diff --git a/.env.template b/.env.template
index 2fb5ff649..88d780ef8 100644
--- a/.env.template
+++ b/.env.template
@@ -7,6 +7,10 @@
 ## For example, to disable coding related features, uncomment the next line
 # DISABLED_COMMAND_CATEGORIES=   
 
+#*******************************************************************#
+#**                        Webserver Port                         **#
+#*******************************************************************#
+WEB_SERVER_PORT=7860
 
 #*******************************************************************#
 #***                       LLM PROVIDER                          ***#
@@ -17,6 +21,7 @@
 #*******************************************************************#
 #**                         LLM MODELS                            **#
 #*******************************************************************#
+# LLM_MODEL, see /pilot/configs/model_config.LLM_MODEL_CONFIG
 LLM_MODEL=vicuna-13b
 MODEL_SERVER=http://127.0.0.1:8000
 LIMIT_MODEL_CONCURRENCY=5
@@ -98,15 +103,20 @@ VECTOR_STORE_TYPE=Chroma
 #MILVUS_SECURE=
 
 
+#*******************************************************************#
+#**                  WebServer Language Support                   **#
+#*******************************************************************#
 LANGUAGE=en
 #LANGUAGE=zh
 
 
 #*******************************************************************#
-# **    PROXY_SERVER
+# **    PROXY_SERVER (openai interface | chatGPT proxy service), use chatGPT as your LLM.
+# ** if your server can visit openai, please set PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
+# ** else if you have a chatgpt proxy server, you can set PROXY_SERVER_URL={your-proxy-serverip:port/xxx}
 #*******************************************************************#
-PROXY_API_KEY=
-PROXY_SERVER_URL=http://127.0.0.1:3000/proxy_address
+PROXY_API_KEY={your-openai-sk}
+PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
 
 
 #*******************************************************************#
diff --git a/pilot/configs/config.py b/pilot/configs/config.py
index 971be9170..01f5a1898 100644
--- a/pilot/configs/config.py
+++ b/pilot/configs/config.py
@@ -17,8 +17,9 @@ class Config(metaclass=Singleton):
     def __init__(self) -> None:
         """Initialize the Config class"""
 
-        # Gradio language version: en, cn
+        # Gradio language version: en, zh
         self.LANGUAGE = os.getenv("LANGUAGE", "en")
+        self.WEB_SERVER_PORT = int(os.getenv("WEB_SERVER_PORT", 7860))
 
         self.debug_mode = False
         self.skip_reprompt = False
diff --git a/pilot/server/llmserver.py b/pilot/server/llmserver.py
index d2730e0d5..a1dba135b 100644
--- a/pilot/server/llmserver.py
+++ b/pilot/server/llmserver.py
@@ -84,6 +84,11 @@ class ModelWorker:
         return get_embeddings(self.model, self.tokenizer, prompt)
 
 
+model_path = LLM_MODEL_CONFIG[CFG.LLM_MODEL]
+worker = ModelWorker(
+    model_path=model_path, model_name=CFG.LLM_MODEL, device=DEVICE, num_gpus=1
+)
+
 app = FastAPI()
 
 
@@ -157,11 +162,4 @@ def embeddings(prompt_request: EmbeddingRequest):
 
 
 if __name__ == "__main__":
-    model_path = LLM_MODEL_CONFIG[CFG.LLM_MODEL]
-    print(model_path, DEVICE)
-
-    worker = ModelWorker(
-        model_path=model_path, model_name=CFG.LLM_MODEL, device=DEVICE, num_gpus=1
-    )
-
     uvicorn.run(app, host="0.0.0.0", port=CFG.MODEL_PORT, log_level="info")
diff --git a/pilot/server/webserver.py b/pilot/server/webserver.py
index 270f3b681..81270ff79 100644
--- a/pilot/server/webserver.py
+++ b/pilot/server/webserver.py
@@ -658,7 +658,7 @@ def signal_handler(sig, frame):
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--host", type=str, default="0.0.0.0")
-    parser.add_argument("--port", type=int)
+    parser.add_argument("--port", type=int, default=CFG.WEB_SERVER_PORT)
     parser.add_argument("--concurrency-count", type=int, default=10)
     parser.add_argument(
         "--model-list-mode", type=str, default="once", choices=["once", "reload"]