name": "Doubao-pro-128k",
-                    "tags": "LLM,CHAT,128k",
-                    "max_tokens": 131072,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "Doubao-pro-32k",
-                    "tags": "LLM,CHAT,32k",
-                    "max_tokens": 32768,
-                    "model_type": "chat",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "Doubao-pro-4k",
-                    "tags": "LLM,CHAT,4k",
-                    "max_tokens": 4096,
-                    "model_type": "chat",
-                    "is_tools": true
-                }
-            ]
+            "llm": []
         },
         {
             "name": "BaiChuan",

rag/llm/cv_model.py

@@ -254,6 +254,17 @@ class StepFunCV(GptV4):
         self.lang = lang
         Base.__init__(self, **kwargs)
 
+class VolcEngineCV(GptV4):
+    _FACTORY_NAME = "VolcEngine"
+
+    def __init__(self, key, model_name, lang="Chinese", base_url="https://ark.cn-beijing.volces.com/api/v3", **kwargs):
+        if not base_url:
+            base_url = "https://ark.cn-beijing.volces.com/api/v3"
+        ark_api_key = json.loads(key).get("ark_api_key", "")
+        self.client = OpenAI(api_key=ark_api_key, base_url=base_url)
+        self.model_name = json.loads(key).get("ep_id", "") + json.loads(key).get("endpoint_id", "")
+        self.lang = lang
+        Base.__init__(self, **kwargs)
 
 class LmStudioCV(GptV4):
     _FACTORY_NAME = "LM-Studio"

web/src/pages/user-setting/setting-model/volcengine-modal/index.tsx

@@ -81,6 +81,7 @@ const VolcEngineModal = ({
           <Select placeholder={t('modelTypeMessage')}>
             <Option value="chat">chat</Option>
             <Option value="embedding">embedding</Option>
+            <Option value="image2text">image2text</Option>
           </Select>
         </Form.Item>
         <Form.Item<FieldType>