diff --git a/README.md b/README.md
index b45f1716..f319a86e 100644
--- a/README.md
+++ b/README.md
@@ -195,7 +195,7 @@ $ python startup.py -a
 [![Telegram](https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white "langchain-chatglm")](https://t.me/+RjliQ3jnJ1YyN2E9)
 
 ### 项目交流群
-<img src="img/qr_code_104.jpg" alt="二维码" width="300" />
+<img src="img/qr_code_105.jpg" alt="二维码" width="300" />
 
 🎉 Langchain-Chatchat 项目微信交流群，如果你也对本项目感兴趣，欢迎加入群聊参与讨论交流。
 
diff --git a/configs/model_config.py.example b/configs/model_config.py.example
index 25f41bb4..af8f35ae 100644
--- a/configs/model_config.py.example
+++ b/configs/model_config.py.example
@@ -81,7 +81,7 @@ ONLINE_LLM_MODEL = {
 
     # 火山方舟 API，文档参考 https://www.volcengine.com/docs/82379
     "fangzhou-api": {
-        "version": "chatglm-6b-model",
+        "version": "", # 对应火山方舟的 endpoint_id
         "version_url": "",
         "api_key": "",
         "secret_key": "",
diff --git a/img/qr_code_105.jpg b/img/qr_code_105.jpg
new file mode 100644
index 00000000..b80c4f18
Binary files /dev/null and b/img/qr_code_105.jpg differ
diff --git a/requirements.txt b/requirements.txt
index f5d0212c..0fdafc66 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -43,7 +43,7 @@ llama-index==0.9.35
 # beautifulsoup4==4.12.2
 # pysrt==1.1.2
 # dashscope==1.13.6 # qwen
-# volcengine==1.0.119 # fangzhou
+# volcengine==1.0.134 # fangzhou
 # uncomment libs if you want to use corresponding vector store
 # pymilvus==2.3.6
 # psycopg2==2.9.9
diff --git a/requirements_api.txt b/requirements_api.txt
index fbb00357..e8962e00 100644
--- a/requirements_api.txt
+++ b/requirements_api.txt
@@ -50,7 +50,7 @@ pyjwt==2.8.0
 # duckduckgo-search~=3.9.9
 # metaphor-python~=0.1.23
 
-# volcengine>=1.0.119
+# volcengine>=1.0.134
 # pymilvus==2.3.6
 # psycopg2==2.9.9
 # pgvector>=0.2.4
diff --git a/requirements_lite.txt b/requirements_lite.txt
index dc420c62..21c869e2 100644
--- a/requirements_lite.txt
+++ b/requirements_lite.txt
@@ -30,7 +30,7 @@ youtube-search~=2.1.2
 duckduckgo-search~=3.9.9
 metaphor-python~=0.1.23
 watchdog~=3.0.0
-# volcengine>=1.0.119
+# volcengine>=1.0.134
 # pymilvus>=2.3.4
 # psycopg2==2.9.9
 # pgvector>=0.2.4
diff --git a/server/model_workers/fangzhou.py b/server/model_workers/fangzhou.py
index fdb50a1c..cd9278d5 100644
--- a/server/model_workers/fangzhou.py
+++ b/server/model_workers/fangzhou.py
@@ -24,9 +24,8 @@ class FangZhouWorker(ApiModelWorker):
         kwargs.setdefault("context_len", 16384)
         super().__init__(**kwargs)
         self.version = version
-
     def do_chat(self, params: ApiChatParams) -> Dict:
-        from volcengine.maas import MaasService
+        from volcengine.maas.v2 import MaasService
 
         params.load_config(self.model_names[0])
         maas = MaasService('maas-api.ml-platform-cn-beijing.volces.com', 'cn-beijing')
@@ -35,9 +34,6 @@ class FangZhouWorker(ApiModelWorker):
 
         # document: "https://www.volcengine.com/docs/82379/1099475"
         req = {
-            "model": {
-                "name": params.version,
-            },
             "parameters": {
                 # 这里的参数仅为示例，具体可用的参数请参考具体模型的 API 说明
                 "max_new_tokens": params.max_tokens,
@@ -49,24 +45,24 @@ class FangZhouWorker(ApiModelWorker):
         text = ""
         if log_verbose:
             self.logger.info(f'{self.__class__.__name__}:maas: {maas}')
-        for resp in maas.stream_chat(req):
-            if error := resp.error:
-                if error.code_n > 0:
-                    data = {
-                        "error_code": error.code_n,
-                        "text": error.message,
-                        "error": {
-                            "message": error.message,
-                            "type": "invalid_request_error",
-                            "param": None,
-                            "code": None,
-                        }
+        for resp in maas.stream_chat(params.version, unicode_escape_data(req)):
+            error = resp.error
+            if error and error.code_n > 0:
+                data = {
+                    "error_code": error.code_n,
+                    "text": error.message,
+                    "error": {
+                        "message": error.message,
+                        "type": "invalid_request_error",
+                        "param": None,
+                        "code": None,
                     }
-                    self.logger.error(f"请求方舟 API 时发生错误：{data}")
-                    yield data
-                elif chunk := resp.choice.message.content:
-                    text += chunk
-                    yield {"error_code": 0, "text": text}
+                }
+                self.logger.error(f"请求方舟 API 时发生错误：{data}")
+                yield data
+            elif chunk := resp.choices and resp.choices[0].message.content:
+                text += chunk
+                yield {"error_code": 0, "text": text}
             else:
                 data = {
                     "error_code": 500,
@@ -91,6 +87,16 @@ class FangZhouWorker(ApiModelWorker):
         )
 
 
+def unicode_escape_data(data):
+    if isinstance(data, str):
+        return data.encode('unicode_escape').decode('ascii')
+    elif isinstance(data, dict):
+        return {key: unicode_escape_data(value) for key, value in data.items()}
+    elif isinstance(data, list):
+        return [unicode_escape_data(item) for item in data]
+    else:
+        return data
+
 if __name__ == "__main__":
     import uvicorn
     from server.utils import MakeFastAPIOffline
@@ -102,4 +108,4 @@ if __name__ == "__main__":
     )
     sys.modules["fastchat.serve.model_worker"].worker = worker
     MakeFastAPIOffline(app)
-    uvicorn.run(app, port=21005)
+    uvicorn.run(app, port=21005)
\ No newline at end of file